fizyr / keras-maskrcnn Goto Github PK
View Code? Open in Web Editor NEWKeras implementation of MaskRCNN object detection.
License: Apache License 2.0
keras-maskrcnn's Issues
Incorrect masks shape?
I feed the following images to network:
Image batch shape: (8, 768, 768, 3)
outputs = model.predict_on_batch(image)
boxes = outputs[-4]
scores = outputs[-3]
labels = outputs[-2]
masks = outputs[-1]
Detections shape: (8, 100, 4) (8, 100) (8, 100) (1, 100, 28, 28, 1)
I expect masks shape to be (8, 100, 28, 28, 1)
Am I missing something?
Faster retraining with new classes.
How to add more classes to predict without retraining whole network from ImageNet weights? May be it will be useful to save backbone, regression, classification and mask subnet weights separately.
mask size and position
Where is the origin of the mask: in the upper left corner of the image or bbox? And what is the size of the mask: the size of the picture or the size of the bbox?
How does the classification loss function work?
Are images for classification considered after cropping the picture by bounding box and after applying a mask?
Train fails
...
Epoch 00010: saving model to /var/tmp/bat/snapshots/resnet50_csv_10.h5
1564 instances of class java-classic with average precision: 0.9435
1650 instances of class vogue-menthe with average precision: 0.9563
mAP: 0.9499
Epoch 11/50
10000/10000 [==============================] - 7936s 794ms/step - loss: 0.2792 - regression_loss: 0.1874 - classification_loss: 0.0191 - masks_loss: 0.0727
Epoch 00011: saving model to /var/tmp/bat/snapshots/resnet50_csv_11.h5
Traceback (most recent call last):
File "/home/michael/keras-maskrcnn/keras_maskrcnn/bin/train.py", line 313, in <module>
main()
File "/home/michael/keras-maskrcnn/keras_maskrcnn/bin/train.py", line 309, in main
max_queue_size=1,
File "/home/michael/.local/lib/python3.5/site-packages/keras/legacy/interfaces.py", line 91, in wrapper
return func(*args, **kwargs)
File "/home/michael/.local/lib/python3.5/site-packages/keras/engine/training.py", line 1418, in fit_generator
initial_epoch=initial_epoch)
File "/home/michael/.local/lib/python3.5/site-packages/keras/engine/training_generator.py", line 251, in fit_generator
callbacks.on_epoch_end(epoch, epoch_logs)
File "/home/michael/.local/lib/python3.5/site-packages/keras/callbacks.py", line 79, in on_epoch_end
callback.on_epoch_end(epoch, logs)
File "/home/michael/.local/lib/python3.5/site-packages/keras_retinanet/callbacks/common.py", line 31, in on_epoch_end
self.callback.on_epoch_end(epoch, logs=logs)
File "/home/michael/keras-maskrcnn/keras_maskrcnn/bin/../../keras_maskrcnn/callbacks/eval.py", line 66, in on_epoch_end
save_path=self.save_path
File "/home/michael/keras-maskrcnn/keras_maskrcnn/bin/../../keras_maskrcnn/utils/eval.py", line 212, in evaluate
mask = cv2.resize(mask, (box[2] - box[0], box[3] - box[1]))
cv2.error: OpenCV(3.4.3) /io/opencv/modules/imgproc/src/resize.cpp:4045: error: (-215:Assertion failed) !dsize.empty() || (inv_scale_x > 0 && inv_scale_y > 0) in function 'resize'
Training using polygons
Is it possible to make a training using polygons vertexes coordinates instead?
ModuleNotFoundError: No module named 'keras_retinanet.utils.config'
Hi, i got the problem of 'ModuleNotFoundError: No module named 'keras_retinanet.utils.config'
any help?
How to train a model on my own datasets with pretrained resnet152 model?
Thanks for your great codes! I want to train my own data with pretrained model when the backbone is resnet152. But I can not find the Corresponding model.May you give me some advice?Thank you!
there is a issue when i want to run the example, ‘No module named 'keras_maskrcnn'‘，what can i do for this?
ResNet50MaskRCNN doesn't appear to be notebook
Hello,
It seems like there is an issue while opening this ResNet50MaskRCNN file. Could you please push this file to git again?
Thanks!
How to Predict on Batch of Images
Hi
Thank you for the amazing work. Could you please specify how to do predictions on batches of images ?
Callbacks removed from train.py in latest 2 commits?
It appears to me (although I am new to Keras) that the callbacks argument has been inadvertently removed from the call to fit_generator in train.py in the latest two commits. Or maybe it is intentional and I am not calling train.py correctly? In my case, I could not save snapshots after each epoch unless I restored the "callbacks=callbacks," line in the argument list for fit_generator. Thanks.
Could you please share your trained model or an open pre-trained model ?
as we konw , a pre-trained model could save a lot of time when training "custom_data".
could you please provide one ?
Thanks very much.
Saving most recent weights
Is there an option to keep the most recent weights and erase previous weights similar to the max to keep option as it causes memory issues when trained for more epochs.
How to train the model to detecte objects only?
How can I close the branch used to Object Segmentation task?I only have images and the corresponding border and category information.Hence how to modify the codes to only detecte the objects?Thanks!
Train error
When csv file do not contain any mask, this error rising:
Using TensorFlow backend.
2018-11-05 17:07:01.724184: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
2018-11-05 17:07:02.346433: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:964] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2018-11-05 17:07:02.347048: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1411] Found device 0 with properties:
name: GeForce GTX 1080 major: 6 minor: 1 memoryClockRate(GHz): 1.7335
pciBusID: 0000:01:00.0
totalMemory: 7.92GiB freeMemory: 7.80GiB
2018-11-05 17:07:02.347075: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1490] Adding visible gpu devices: 0
2018-11-05 17:07:02.531325: I tensorflow/core/common_runtime/gpu/gpu_device.cc:971] Device interconnect StreamExecutor with strength 1 edge matrix:
2018-11-05 17:07:02.531370: I tensorflow/core/common_runtime/gpu/gpu_device.cc:977] 0
2018-11-05 17:07:02.531375: I tensorflow/core/common_runtime/gpu/gpu_device.cc:990] 0: N
2018-11-05 17:07:02.531522: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1103] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 7528 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1080, pci bus id: 0000:01:00.0, compute capability: 6.1)
Creating model, this may take a second...
../keras-maskrcnn/keras_maskrcnn/bin/train.py:79: UserWarning: Output "filtered_detections" missing from loss dictionary. We assume this was done on purpose, and we will not be expecting any data to be passed to "filtered_detections" during training.
optimizer=keras.optimizers.adam(lr=1e-5, clipnorm=0.001)
../keras-maskrcnn/keras_maskrcnn/bin/train.py:79: UserWarning: Output "mask_submodel" missing from loss dictionary. We assume this was done on purpose, and we will not be expecting any data to be passed to "mask_submodel" during training.
optimizer=keras.optimizers.adam(lr=1e-5, clipnorm=0.001)
__________________________________________________________________________________________________
Layer (type) Output Shape Param # Connected to
==================================================================================================
image (InputLayer) (None, None, None, 3 0
__________________________________________________________________________________________________
padding_conv1 (ZeroPadding2D) (None, None, None, 3 0 image[0][0]
__________________________________________________________________________________________________
conv1 (Conv2D) (None, None, None, 6 9408 padding_conv1[0][0]
__________________________________________________________________________________________________
bn_conv1 (BatchNormalization) (None, None, None, 6 256 conv1[0][0]
__________________________________________________________________________________________________
conv1_relu (Activation) (None, None, None, 6 0 bn_conv1[0][0]
__________________________________________________________________________________________________
pool1 (MaxPooling2D) (None, None, None, 6 0 conv1_relu[0][0]
__________________________________________________________________________________________________
res2a_branch2a (Conv2D) (None, None, None, 6 4096 pool1[0][0]
__________________________________________________________________________________________________
bn2a_branch2a (BatchNormalizati (None, None, None, 6 256 res2a_branch2a[0][0]
__________________________________________________________________________________________________
res2a_branch2a_relu (Activation (None, None, None, 6 0 bn2a_branch2a[0][0]
__________________________________________________________________________________________________
padding2a_branch2b (ZeroPadding (None, None, None, 6 0 res2a_branch2a_relu[0][0]
__________________________________________________________________________________________________
res2a_branch2b (Conv2D) (None, None, None, 6 36864 padding2a_branch2b[0][0]
__________________________________________________________________________________________________
bn2a_branch2b (BatchNormalizati (None, None, None, 6 256 res2a_branch2b[0][0]
__________________________________________________________________________________________________
res2a_branch2b_relu (Activation (None, None, None, 6 0 bn2a_branch2b[0][0]
__________________________________________________________________________________________________
res2a_branch2c (Conv2D) (None, None, None, 2 16384 res2a_branch2b_relu[0][0]
__________________________________________________________________________________________________
res2a_branch1 (Conv2D) (None, None, None, 2 16384 pool1[0][0]
__________________________________________________________________________________________________
bn2a_branch2c (BatchNormalizati (None, None, None, 2 1024 res2a_branch2c[0][0]
__________________________________________________________________________________________________
bn2a_branch1 (BatchNormalizatio (None, None, None, 2 1024 res2a_branch1[0][0]
__________________________________________________________________________________________________
res2a (Add) (None, None, None, 2 0 bn2a_branch2c[0][0]
bn2a_branch1[0][0]
__________________________________________________________________________________________________
res2a_relu (Activation) (None, None, None, 2 0 res2a[0][0]
__________________________________________________________________________________________________
res2b_branch2a (Conv2D) (None, None, None, 6 16384 res2a_relu[0][0]
__________________________________________________________________________________________________
bn2b_branch2a (BatchNormalizati (None, None, None, 6 256 res2b_branch2a[0][0]
__________________________________________________________________________________________________
res2b_branch2a_relu (Activation (None, None, None, 6 0 bn2b_branch2a[0][0]
__________________________________________________________________________________________________
padding2b_branch2b (ZeroPadding (None, None, None, 6 0 res2b_branch2a_relu[0][0]
__________________________________________________________________________________________________
res2b_branch2b (Conv2D) (None, None, None, 6 36864 padding2b_branch2b[0][0]
__________________________________________________________________________________________________
bn2b_branch2b (BatchNormalizati (None, None, None, 6 256 res2b_branch2b[0][0]
__________________________________________________________________________________________________
res2b_branch2b_relu (Activation (None, None, None, 6 0 bn2b_branch2b[0][0]
__________________________________________________________________________________________________
res2b_branch2c (Conv2D) (None, None, None, 2 16384 res2b_branch2b_relu[0][0]
__________________________________________________________________________________________________
bn2b_branch2c (BatchNormalizati (None, None, None, 2 1024 res2b_branch2c[0][0]
__________________________________________________________________________________________________
res2b (Add) (None, None, None, 2 0 bn2b_branch2c[0][0]
res2a_relu[0][0]
__________________________________________________________________________________________________
res2b_relu (Activation) (None, None, None, 2 0 res2b[0][0]
__________________________________________________________________________________________________
res2c_branch2a (Conv2D) (None, None, None, 6 16384 res2b_relu[0][0]
__________________________________________________________________________________________________
bn2c_branch2a (BatchNormalizati (None, None, None, 6 256 res2c_branch2a[0][0]
__________________________________________________________________________________________________
res2c_branch2a_relu (Activation (None, None, None, 6 0 bn2c_branch2a[0][0]
__________________________________________________________________________________________________
padding2c_branch2b (ZeroPadding (None, None, None, 6 0 res2c_branch2a_relu[0][0]
__________________________________________________________________________________________________
res2c_branch2b (Conv2D) (None, None, None, 6 36864 padding2c_branch2b[0][0]
__________________________________________________________________________________________________
bn2c_branch2b (BatchNormalizati (None, None, None, 6 256 res2c_branch2b[0][0]
__________________________________________________________________________________________________
res2c_branch2b_relu (Activation (None, None, None, 6 0 bn2c_branch2b[0][0]
__________________________________________________________________________________________________
res2c_branch2c (Conv2D) (None, None, None, 2 16384 res2c_branch2b_relu[0][0]
__________________________________________________________________________________________________
bn2c_branch2c (BatchNormalizati (None, None, None, 2 1024 res2c_branch2c[0][0]
__________________________________________________________________________________________________
res2c (Add) (None, None, None, 2 0 bn2c_branch2c[0][0]
res2b_relu[0][0]
__________________________________________________________________________________________________
res2c_relu (Activation) (None, None, None, 2 0 res2c[0][0]
__________________________________________________________________________________________________
res3a_branch2a (Conv2D) (None, None, None, 1 32768 res2c_relu[0][0]
__________________________________________________________________________________________________
bn3a_branch2a (BatchNormalizati (None, None, None, 1 512 res3a_branch2a[0][0]
__________________________________________________________________________________________________
res3a_branch2a_relu (Activation (None, None, None, 1 0 bn3a_branch2a[0][0]
__________________________________________________________________________________________________
padding3a_branch2b (ZeroPadding (None, None, None, 1 0 res3a_branch2a_relu[0][0]
__________________________________________________________________________________________________
res3a_branch2b (Conv2D) (None, None, None, 1 147456 padding3a_branch2b[0][0]
__________________________________________________________________________________________________
bn3a_branch2b (BatchNormalizati (None, None, None, 1 512 res3a_branch2b[0][0]
__________________________________________________________________________________________________
res3a_branch2b_relu (Activation (None, None, None, 1 0 bn3a_branch2b[0][0]
__________________________________________________________________________________________________
res3a_branch2c (Conv2D) (None, None, None, 5 65536 res3a_branch2b_relu[0][0]
__________________________________________________________________________________________________
res3a_branch1 (Conv2D) (None, None, None, 5 131072 res2c_relu[0][0]
__________________________________________________________________________________________________
bn3a_branch2c (BatchNormalizati (None, None, None, 5 2048 res3a_branch2c[0][0]
__________________________________________________________________________________________________
bn3a_branch1 (BatchNormalizatio (None, None, None, 5 2048 res3a_branch1[0][0]
__________________________________________________________________________________________________
res3a (Add) (None, None, None, 5 0 bn3a_branch2c[0][0]
bn3a_branch1[0][0]
__________________________________________________________________________________________________
res3a_relu (Activation) (None, None, None, 5 0 res3a[0][0]
__________________________________________________________________________________________________
res3b_branch2a (Conv2D) (None, None, None, 1 65536 res3a_relu[0][0]
__________________________________________________________________________________________________
bn3b_branch2a (BatchNormalizati (None, None, None, 1 512 res3b_branch2a[0][0]
__________________________________________________________________________________________________
res3b_branch2a_relu (Activation (None, None, None, 1 0 bn3b_branch2a[0][0]
__________________________________________________________________________________________________
padding3b_branch2b (ZeroPadding (None, None, None, 1 0 res3b_branch2a_relu[0][0]
__________________________________________________________________________________________________
res3b_branch2b (Conv2D) (None, None, None, 1 147456 padding3b_branch2b[0][0]
__________________________________________________________________________________________________
bn3b_branch2b (BatchNormalizati (None, None, None, 1 512 res3b_branch2b[0][0]
__________________________________________________________________________________________________
res3b_branch2b_relu (Activation (None, None, None, 1 0 bn3b_branch2b[0][0]
__________________________________________________________________________________________________
res3b_branch2c (Conv2D) (None, None, None, 5 65536 res3b_branch2b_relu[0][0]
__________________________________________________________________________________________________
bn3b_branch2c (BatchNormalizati (None, None, None, 5 2048 res3b_branch2c[0][0]
__________________________________________________________________________________________________
res3b (Add) (None, None, None, 5 0 bn3b_branch2c[0][0]
res3a_relu[0][0]
__________________________________________________________________________________________________
res3b_relu (Activation) (None, None, None, 5 0 res3b[0][0]
__________________________________________________________________________________________________
res3c_branch2a (Conv2D) (None, None, None, 1 65536 res3b_relu[0][0]
__________________________________________________________________________________________________
bn3c_branch2a (BatchNormalizati (None, None, None, 1 512 res3c_branch2a[0][0]
__________________________________________________________________________________________________
res3c_branch2a_relu (Activation (None, None, None, 1 0 bn3c_branch2a[0][0]
__________________________________________________________________________________________________
padding3c_branch2b (ZeroPadding (None, None, None, 1 0 res3c_branch2a_relu[0][0]
__________________________________________________________________________________________________
res3c_branch2b (Conv2D) (None, None, None, 1 147456 padding3c_branch2b[0][0]
__________________________________________________________________________________________________
bn3c_branch2b (BatchNormalizati (None, None, None, 1 512 res3c_branch2b[0][0]
__________________________________________________________________________________________________
res3c_branch2b_relu (Activation (None, None, None, 1 0 bn3c_branch2b[0][0]
__________________________________________________________________________________________________
res3c_branch2c (Conv2D) (None, None, None, 5 65536 res3c_branch2b_relu[0][0]
__________________________________________________________________________________________________
bn3c_branch2c (BatchNormalizati (None, None, None, 5 2048 res3c_branch2c[0][0]
__________________________________________________________________________________________________
res3c (Add) (None, None, None, 5 0 bn3c_branch2c[0][0]
res3b_relu[0][0]
__________________________________________________________________________________________________
res3c_relu (Activation) (None, None, None, 5 0 res3c[0][0]
__________________________________________________________________________________________________
res3d_branch2a (Conv2D) (None, None, None, 1 65536 res3c_relu[0][0]
__________________________________________________________________________________________________
bn3d_branch2a (BatchNormalizati (None, None, None, 1 512 res3d_branch2a[0][0]
__________________________________________________________________________________________________
res3d_branch2a_relu (Activation (None, None, None, 1 0 bn3d_branch2a[0][0]
__________________________________________________________________________________________________
padding3d_branch2b (ZeroPadding (None, None, None, 1 0 res3d_branch2a_relu[0][0]
__________________________________________________________________________________________________
res3d_branch2b (Conv2D) (None, None, None, 1 147456 padding3d_branch2b[0][0]
__________________________________________________________________________________________________
bn3d_branch2b (BatchNormalizati (None, None, None, 1 512 res3d_branch2b[0][0]
__________________________________________________________________________________________________
res3d_branch2b_relu (Activation (None, None, None, 1 0 bn3d_branch2b[0][0]
__________________________________________________________________________________________________
res3d_branch2c (Conv2D) (None, None, None, 5 65536 res3d_branch2b_relu[0][0]
__________________________________________________________________________________________________
bn3d_branch2c (BatchNormalizati (None, None, None, 5 2048 res3d_branch2c[0][0]
__________________________________________________________________________________________________
res3d (Add) (None, None, None, 5 0 bn3d_branch2c[0][0]
res3c_relu[0][0]
__________________________________________________________________________________________________
res3d_relu (Activation) (None, None, None, 5 0 res3d[0][0]
__________________________________________________________________________________________________
res4a_branch2a (Conv2D) (None, None, None, 2 131072 res3d_relu[0][0]
__________________________________________________________________________________________________
bn4a_branch2a (BatchNormalizati (None, None, None, 2 1024 res4a_branch2a[0][0]
__________________________________________________________________________________________________
res4a_branch2a_relu (Activation (None, None, None, 2 0 bn4a_branch2a[0][0]
__________________________________________________________________________________________________
padding4a_branch2b (ZeroPadding (None, None, None, 2 0 res4a_branch2a_relu[0][0]
__________________________________________________________________________________________________
res4a_branch2b (Conv2D) (None, None, None, 2 589824 padding4a_branch2b[0][0]
__________________________________________________________________________________________________
bn4a_branch2b (BatchNormalizati (None, None, None, 2 1024 res4a_branch2b[0][0]
__________________________________________________________________________________________________
res4a_branch2b_relu (Activation (None, None, None, 2 0 bn4a_branch2b[0][0]
__________________________________________________________________________________________________
res4a_branch2c (Conv2D) (None, None, None, 1 262144 res4a_branch2b_relu[0][0]
__________________________________________________________________________________________________
res4a_branch1 (Conv2D) (None, None, None, 1 524288 res3d_relu[0][0]
__________________________________________________________________________________________________
bn4a_branch2c (BatchNormalizati (None, None, None, 1 4096 res4a_branch2c[0][0]
__________________________________________________________________________________________________
bn4a_branch1 (BatchNormalizatio (None, None, None, 1 4096 res4a_branch1[0][0]
__________________________________________________________________________________________________
res4a (Add) (None, None, None, 1 0 bn4a_branch2c[0][0]
bn4a_branch1[0][0]
__________________________________________________________________________________________________
res4a_relu (Activation) (None, None, None, 1 0 res4a[0][0]
__________________________________________________________________________________________________
res4b_branch2a (Conv2D) (None, None, None, 2 262144 res4a_relu[0][0]
__________________________________________________________________________________________________
bn4b_branch2a (BatchNormalizati (None, None, None, 2 1024 res4b_branch2a[0][0]
__________________________________________________________________________________________________
res4b_branch2a_relu (Activation (None, None, None, 2 0 bn4b_branch2a[0][0]
__________________________________________________________________________________________________
padding4b_branch2b (ZeroPadding (None, None, None, 2 0 res4b_branch2a_relu[0][0]
__________________________________________________________________________________________________
res4b_branch2b (Conv2D) (None, None, None, 2 589824 padding4b_branch2b[0][0]
__________________________________________________________________________________________________
bn4b_branch2b (BatchNormalizati (None, None, None, 2 1024 res4b_branch2b[0][0]
__________________________________________________________________________________________________
res4b_branch2b_relu (Activation (None, None, None, 2 0 bn4b_branch2b[0][0]
__________________________________________________________________________________________________
res4b_branch2c (Conv2D) (None, None, None, 1 262144 res4b_branch2b_relu[0][0]
__________________________________________________________________________________________________
bn4b_branch2c (BatchNormalizati (None, None, None, 1 4096 res4b_branch2c[0][0]
__________________________________________________________________________________________________
res4b (Add) (None, None, None, 1 0 bn4b_branch2c[0][0]
res4a_relu[0][0]
__________________________________________________________________________________________________
res4b_relu (Activation) (None, None, None, 1 0 res4b[0][0]
__________________________________________________________________________________________________
res4c_branch2a (Conv2D) (None, None, None, 2 262144 res4b_relu[0][0]
__________________________________________________________________________________________________
bn4c_branch2a (BatchNormalizati (None, None, None, 2 1024 res4c_branch2a[0][0]
__________________________________________________________________________________________________
res4c_branch2a_relu (Activation (None, None, None, 2 0 bn4c_branch2a[0][0]
__________________________________________________________________________________________________
padding4c_branch2b (ZeroPadding (None, None, None, 2 0 res4c_branch2a_relu[0][0]
__________________________________________________________________________________________________
res4c_branch2b (Conv2D) (None, None, None, 2 589824 padding4c_branch2b[0][0]
__________________________________________________________________________________________________
bn4c_branch2b (BatchNormalizati (None, None, None, 2 1024 res4c_branch2b[0][0]
__________________________________________________________________________________________________
res4c_branch2b_relu (Activation (None, None, None, 2 0 bn4c_branch2b[0][0]
__________________________________________________________________________________________________
res4c_branch2c (Conv2D) (None, None, None, 1 262144 res4c_branch2b_relu[0][0]
__________________________________________________________________________________________________
bn4c_branch2c (BatchNormalizati (None, None, None, 1 4096 res4c_branch2c[0][0]
__________________________________________________________________________________________________
res4c (Add) (None, None, None, 1 0 bn4c_branch2c[0][0]
res4b_relu[0][0]
__________________________________________________________________________________________________
res4c_relu (Activation) (None, None, None, 1 0 res4c[0][0]
__________________________________________________________________________________________________
res4d_branch2a (Conv2D) (None, None, None, 2 262144 res4c_relu[0][0]
__________________________________________________________________________________________________
bn4d_branch2a (BatchNormalizati (None, None, None, 2 1024 res4d_branch2a[0][0]
__________________________________________________________________________________________________
res4d_branch2a_relu (Activation (None, None, None, 2 0 bn4d_branch2a[0][0]
__________________________________________________________________________________________________
padding4d_branch2b (ZeroPadding (None, None, None, 2 0 res4d_branch2a_relu[0][0]
__________________________________________________________________________________________________
res4d_branch2b (Conv2D) (None, None, None, 2 589824 padding4d_branch2b[0][0]
__________________________________________________________________________________________________
bn4d_branch2b (BatchNormalizati (None, None, None, 2 1024 res4d_branch2b[0][0]
__________________________________________________________________________________________________
res4d_branch2b_relu (Activation (None, None, None, 2 0 bn4d_branch2b[0][0]
__________________________________________________________________________________________________
res4d_branch2c (Conv2D) (None, None, None, 1 262144 res4d_branch2b_relu[0][0]
__________________________________________________________________________________________________
bn4d_branch2c (BatchNormalizati (None, None, None, 1 4096 res4d_branch2c[0][0]
__________________________________________________________________________________________________
res4d (Add) (None, None, None, 1 0 bn4d_branch2c[0][0]
res4c_relu[0][0]
__________________________________________________________________________________________________
res4d_relu (Activation) (None, None, None, 1 0 res4d[0][0]
__________________________________________________________________________________________________
res4e_branch2a (Conv2D) (None, None, None, 2 262144 res4d_relu[0][0]
__________________________________________________________________________________________________
bn4e_branch2a (BatchNormalizati (None, None, None, 2 1024 res4e_branch2a[0][0]
__________________________________________________________________________________________________
res4e_branch2a_relu (Activation (None, None, None, 2 0 bn4e_branch2a[0][0]
__________________________________________________________________________________________________
padding4e_branch2b (ZeroPadding (None, None, None, 2 0 res4e_branch2a_relu[0][0]
__________________________________________________________________________________________________
res4e_branch2b (Conv2D) (None, None, None, 2 589824 padding4e_branch2b[0][0]
__________________________________________________________________________________________________
bn4e_branch2b (BatchNormalizati (None, None, None, 2 1024 res4e_branch2b[0][0]
__________________________________________________________________________________________________
res4e_branch2b_relu (Activation (None, None, None, 2 0 bn4e_branch2b[0][0]
__________________________________________________________________________________________________
res4e_branch2c (Conv2D) (None, None, None, 1 262144 res4e_branch2b_relu[0][0]
__________________________________________________________________________________________________
bn4e_branch2c (BatchNormalizati (None, None, None, 1 4096 res4e_branch2c[0][0]
__________________________________________________________________________________________________
res4e (Add) (None, None, None, 1 0 bn4e_branch2c[0][0]
res4d_relu[0][0]
__________________________________________________________________________________________________
res4e_relu (Activation) (None, None, None, 1 0 res4e[0][0]
__________________________________________________________________________________________________
res4f_branch2a (Conv2D) (None, None, None, 2 262144 res4e_relu[0][0]
__________________________________________________________________________________________________
bn4f_branch2a (BatchNormalizati (None, None, None, 2 1024 res4f_branch2a[0][0]
__________________________________________________________________________________________________
res4f_branch2a_relu (Activation (None, None, None, 2 0 bn4f_branch2a[0][0]
__________________________________________________________________________________________________
padding4f_branch2b (ZeroPadding (None, None, None, 2 0 res4f_branch2a_relu[0][0]
__________________________________________________________________________________________________
res4f_branch2b (Conv2D) (None, None, None, 2 589824 padding4f_branch2b[0][0]
__________________________________________________________________________________________________
bn4f_branch2b (BatchNormalizati (None, None, None, 2 1024 res4f_branch2b[0][0]
__________________________________________________________________________________________________
res4f_branch2b_relu (Activation (None, None, None, 2 0 bn4f_branch2b[0][0]
__________________________________________________________________________________________________
res4f_branch2c (Conv2D) (None, None, None, 1 262144 res4f_branch2b_relu[0][0]
__________________________________________________________________________________________________
bn4f_branch2c (BatchNormalizati (None, None, None, 1 4096 res4f_branch2c[0][0]
__________________________________________________________________________________________________
res4f (Add) (None, None, None, 1 0 bn4f_branch2c[0][0]
res4e_relu[0][0]
__________________________________________________________________________________________________
res4f_relu (Activation) (None, None, None, 1 0 res4f[0][0]
__________________________________________________________________________________________________
res5a_branch2a (Conv2D) (None, None, None, 5 524288 res4f_relu[0][0]
__________________________________________________________________________________________________
bn5a_branch2a (BatchNormalizati (None, None, None, 5 2048 res5a_branch2a[0][0]
__________________________________________________________________________________________________
res5a_branch2a_relu (Activation (None, None, None, 5 0 bn5a_branch2a[0][0]
__________________________________________________________________________________________________
padding5a_branch2b (ZeroPadding (None, None, None, 5 0 res5a_branch2a_relu[0][0]
__________________________________________________________________________________________________
res5a_branch2b (Conv2D) (None, None, None, 5 2359296 padding5a_branch2b[0][0]
__________________________________________________________________________________________________
bn5a_branch2b (BatchNormalizati (None, None, None, 5 2048 res5a_branch2b[0][0]
__________________________________________________________________________________________________
res5a_branch2b_relu (Activation (None, None, None, 5 0 bn5a_branch2b[0][0]
__________________________________________________________________________________________________
res5a_branch2c (Conv2D) (None, None, None, 2 1048576 res5a_branch2b_relu[0][0]
__________________________________________________________________________________________________
res5a_branch1 (Conv2D) (None, None, None, 2 2097152 res4f_relu[0][0]
__________________________________________________________________________________________________
bn5a_branch2c (BatchNormalizati (None, None, None, 2 8192 res5a_branch2c[0][0]
__________________________________________________________________________________________________
bn5a_branch1 (BatchNormalizatio (None, None, None, 2 8192 res5a_branch1[0][0]
__________________________________________________________________________________________________
res5a (Add) (None, None, None, 2 0 bn5a_branch2c[0][0]
bn5a_branch1[0][0]
__________________________________________________________________________________________________
res5a_relu (Activation) (None, None, None, 2 0 res5a[0][0]
__________________________________________________________________________________________________
res5b_branch2a (Conv2D) (None, None, None, 5 1048576 res5a_relu[0][0]
__________________________________________________________________________________________________
bn5b_branch2a (BatchNormalizati (None, None, None, 5 2048 res5b_branch2a[0][0]
__________________________________________________________________________________________________
res5b_branch2a_relu (Activation (None, None, None, 5 0 bn5b_branch2a[0][0]
__________________________________________________________________________________________________
padding5b_branch2b (ZeroPadding (None, None, None, 5 0 res5b_branch2a_relu[0][0]
__________________________________________________________________________________________________
res5b_branch2b (Conv2D) (None, None, None, 5 2359296 padding5b_branch2b[0][0]
__________________________________________________________________________________________________
bn5b_branch2b (BatchNormalizati (None, None, None, 5 2048 res5b_branch2b[0][0]
__________________________________________________________________________________________________
res5b_branch2b_relu (Activation (None, None, None, 5 0 bn5b_branch2b[0][0]
__________________________________________________________________________________________________
res5b_branch2c (Conv2D) (None, None, None, 2 1048576 res5b_branch2b_relu[0][0]
__________________________________________________________________________________________________
bn5b_branch2c (BatchNormalizati (None, None, None, 2 8192 res5b_branch2c[0][0]
__________________________________________________________________________________________________
res5b (Add) (None, None, None, 2 0 bn5b_branch2c[0][0]
res5a_relu[0][0]
__________________________________________________________________________________________________
res5b_relu (Activation) (None, None, None, 2 0 res5b[0][0]
__________________________________________________________________________________________________
res5c_branch2a (Conv2D) (None, None, None, 5 1048576 res5b_relu[0][0]
__________________________________________________________________________________________________
bn5c_branch2a (BatchNormalizati (None, None, None, 5 2048 res5c_branch2a[0][0]
__________________________________________________________________________________________________
res5c_branch2a_relu (Activation (None, None, None, 5 0 bn5c_branch2a[0][0]
__________________________________________________________________________________________________
padding5c_branch2b (ZeroPadding (None, None, None, 5 0 res5c_branch2a_relu[0][0]
__________________________________________________________________________________________________
res5c_branch2b (Conv2D) (None, None, None, 5 2359296 padding5c_branch2b[0][0]
__________________________________________________________________________________________________
bn5c_branch2b (BatchNormalizati (None, None, None, 5 2048 res5c_branch2b[0][0]
__________________________________________________________________________________________________
res5c_branch2b_relu (Activation (None, None, None, 5 0 bn5c_branch2b[0][0]
__________________________________________________________________________________________________
res5c_branch2c (Conv2D) (None, None, None, 2 1048576 res5c_branch2b_relu[0][0]
__________________________________________________________________________________________________
bn5c_branch2c (BatchNormalizati (None, None, None, 2 8192 res5c_branch2c[0][0]
__________________________________________________________________________________________________
res5c (Add) (None, None, None, 2 0 bn5c_branch2c[0][0]
res5b_relu[0][0]
__________________________________________________________________________________________________
res5c_relu (Activation) (None, None, None, 2 0 res5c[0][0]
__________________________________________________________________________________________________
C5_reduced (Conv2D) (None, None, None, 2 524544 res5c_relu[0][0]
__________________________________________________________________________________________________
P5_upsampled (UpsampleLike) (None, None, None, 2 0 C5_reduced[0][0]
res4f_relu[0][0]
__________________________________________________________________________________________________
C4_reduced (Conv2D) (None, None, None, 2 262400 res4f_relu[0][0]
__________________________________________________________________________________________________
P4_merged (Add) (None, None, None, 2 0 P5_upsampled[0][0]
C4_reduced[0][0]
__________________________________________________________________________________________________
P4_upsampled (UpsampleLike) (None, None, None, 2 0 P4_merged[0][0]
res3d_relu[0][0]
__________________________________________________________________________________________________
C3_reduced (Conv2D) (None, None, None, 2 131328 res3d_relu[0][0]
__________________________________________________________________________________________________
P6 (Conv2D) (None, None, None, 2 4718848 res5c_relu[0][0]
__________________________________________________________________________________________________
P3_merged (Add) (None, None, None, 2 0 P4_upsampled[0][0]
C3_reduced[0][0]
__________________________________________________________________________________________________
C6_relu (Activation) (None, None, None, 2 0 P6[0][0]
__________________________________________________________________________________________________
P3 (Conv2D) (None, None, None, 2 590080 P3_merged[0][0]
__________________________________________________________________________________________________
P4 (Conv2D) (None, None, None, 2 590080 P4_merged[0][0]
__________________________________________________________________________________________________
P5 (Conv2D) (None, None, None, 2 590080 C5_reduced[0][0]
__________________________________________________________________________________________________
P7 (Conv2D) (None, None, None, 2 590080 C6_relu[0][0]
__________________________________________________________________________________________________
regression_submodel (Model) (None, None, 4) 2443300 P3[0][0]
P4[0][0]
P5[0][0]
P6[0][0]
P7[0][0]
__________________________________________________________________________________________________
anchors_0 (Anchors) (None, None, 4) 0 P3[0][0]
__________________________________________________________________________________________________
anchors_1 (Anchors) (None, None, 4) 0 P4[0][0]
__________________________________________________________________________________________________
anchors_2 (Anchors) (None, None, 4) 0 P5[0][0]
__________________________________________________________________________________________________
anchors_3 (Anchors) (None, None, 4) 0 P6[0][0]
__________________________________________________________________________________________________
anchors_4 (Anchors) (None, None, 4) 0 P7[0][0]
__________________________________________________________________________________________________
regression (Concatenate) (None, None, 4) 0 regression_submodel[1][0]
regression_submodel[2][0]
regression_submodel[3][0]
regression_submodel[4][0]
regression_submodel[5][0]
__________________________________________________________________________________________________
anchors (Concatenate) (None, None, 4) 0 anchors_0[0][0]
anchors_1[0][0]
anchors_2[0][0]
anchors_3[0][0]
anchors_4[0][0]
__________________________________________________________________________________________________
classification_submodel (Model) (None, None, 97) 4372585 P3[0][0]
P4[0][0]
P5[0][0]
P6[0][0]
P7[0][0]
__________________________________________________________________________________________________
boxes (RegressBoxes) (None, None, 4) 0 anchors[0][0]
regression[0][0]
__________________________________________________________________________________________________
classification (Concatenate) (None, None, 97) 0 classification_submodel[1][0]
classification_submodel[2][0]
classification_submodel[3][0]
classification_submodel[4][0]
classification_submodel[5][0]
__________________________________________________________________________________________________
clipped_boxes (ClipBoxes) (None, None, 4) 0 image[0][0]
boxes[0][0]
__________________________________________________________________________________________________
filtered_detections (FilterDete [(None, 100, 4), (No 0 clipped_boxes[0][0]
classification[0][0]
__________________________________________________________________________________________________
shape_1 (Shape) (4,) 0 image[0][0]
__________________________________________________________________________________________________
roi_align_1 (RoiAlign) (None, None, 14, 14, 0 shape_1[0][0]
filtered_detections[0][0]
filtered_detections[0][1]
P3[0][0]
P4[0][0]
P5[0][0]
P6[0][0]
P7[0][0]
__________________________________________________________________________________________________
mask_submodel (Model) (None, None, 28, 28, 2975329 roi_align_1[0][0]
__________________________________________________________________________________________________
masks (ConcatenateBoxes) (None, 100, 76052) 0 filtered_detections[0][0]
mask_submodel[1][0]
==================================================================================================
Total params: 41,349,806
Trainable params: 41,243,566
Non-trainable params: 106,240
__________________________________________________________________________________________________
None
/home/xxxxxx/.local/lib/python3.5/site-packages/keras/callbacks.py:1065: UserWarning: `epsilon` argument is deprecated and will be removed, use `min_delta` instead.
warnings.warn('`epsilon` argument is deprecated and '
/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/gradients_impl.py:108: UserWarning: Converting sparse IndexedSlices to a dense Tensor of unknown shape. This may consume a large amount of memory.
"Converting sparse IndexedSlices to a dense Tensor of unknown shape. "
Epoch 1/50
Traceback (most recent call last):
File "../keras-maskrcnn/keras_maskrcnn/bin/train.py", line 313, in <module>
main()
File "../keras-maskrcnn/keras_maskrcnn/bin/train.py", line 309, in main
max_queue_size=1,
File "/home/xxxxxx/.local/lib/python3.5/site-packages/keras/legacy/interfaces.py", line 91, in wrapper
return func(*args, **kwargs)
File "/home/xxxxxx/.local/lib/python3.5/site-packages/keras/engine/training.py", line 1418, in fit_generator
initial_epoch=initial_epoch)
File "/home/xxxxxx/.local/lib/python3.5/site-packages/keras/engine/training_generator.py", line 181, in fit_generator
generator_output = next(output_generator)
File "/home/xxxxxx/.local/lib/python3.5/site-packages/keras/utils/data_utils.py", line 709, in get
six.reraise(*sys.exc_info())
File "/home/xxxxxx/.local/lib/python3.5/site-packages/six.py", line 693, in reraise
raise value
File "/home/xxxxxx/.local/lib/python3.5/site-packages/keras/utils/data_utils.py", line 685, in get
inputs = self.queue.get(block=True).get()
File "/usr/lib/python3.5/multiprocessing/pool.py", line 608, in get
raise self._value
File "/usr/lib/python3.5/multiprocessing/pool.py", line 119, in worker
result = (True, func(*args, **kwds))
File "/home/xxxxxx/.local/lib/python3.5/site-packages/keras/utils/data_utils.py", line 626, in next_sample
return six.next(_SHARED_SEQUENCES[uid])
File "../keras-maskrcnn/keras_maskrcnn/bin/../../keras_maskrcnn/preprocessing/generator.py", line 266, in __next__
return self.next()
File "../keras-maskrcnn/keras_maskrcnn/bin/../../keras_maskrcnn/preprocessing/generator.py", line 277, in next
return self.compute_input_output(group)
File "../keras-maskrcnn/keras_maskrcnn/bin/../../keras_maskrcnn/preprocessing/generator.py", line 249, in compute_input_output
annotations_group = self.load_annotations_group(group)
File "../keras-maskrcnn/keras_maskrcnn/bin/../../keras_maskrcnn/preprocessing/generator.py", line 93, in load_annotations_group
return [self.load_annotations(image_index) for image_index in group]
File "../keras-maskrcnn/keras_maskrcnn/bin/../../keras_maskrcnn/preprocessing/generator.py", line 93, in <listcomp>
return [self.load_annotations(image_index) for image_index in group]
File "../keras-maskrcnn/keras_maskrcnn/bin/../../keras_maskrcnn/preprocessing/csv_generator.py", line 186, in load_annotations
mask = (mask > 0).astype(np.uint8) # convert from 0-255 to binary mask
TypeError: unorderable types: NoneType() > int()
Keypoint usage?
Can this be used for key point detection?
To train on multiple gpus
How to train the model using multiple gpus in parallel
when can you finish this project?
Mask loss fails on empty masks
The mask loss makes the training process crash if an image doesn't contain any annotations (and therefore has no masks).
Error in random_transform of mask
I have a custom dataset consisting of 900 x 900 images that are annotated in the COCO format. When I try to train the model, I'm getting this error.
Traceback (most recent call last):
File "/usr/lib/python3.5/multiprocessing/pool.py", line 119, in worker
result = (True, func(*args, **kwds))
File "/root/.local/lib/python3.5/site-packages/keras/utils/data_utils.py", line 401, in get_index
return _SHARED_SEQUENCES[uid][i]
File "keras_maskrcnn/bin/../../keras_maskrcnn/preprocessing/generator.py", line 287, in __getitem__
inputs, targets = self.compute_input_output(group)
File "keras_maskrcnn/bin/../../keras_maskrcnn/preprocessing/generator.py", line 265, in compute_input_
image_group, annotations_group = self.preprocess_group(image_group, annotations_group)
File "keras_maskrcnn/bin/../../keras_maskrcnn/preprocessing/generator.py", line 188, in preprocess_group
image, annotations = self.preprocess_group_entry(image, annotations)
File "keras_maskrcnn/bin/../../keras_maskrcnn/preprocessing/generator.py", line 168, in preprocess_group_entry
image, annotations = self.random_transform_group_entry(image, annotations)
File "keras_maskrcnn/bin/../../keras_maskrcnn/preprocessing/generator.py", line 145, in random_transform_group_entry
annotations['masks'][i] = apply_transform(transform, mask, self.transform_parameters)
ValueError: could not broadcast input array from shape (900,900) into shape (900,900,1)
"""
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "keras_maskrcnn/bin/train.py", line 325, in <module>
main()
File "keras_maskrcnn/bin/train.py", line 321, in main
max_queue_size=args.max_queue_size
File "/root/.local/lib/python3.5/site-packages/keras/legacy/interfaces.py", line 91, in wrapper
return func(*args, **kwargs)
File "/root/.local/lib/python3.5/site-packages/keras/engine/training.py", line 1418, in fit_generator
initial_epoch=initial_epoch)
File "/root/.local/lib/python3.5/site-packages/keras/engine/training_generator.py", line 181, in fit_generator
generator_output = next(output_generator)
File "/root/.local/lib/python3.5/site-packages/keras/utils/data_utils.py", line 601, in get
six.reraise(*sys.exc_info())
File "/usr/local/lib/python3.5/dist-packages/six.py", line 693, in reraise
raise value
File "/root/.local/lib/python3.5/site-packages/keras/utils/data_utils.py", line 595, in get
inputs = self.queue.get(block=True).get()
File "/usr/lib/python3.5/multiprocessing/pool.py", line 608, in get
raise self._value
ValueError: could not broadcast input array from shape (900,900) into shape (900,900,1)
I understand that the random transformation of masks involve adding an extra 'fake' channel. However it seems the mask I get from annotations['masks'] is already of shape (900,900,1). In addition to the error, I'm confused as to why the mask is set to be the the size of the image and why it already has an extra dimension.
Would you happen to have an idea as to what could be causing this?
Syntax error while running train.py
$ ./keras_maskrcnn/bin/train.py coco ~/Downloads/train2017/
/home/ros/.local/lib/python2.7/site-packages/h5py/__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`.
from ._conv import register_converters as _register_converters
Using TensorFlow backend.
Traceback (most recent call last):
File "./keras_maskrcnn/bin/train.py", line 288, in <module>
main()
File "./keras_maskrcnn/bin/train.py", line 235, in main
backbone = models.backbone(args.backbone)
File "./keras_maskrcnn/bin/../../keras_maskrcnn/models/__init__.py", line 33, in backbone
from .resnet import ResNetBackbone as b
File "./keras_maskrcnn/bin/../../keras_maskrcnn/models/resnet.py", line 23, in <module>
from ..models import retinanet, Backbone
File "./keras_maskrcnn/bin/../../keras_maskrcnn/models/retinanet.py", line 32
**options,
^
SyntaxError: invalid syntaxCould not satisfy explicit device specification?
Hi, I've tried training maskrcnn on a custom dataset, and I'm getting the following crash,
It seems to come from tensorflow, I've now installed multiple versions, and tested on titan and 1070 same result.
Could it have something to do with this?
google/prettytensor#1
Running Ubuntu 16, keras 2.2.4, tensorflow 1.4
Any ideas?
/media/felix/MongoDB/Train_Test/Knox/mask5/lib/python3.5/site-packages/keras/callbacks.py:1065: UserWarning: epsilon argument is deprecated and will be removed, use min_delta instead.
warnings.warn('epsilon argument is deprecated and '
/media/felix/MongoDB/Train_Test/Knox/mask5/lib/python3.5/site-packages/tensorflow/python/ops/gradients_impl.py:95: UserWarning: Converting sparse IndexedSlices to a dense Tensor of unknown shape. This may consume a large amount of memory.
"Converting sparse IndexedSlices to a dense Tensor of unknown shape. "
Traceback (most recent call last):
File "/media/felix/MongoDB/Train_Test/Knox/mask5/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1327, in _do_call
return fn(*args)
File "/media/felix/MongoDB/Train_Test/Knox/mask5/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1297, in _run_fn
self._extend_graph()
File "/media/felix/MongoDB/Train_Test/Knox/mask5/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1358, in _extend_graph
self._session, graph_def.SerializeToString(), status)
File "/usr/lib/python3.5/contextlib.py", line 66, in exit
next(self.gen)
File "/media/felix/MongoDB/Train_Test/Knox/mask5/lib/python3.5/site-packages/tensorflow/python/framework/errors_impl.py", line 466, in raise_exception_on_not_ok_status
pywrap_tensorflow.TF_GetCode(status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: Cannot assign a device for operation 'training/Adam/gradients/filtered_detections/map/while/embedding_lookup_5_grad/Reshape_1/f_acc': Could not satisfy explicit device specification '' because the node was colocated with a group of nodes that required incompatible device '/job:localhost/replica:0/task:0/device:GPU:0'
Colocation Debug Info:
Colocation group had the following types and devices:
Gather: GPU CPU
ConcatV2: GPU CPU
StridedSlice: CPU
Cast: GPU CPU
TensorArrayGradV3: GPU CPU
Pack: GPU CPU
RefEnter: GPU CPU
Enter: GPU CPU
ExpandDims: GPU CPU
StackPop: GPU CPU
Stack: GPU CPU
TensorArrayReadV3: GPU CPU
Reshape: GPU CPU
UnsortedSegmentSum: GPU CPU
Identity: GPU CPU
TensorArrayGatherV3: GPU CPU
TensorArrayV3: GPU CPU
Unpack: GPU CPU
TensorArrayScatterV3: GPU CPU
Const: GPU CPU
TensorArrayWriteV3: GPU CPU
Shape: GPU CPU
Size: GPU CPU
StackPush: GPU CPU
[[Node: training/Adam/gradients/filtered_detections/map/while/embedding_lookup_5_grad/Reshape_1/f_acc = Stack_class=["loc:@filtered_detections/map/while/TensorArrayReadV3", "loc:@filtered_detections/map/while/strided_slice_10"], elem_type=DT_INT64, stack_name=""]]
'Resize method is not implemented.
There are no ResizeMethod.NEAREST in tf.image.resize_images and the code is calling it
def call(self, inputs, **kwargs): return keras_retinanet.backend.resize_images(inputs, (self.target_size[0], self.target_size[1]), method='nearest')
File "D:/repos/keras-maskrcnn/keras_maskrcnn/bin\..\..\keras_maskrcnn\layers\upsample.py", line 30, in call
return keras_retinanet.backend.resize_images(inputs, (self.target_size[0], self.target_size[1]), method='nearest')
File "C:\Users\User\AppData\Roaming\Python\Python36\site-packages\keras_retinanet\backend\tensorflow_backend.py", line 38, in resize_images
return tensorflow.image.resize_images(*args, **kwargs)
File "C:\Users\User\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\ops\image_ops_impl.py", line 939, in resize_images
raise ValueError('Resize method is not implemented.')
Mask colors
Just to clarify.
For my own dataset I should create csv file in valid format. It's clear.
But when I create mask pictures, should I use the same color for all mask of the same class?
For example:
for cow always red
for cat always blue
etc
Also if I have several cows on picture with some superposition, should I create masks with at least 1 pixel between two objects?
How to visualise loss functions
How to visualise the loss functions using tensorboard with tensorflow as backend
To change color of the masks generated
I want to know how the color of the masks for a particular class is generated. How can I customise it as per my requirements.
Not really an issue but a question
When creating my own CSV file for keras-maskrcnn training, how many different classes do I have to include? Can I have only one object class such as tumor across all images? Or does it has to be something like 'tumor' vs. 'kidney', meaning at least two object classes? Thank you.
How to get the coordinates of the mask generated
I was successfully able to train the model on my own dataset.But I want to get the coordinates of the mask generated
mask is none
A part of my "annotations.csv" file is :
JPEGImages/20130320T004351.039789.Cam6_32.png,,,,,,
JPEGImages/20130320T004351.801805.Cam6_43.png,,,,,,
JPEGImages/20130320T004351.992184.Cam6_61.png,193,105,232,145,apple,masks/20130320T004351.992184.Cam6_61.png
JPEGImages/20130320T004351.992184.Cam6_61.png,131,107,170,147,apple,masks/20130320T004351.992184.Cam6_61.png
And classes file is
apple,0
But, when I trained these data, I had a issue.
Epoch 1/50
multiprocessing.pool.RemoteTraceback:
"""
Traceback (most recent call last):
File "/home/cbf/anaconda3/envs/tfGPU/lib/python3.6/multiprocessing/pool.py", line 119, in worker
result = (True, func(*args, **kwds))
File "/home/cbf/anaconda3/envs/tfGPU/lib/python3.6/site-packages/keras/utils/data_utils.py", line 401, in get_index
return _SHARED_SEQUENCES[uid][i]
File "keras_maskrcnn/bin/../../keras_maskrcnn/preprocessing/generator.py", line 284, in getitem
inputs, targets = self.compute_input_output(group)
File "keras_maskrcnn/bin/../../keras_maskrcnn/preprocessing/generator.py", line 256, in compute_input_output
annotations_group = self.load_annotations_group(group)
File "keras_maskrcnn/bin/../../keras_maskrcnn/preprocessing/generator.py", line 97, in load_annotations_group
return [self.load_annotations(image_index) for image_index in group]
File "keras_maskrcnn/bin/../../keras_maskrcnn/preprocessing/generator.py", line 97, in
return [self.load_annotations(image_index) for image_index in group]
File "keras_maskrcnn/bin/../../keras_maskrcnn/preprocessing/csv_generator.py", line 186, in load_annotations
mask = (mask > 0).astype(np.uint8) # convert from 0-255 to binary mask
TypeError: '>' not supported between instances of 'NoneType' and 'int'
"""
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "keras_maskrcnn/bin/train.py", line 325, in
main()
File "keras_maskrcnn/bin/train.py", line 321, in main
max_queue_size=args.max_queue_size
File "/home/cbf/anaconda3/envs/tfGPU/lib/python3.6/site-packages/keras/legacy/interfaces.py", line 91, in wrapper
return func(*args, **kwargs)
File "/home/cbf/anaconda3/envs/tfGPU/lib/python3.6/site-packages/keras/engine/training.py", line 1418, in fit_generator
initial_epoch=initial_epoch)
File "/home/cbf/anaconda3/envs/tfGPU/lib/python3.6/site-packages/keras/engine/training_generator.py", line 181, in fit_generator
generator_output = next(output_generator)
File "/home/cbf/anaconda3/envs/tfGPU/lib/python3.6/site-packages/keras/utils/data_utils.py", line 601, in get
six.reraise(*sys.exc_info())
File "/home/cbf/anaconda3/envs/tfGPU/lib/python3.6/site-packages/six.py", line 693, in reraise
raise value
File "/home/cbf/anaconda3/envs/tfGPU/lib/python3.6/site-packages/keras/utils/data_utils.py", line 595, in get
inputs = self.queue.get(block=True).get()
File "/home/cbf/anaconda3/envs/tfGPU/lib/python3.6/multiprocessing/pool.py", line 644, in get
raise self._value
TypeError: '>' not supported between instances of 'NoneType' and 'int'
It may be mask is none. I don't know is the issue about data or code.
How can I change?
OOM
OM when allocating tensor with shape[100,256,28,28] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc
Traceback (most recent call last):
File "keras_maskrcnn/bin/train.py", line 314, in
main()
File "keras_maskrcnn/bin/train.py", line 310, in main
max_queue_size=1,
File "/home/devinda/libs/keras-maskrcnn/.env/local/lib/python2.7/site-packages/keras/legacy/interfaces.py", line 91, in wrapper
return func(*args, **kwargs)
File "/home/devinda/libs/keras-maskrcnn/.env/local/lib/python2.7/site-packages/keras/engine/training.py", line 1418, in fit_generator
initial_epoch=initial_epoch)
File "/home/devinda/libs/keras-maskrcnn/.env/local/lib/python2.7/site-packages/keras/engine/training_generator.py", line 217, in fit_generator
class_weight=class_weight)
File "/home/devinda/libs/keras-maskrcnn/.env/local/lib/python2.7/site-packages/keras/engine/training.py", line 1217, in train_on_batch
outputs = self.train_function(ins)
File "/home/devinda/libs/keras-maskrcnn/.env/local/lib/python2.7/site-packages/keras/backend/tensorflow_backend.py", line 2715, in call
return self._call(inputs)
File "/home/devinda/libs/keras-maskrcnn/.env/local/lib/python2.7/site-packages/keras/backend/tensorflow_backend.py", line 2675, in _call
fetched = self._callable_fn(*array_vals)
File "/home/devinda/libs/keras-maskrcnn/.env/local/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1399, in call
run_metadata_ptr)
File "/home/devinda/libs/keras-maskrcnn/.env/local/lib/python2.7/site-packages/tensorflow/python/framework/errors_impl.py", line 526, in exit
c_api.TF_GetCode(self.status.status))
tensorflow.python.framework.errors_impl.ResourceExhaustedError: OOM when allocating tensor with shape[100,256,28,28] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc
[[{{node training/Adam/gradients/mask_submodel/roi_mask_features/convolution_grad/Conv2DBackpropFilter-0-TransposeNHWCToNCHW-LayoutOptimizer}} = Transpose[T=DT_FLOAT, Tperm=DT_INT32, _device="/job:localhost/replica:0/task:0/device:GPU:0"](mask_submodel/roi_mask_upsample/resize_images/ResizeNearestNeighbor, PermConstNHWCToNCHW-LayoutOptimizer)]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info.
Mask per instace or mask per class?
I generate synthetic dataset and try to train on it. I found example:
/data/imgs/img_001.jpg,837,346,981,456,cow,/data/masks/img_001_001.png
/data/imgs/img_002.jpg,215,312,279,391,cat,/data/masks/img_002_001.png
/data/imgs/img_002.jpg,22,5,89,84,bird,/data/masks/img_002_002.png
/data/imgs/img_003.jpg,,,,,,
/data/masks/img_001_001.png - is it mask for all cows on /data/imgs/img_001.jpg , or it containing mask for only one cow located inside bbox(837,346,981,456) ?
'It looks like you are subclassing `Model` and you '
I would like to retrain the maskrcnn from the released model. But I got errors below:
/home/wen/anaconda3/bin/python /home/wen/net_project/MASK/Mask_RCNN-master/samples/coco/coco.py train --dataset=/home/wen/net_project/MASK/data/ --model=/home/wen/net_project/MASK/Mask_RCNN-master/weight/resnet50_coco_v0.1.0.h5
Using TensorFlow backend.
Command: train
Model: /home/wen/net_project/MASK/Mask_RCNN-master/weight/resnet50_coco_v0.1.0.h5
Dataset: /home/wen/net_project/MASK/data/
Year: 2014
Logs: /home/wen/net_project/MASK/Mask_RCNN-master/logs
Auto Download: False
Configurations:
BACKBONE resnet50
BACKBONE_STRIDES [4, 8, 16, 32, 64]
BATCH_SIZE 8
BBOX_STD_DEV [0.1 0.1 0.2 0.2]
COMPUTE_BACKBONE_SHAPE None
DETECTION_MAX_INSTANCES 100
DETECTION_MIN_CONFIDENCE 0.7
DETECTION_NMS_THRESHOLD 0.3
FPN_CLASSIF_FC_LAYERS_SIZE 1024
GPU_COUNT 4
GRADIENT_CLIP_NORM 5.0
IMAGES_PER_GPU 2
IMAGE_MAX_DIM 1024
IMAGE_META_SIZE 93
IMAGE_MIN_DIM 800
IMAGE_MIN_SCALE 0
IMAGE_RESIZE_MODE square
IMAGE_SHAPE [1024 1024 3]
LEARNING_MOMENTUM 0.9
LEARNING_RATE 0.001
LOSS_WEIGHTS {'rpn_class_loss': 1.0, 'rpn_bbox_loss': 1.0, 'mrcnn_class_loss': 1.0, 'mrcnn_bbox_loss': 1.0, 'mrcnn_mask_loss': 1.0}
MASK_POOL_SIZE 14
MASK_SHAPE [28, 28]
MAX_GT_INSTANCES 100
MEAN_PIXEL [123.7 116.8 103.9]
MINI_MASK_SHAPE (56, 56)
NAME coco
NUM_CLASSES 81
POOL_SIZE 7
POST_NMS_ROIS_INFERENCE 1000
POST_NMS_ROIS_TRAINING 2000
ROI_POSITIVE_RATIO 0.33
RPN_ANCHOR_RATIOS [0.5, 1, 2]
RPN_ANCHOR_SCALES (32, 64, 128, 256, 512)
RPN_ANCHOR_STRIDE 1
RPN_BBOX_STD_DEV [0.1 0.1 0.2 0.2]
RPN_NMS_THRESHOLD 0.7
RPN_TRAIN_ANCHORS_PER_IMAGE 256
STEPS_PER_EPOCH 1000
TOP_DOWN_PYRAMID_SIZE 256
TRAIN_BN False
TRAIN_ROIS_PER_IMAGE 200
USE_MINI_MASK True
USE_RPN_ROIS True
VALIDATION_STEPS 50
WEIGHT_DECAY 0.0001
Traceback (most recent call last):
File "/home/wen/anaconda3/lib/python3.6/site-packages/keras/engine/network.py", line 313, in setattr
is_graph_network = self._is_graph_network
File "/home/wen/net_project/MASK/Mask_RCNN-master/mrcnn/parallel_model.py", line 46, in getattribute
return super(ParallelModel, self).getattribute(attrname)
AttributeError: 'ParallelModel' object has no attribute '_is_graph_network'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/home/wen/net_project/MASK/Mask_RCNN-master/samples/coco/coco.py", line 455, in
model_dir=args.logs)
File "/home/wen/net_project/MASK/Mask_RCNN-master/mrcnn/model.py", line 1848, in init
self.keras_model = self.build(mode=mode, config=config)
File "/home/wen/net_project/MASK/Mask_RCNN-master/mrcnn/model.py", line 2073, in build
model = ParallelModel(model, config.GPU_COUNT)
File "/home/wen/net_project/MASK/Mask_RCNN-master/mrcnn/parallel_model.py", line 35, in init
self.inner_model = keras_model
File "/home/wen/anaconda3/lib/python3.6/site-packages/keras/engine/network.py", line 316, in setattr
'It looks like you are subclassing Model and you '
RuntimeError: It looks like you are subclassing Model and you forgot to call super(YourClass, self).__init__(). Always start with this line.
Process finished with exit code 1
the tensorflow is 1.10. Keras is 2.2.2. when I degrade Keras to 2.1.3, another error occured.
Loading weights /home/wen/net_project/MASK/Mask_RCNN-master/weight/resnet50_coco_v0.1.0.h5
Traceback (most recent call last):
File "/home/wen/net_project/MASK/Mask_RCNN-master/samples/coco/coco.py", line 474, in
model.load_weights(model_path, by_name=True)
File "/home/wen/net_project/MASK/Mask_RCNN-master/mrcnn/model.py", line 2141, in load_weights
saving.load_weights_from_hdf5_group_by_name(f, layers)
File "/home/wen/anaconda3/lib/python3.6/site-packages/keras/engine/topology.py", line 3233, in load_weights_from_hdf5_group_by_name
' element(s).')
ValueError: Layer #2 (named "conv1") expects 2 weight(s), but the saved weights have 1 element(s).
Maybe that the pretrained model dosen't fit the network?
Getting masks polygon points with respect to image shape
I have trained the model on two classes and my masks shape is [100,28,28,2].I want to know what does the 4 dimension here represents and how can I get the masks polygon points.
hi, how can i run in my linux server (with pure word linux command)?
To draw masks on Grayscale image
I want to draw the masks on grayscale image rathar than bgr image which is implemented in ResNet50MaskRCNN.ipynb cell 10 line 3 where the bgr format is converted to rgb and then the masks are drawn on it.
Cell 10 line 3:
draw = image.copy()
draw = cv2.cvtColor(draw, cv2.COLOR_BGR2RGB)
However when I try to convert it into grayscale with
draw = cv2.cvtColor(draw, cv2.COLOR_BGR2GRAY)
It gives me this error:
IndexError: too many indices for array
This is the traceback:
IndexError Traceback (most recent call last)
in ()
40 draw_box(draw, b, color=color)
41 mask = mask[:, :, label]
---> 42 draw_mask(draw, b, mask, color=label_color(label))
43 caption = "{} {:.3f}".format(labels_to_names[label], score)
44 draw_caption(draw, b, caption)
~/keras-maskrcnn-second/keras-maskrcnn/keras_maskrcnn/utils/visualization.py in draw_mask(image, box, mask, label, color, binarize_threshold)
39 # draw the mask
40 indices = np.where(mask != [0, 0, 0])
---> 41 image[indices[0], indices[1], :] = 0.5 * image[indices[0], indices[1], :] + 0.5 * mask[indices[0], indices[1], :]
Instance Segmentation Mode
Hi thank you for all of your help. I have successfully tested the example you provide in the code on my own data and it works REALLY well!
Is there a way to get the output to be instance aware? I think there is I am just wondering if it means modifying the draw_mask function.
from keras_maskrcnn.utils.visualization import draw_mask
Lack of license
Please add License file to the project.
How to generate the heatmap of the image?
Hi, I have trained a model by this repository, and i want to generate the heatmap of the features to visual which the importance regions during the feature extracting stage, so is there possible to generate the heatmap ?
CPU usage exceeding 60 GB when running model.predict on single image
running this
outputs = model.predict_on_batch(np.expand_dims(image, axis=0)),
where model is
resnet50_coco_v0.1.0.h5
on a GPU enabled device consumes more than 60 GB of RAM, after that machine freezes.
- Device is GPU enabled.
- Batch size is 1.
TypeError: 'list' object cannot be interpreted as an integer when training on custom dataset
Hi, I have a problem with the training on a custom dataset. I've downloaded the dataset from Data Science Bowl 2018 and generated myself the requiered .csv for training your network.
Example row of my annotations csv : data/stage1train/00071198d059ba7f5914a526d124d28e6d010c92466da21d4a04cd5413362552/images/00071198d059ba7f5914a526d124d28e6d010c92466da21d4a04cd5413362552.png,46,180,64,200,nucleus,data/stage1train/00071198d059ba7f5914a526d124d28e6d010c92466da21d4a04cd5413362552/masks/07a9bf1d7594af2763c86e93f05d22c4d5181353c6d3ab30a345b908ffe5aadc.png
The only row in my classes csv:
nucleus,0
When I try to train your network like this:
%run -i keras_maskrcnn/bin/train.py csv annotations.csv classes.csv
in the notebook it starts of fine with showing me the architecture and loading model stuff, I see Epoch 1/50 and after that an error:
TypeError Traceback (most recent call last)
~\Source\Repos\Mask-RCNN\keras_maskrcnn\bin\train.py in ()
295
296 if name == 'main':
--> 297 main()~\Source\Repos\Mask-RCNN\keras_maskrcnn\bin\train.py in main(args)
291 verbose=1,
292 callbacks=callbacks,
--> 293 max_queue_size=1,
294 )
295~\Anaconda3\lib\site-packages\keras\legacy\interfaces.py in wrapper(*args, **kwargs)
89 warnings.warn('Update your' + object_name + 90 'call to the Keras 2 API: ' + signature, stacklevel=2)
---> 91 return func(*args, **kwargs)
92 wrapper._original_function = func
93 return wrapper~\Anaconda3\lib\site-packages\keras\engine\training.py in fit_generator(self, generator, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, class_weight, max_queue_size, workers, use_multiprocessing, shuffle, initial_epoch)
1413 use_multiprocessing=use_multiprocessing,
1414 shuffle=shuffle,
-> 1415 initial_epoch=initial_epoch)
1416
1417 @interfaces.legacy_generator_methods_support~\Anaconda3\lib\site-packages\keras\engine\training_generator.py in fit_generator(model, generator, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, class_weight, max_queue_size, workers, use_multiprocessing, shuffle, initial_epoch)
175 batch_index = 0
176 while steps_done < steps_per_epoch:
--> 177 generator_output = next(output_generator)
178
179 if not hasattr(generator_output, 'len'):~\Anaconda3\lib\site-packages\keras\utils\data_utils.py in get(self)
791 success, value = self.queue.get()
792 if not success:
--> 793 six.reraise(value.class, value, value.traceback)~\Anaconda3\lib\site-packages\six.py in reraise(tp, value, tb)
691 if value.traceback is not tb:
692 raise value.with_traceback(tb)
--> 693 raise value
694 finally:
695 value = None~\Anaconda3\lib\site-packages\keras\utils\data_utils.py in _data_generator_task(self)
656 # => Serialize calls to
657 # infinite iterator/generator's next() function
--> 658 generator_output = next(self._generator)
659 self.queue.put((True, generator_output))
660 else:~\Source\Repos\Mask-RCNN\keras_maskrcnn\preprocessing\generator.py in next(self)
259
260 def next(self):
--> 261 return self.next()
262
263 def next(self):~\Source\Repos\Mask-RCNN\keras_maskrcnn\preprocessing\generator.py in next(self)
270 self.group_index = (self.group_index + 1) % len(self.groups)
271
--> 272 return self.compute_input_output(group)~\Source\Repos\Mask-RCNN\keras_maskrcnn\preprocessing\generator.py in compute_input_output(self, group)
254
255 # compute network targets
--> 256 targets = self.compute_targets(image_group, annotations_group, masks_group)
257
258 return inputs, targets~\Source\Repos\Mask-RCNN\keras_maskrcnn\preprocessing\generator.py in compute_targets(self, image_group, annotations_group, masks_group)
217 image_group,
218 annotations_group,
--> 219 self.num_classes()
220 )
221~\AppData\Roaming\Python\Python36\site-packages\keras_retinanet\utils\anchors.py in anchor_targets_bbox(anchors, annotations, num_classes, mask_shape, negative_overlap, positive_overlap, **kwargs)
46 # anchor states: 1 is positive, 0 is negative, -1 is dont care
47 anchor_states = np.zeros((anchors.shape[0],))
---> 48 labels = np.zeros((anchors.shape[0], num_classes))
49
50 if annotations.shape[0]:TypeError: 'list' object cannot be interpreted as an integer
I failed to find my error. Any help is appreciated!
(btw running keras 2.2.2)
Can you provide me with a CSV data format? just like retinanet
not mask, like this: /data/imgs/img_001.jpg,837,346,981,456,cow
ResNEt50 Model
Where do we download the trained ResNet50 model from? I can't execute the sample code as a result.
# adjust this to point to your downloaded/trained model
model_path = os.path.join('', 'snapshots', 'resnet50_coco_v0.1.0.h5')
But I don't know where to find this model and I don't see where in the documentation.
Splitting training and validation data
How to train training and validation data and get both training and validation loss simultaneously.
Please explain this:Instead, this repository uses RetinaNet to do the bounding box regression and classification and builds a mask estimation head on top of those predictions.
How to get mask coordinates in unnormalised form
In the script masks = outputs[-1] gives masks in normalised form. I want to get the coordinates of the mask with respect to image height and width. The sample of the output is:
[[7.16073439e-03 4.37061749e-02]
[6.46292232e-04 1.69230737e-02]
[1.34358503e-04 5.98104158e-03]
[8.63772402e-06 9.09183756e-04]
[1.52459143e-06 1.63313583e-04]
[2.57795051e-07 2.88743213e-05]
[1.29549534e-07 1.26992200e-05]
[8.25274427e-08 7.62913623e-06]
[7.40132506e-08 6.40763710e-06]
[7.66042589e-08 5.65424489e-06]
[8.67134844e-08 4.97382689e-06]
[1.13187959e-07 4.59511102e-06]
[1.53445043e-07 4.22227777e-06]
[3.08056343e-07 4.42291275e-06]
[5.39382484e-07 4.72564534e-06]
[1.31324907e-06 5.01810291e-06]
[2.55442023e-06 5.85846055e-06]
[7.54164967e-06 6.80027006e-06]
[1.86023644e-05 7.52933192e-06]
[7.82388088e-05 8.57268788e-06]
[2.59211636e-04 9.38609355e-06]
[1.88827200e-03 1.56105234e-05]
[1.05140945e-02 3.96420655e-05]
[9.86787602e-02 1.63567151e-04]
[3.92987221e-01 7.62552896e-04]
[7.30162382e-01 3.77393607e-03]
[7.52994001e-01 1.26113920e-02]
[4.81491148e-01 2.60339025e-02]]
How to resume training from saved snapshots
I am able to train the model by using the command
python train.py csv training/annotations.csv training/classes.csv which by default starts from IMage net weights. Now if I want to resume the training from my own weights which is getting saved in the snapshots folder I am confused how should I pass that parameter via command line.
Right now I am using this:
python train.py csv training/annotations.csv training/classes.csv --weights=snapshots/r
esnet50_csv_02.h5
But I am getting this message:
usage: train.py [-h]
[--snapshot SNAPSHOT | --imagenet-weights | --weights WEIGHTS | --no-weights]
[--backbone BACKBONE] [--batch-size BATCH_SIZE] [--gpu GPU]
[--epochs EPOCHS] [--steps STEPS]
[--snapshot-path SNAPSHOT_PATH]
[--tensorboard-dir TENSORBOARD_DIR] [--no-snapshots]
[--no-evaluation] [--freeze-backbone]
[--no-class-specific-filter] [--config CONFIG]
[--weighted-average]
{coco,csv} ...
Can you explain how can I pass mutually exclusive group arguments.Thanks!
Tensor shape error while training starts
I am getting following error while startring the training. I have created my custom dataset in coco format with 1000x1000 training image size.
Total params: 39,333,614
Trainable params: 39,227,374
Non-trainable params: 106,240
None
/home/amjn_cowi/.local/lib/python3.6/site-packages/keras/callbacks.py:1065: UserWarning: epsilon argument is deprecated and will be removed, use min_delta instead.
warnings.warn('epsilon argument is deprecated and '
/anaconda/envs/maskrcnn_retinanet/lib/python3.6/site-packages/tensorflow/python/ops/gradients_impl.py:112: UserWarning: Converting sparse IndexedSlices to a dense Tensor of unknown shape. This may consume a large amount of memory.
"Converting sparse IndexedSlices to a dense Tensor of unknown shape. "
Epoch 1/50
Traceback (most recent call last):
File "keras_maskrcnn/bin/train.py", line 313, in
main()
File "keras_maskrcnn/bin/train.py", line 309, in main
max_queue_size=1,
File "/home/amjn_cowi/.local/lib/python3.6/site-packages/keras/legacy/interfaces.py", line 91, in wrapper
return func(*args, **kwargs)
File "/home/amjn_cowi/.local/lib/python3.6/site-packages/keras/engine/training.py", line 1418, in fit_generator
initial_epoch=initial_epoch)
File "/home/amjn_cowi/.local/lib/python3.6/site-packages/keras/engine/training_generator.py", line 217, in fit_generator
class_weight=class_weight)
File "/home/amjn_cowi/.local/lib/python3.6/site-packages/keras/engine/training.py", line 1217, in train_on_batch
outputs = self.train_function(ins)
File "/home/amjn_cowi/.local/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py", line 2715, in call
return self._call(inputs)
File "/home/amjn_cowi/.local/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py", line 2675, in _call
fetched = self._callable_fn(*array_vals)
File "/anaconda/envs/maskrcnn_retinanet/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1439, in call
run_metadata_ptr)
File "/anaconda/envs/maskrcnn_retinanet/lib/python3.6/site-packages/tensorflow/python/framework/errors_impl.py", line 528, in exit
c_api.TF_GetCode(self.status.status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: Input to reshape is a tensor with 78400 values, but the requested shape requires a multiple of 300
[[{{node masks/Reshape}} = Reshape[T=DT_FLOAT, Tshape=DT_INT32, _device="/job:localhost/replica:0/task:0/device:GPU:0"](mask_submodel/roi_mask/Sigmoid-2-0-TransposeNCHWToNHWC-LayoutOptimizer, masks/Reshape/shape)]]
[[{{node loss/add_1/_2619}} = _Recvclient_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device_incarnation=1, tensor_name="edge_12418_loss/add_1", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"]]
Please let me know, what could be the issue.
Is there any image augmentation operation during the training ? some early-stopping metrics to avoid the network being overfitting ?
Hello, Is there any image augmentation operation during the training ?
Meanwhile, any some early-stopping metrics to avoid the network being overfitting ?
Thanks~
one mask per image
hi, I have lots of objects in one image is that possible to use only one mask for each image. this way all the objects in the image will have same mask but different bounding boxes, thanks
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.