zhihou7 / vcl Goto Github PK

Thnaks for you enlightening work.
The object detection result you provide in VCL is https://drive.google.com/file/d/1QI1kcZJqI-ym6AGQ2swwp4CKb39uLf-4/view. But the object detection result only contains 71 kinds of objects.Shouldn't it be 80?

Thank you for your work. Sorry to interrupt. I tried to train your code on a single 1080 (12G) and the training stopped because of the following error.

`2022-05-16 20:09:46.768782: W tensorflow/core/framework/op_kernel.cc:1651] OP_REQUIRES failed at save_restore_v2_ops.cc:185 : Out of range: Read less bytes than requested
Traceback (most recent call last):
  File "/root/miniconda3/lib/python3.8/site-packages/tensorflow_core/python/client/session.py", line 1365, in _do_call
    return fn(*args)
  File "/root/miniconda3/lib/python3.8/site-packages/tensorflow_core/python/client/session.py", line 1349, in _run_fn
    return self._call_tf_sessionrun(options, feed_dict, fetch_list,
  File "/root/miniconda3/lib/python3.8/site-packages/tensorflow_core/python/client/session.py", line 1441, in _call_tf_sessionrun
    return tf_session.TF_SessionRun_wrapper(self._session, options, feed_dict,
tensorflow.python.framework.errors_impl.OutOfRangeError: 2 root error(s) found.
  (0) Out of range: Read less bytes than requested
         [[{{node save_1/RestoreV2}}]]
         [[save_1/RestoreV2/_235]]
  (1) Out of range: Read less bytes than requested
         [[{{node save_1/RestoreV2}}]]
0 successful operations.
0 derived errors ignored.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "tools/Train_VCL_ResNet_VCOCO.py", line 115, in <module>
    sw.train_model(sess, args.max_iters)
  File "/root/autodl-tmp/VCL-master/tools/../lib/models/train_Solver_VCOCO_MultiGPU.py", line 153, in train_model
    self.from_snapshot(sess)
  File "/root/autodl-tmp/VCL-master/tools/../lib/models/train_Solver_VCOCO.py", line 170, in from_snapshot
    self.saver_restore.restore(sess, self.pretrained_model)
  File "/root/miniconda3/lib/python3.8/site-packages/tensorflow_core/python/training/saver.py", line 1289, in restore
    sess.run(self.saver_def.restore_op_name,
  File "/root/miniconda3/lib/python3.8/site-packages/tensorflow_core/python/client/session.py", line 955, in run
    result = self._run(None, fetches, feed_dict, options_ptr,
  File "/root/miniconda3/lib/python3.8/site-packages/tensorflow_core/python/client/session.py", line 1179, in _run
    results = self._do_run(handle, final_targets, final_fetches,
  File "/root/miniconda3/lib/python3.8/site-packages/tensorflow_core/python/client/session.py", line 1358, in _do_run
    return self._do_call(_run_fn, feeds, fetches, targets, options,
  File "/root/miniconda3/lib/python3.8/site-packages/tensorflow_core/python/client/session.py", line 1384, in _do_call
    raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.OutOfRangeError: 2 root error(s) found.
  (0) Out of range: Read less bytes than requested
         [[node save_1/RestoreV2 (defined at /root/miniconda3/lib/python3.8/site-packages/tensorflow_core/python/framework/ops.py:1748) ]]
         [[save_1/RestoreV2/_235]]
  (1) Out of range: Read less bytes than requested
         [[node save_1/RestoreV2 (defined at /root/miniconda3/lib/python3.8/site-packages/tensorflow_core/python/framework/ops.py:1748) ]]
0 successful operations.
0 derived errors ignored.

Original stack trace for 'save_1/RestoreV2':
  File "tools/Train_VCL_ResNet_VCOCO.py", line 115, in <module>
    sw.train_model(sess, args.max_iters)
  File "/root/autodl-tmp/VCL-master/tools/../lib/models/train_Solver_VCOCO_MultiGPU.py", line 153, in train_model
    self.from_snapshot(sess)
  File "/root/autodl-tmp/VCL-master/tools/../lib/models/train_Solver_VCOCO.py", line 169, in from_snapshot
    self.saver_restore = tf.train.Saver(saver_t)
  File "/root/miniconda3/lib/python3.8/site-packages/tensorflow_core/python/training/saver.py", line 828, in __init__
    self.build()
  File "/root/miniconda3/lib/python3.8/site-packages/tensorflow_core/python/training/saver.py", line 840, in build
    self._build(self._filename, build_save=True, build_restore=True)
  File "/root/miniconda3/lib/python3.8/site-packages/tensorflow_core/python/training/saver.py", line 868, in _build
    self.saver_def = self._builder._build_internal(  # pylint: disable=protected-access
  File "/root/miniconda3/lib/python3.8/site-packages/tensorflow_core/python/training/saver.py", line 507, in _build_internal
    restore_op = self._AddRestoreOps(filename_tensor, saveables,
  File "/root/miniconda3/lib/python3.8/site-packages/tensorflow_core/python/training/saver.py", line 327, in _AddRestoreOps
    all_tensors = self.bulk_restore(filename_tensor, saveables, preferred_shard,
  File "/root/miniconda3/lib/python3.8/site-packages/tensorflow_core/python/training/saver.py", line 575, in bulk_restore
    return io_ops.restore_v2(filename_tensor, names, slices, dtypes)
  File "/root/miniconda3/lib/python3.8/site-packages/tensorflow_core/python/ops/gen_io_ops.py", line 1693, in restore_v2
    _, _, _op = _op_def_lib._apply_op_helper(
  File "/root/miniconda3/lib/python3.8/site-packages/tensorflow_core/python/framework/op_def_library.py", line 792, in _apply_op_helper
    op = g.create_op(op_type_name, inputs, dtypes=None, name=scope,
  File "/root/miniconda3/lib/python3.8/site-packages/tensorflow_core/python/util/deprecation.py", line 513, in new_func
    return func(*args, **kwargs)
  File "/root/miniconda3/lib/python3.8/site-packages/tensorflow_core/python/framework/ops.py", line 3356, in create_op
    return self._create_op_internal(op_type, inputs, dtypes, input_types, name,
  File "/root/miniconda3/lib/python3.8/site-packages/tensorflow_core/python/framework/ops.py", line 3418, in _create_op_internal
    ret = Operation(
  File "/root/miniconda3/lib/python3.8/site-packages/tensorflow_core/python/framework/ops.py", line 1748, in __init__
    self._traceback = `tf_stack.extract_stack()``

I have never used TensorFlow before and I wonder whether it is due to insufficient GPU memory, if so, how should I adjust batchsize, I did not find any place to adjust batchsize in the code. I would appreciate it if you could help me and look forward to your reply

Does one GPU work?

Hello! Thank you for this work! I would like to know how to run inference of your model on a single image.

Dear, sir

Thank you for your works!

I try to train VCL on V-COCO as following instructions.

Train an VCL on V-COCO
python tools/Train_VCL_ResNet_VCOCO.py --model VCL_union_multi_ml1_l05_t3_rew_aug5_3_new_VCOCO_test --num_iteration 400000

I only assigned 1 GPU for training and I got error messages as below, would you help me to solve with this?
I don't know why I am try to training on V-COCO, but the error is about HICO.

Traceback (most recent call last):
File "/home/kogashi/miniconda3/envs/VCL/lib/python3.7/site-packages/tensorflow/python/client/session.py", line 1356, in _do_call
return fn(*args)
File "/home/kogashi/miniconda3/envs/VCL/lib/python3.7/site-packages/tensorflow/python/client/session.py", line 1339, in _run_fn
self._extend_graph()
File "/home/kogashi/miniconda3/envs/VCL/lib/python3.7/site-packages/tensorflow/python/client/session.py", line 1374, in _extend_graph
tf_session.ExtendSession(self._session)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Cannot assign a device for operation HICO_0/MatMul: {{node HICO_0/MatMul}}was explicitly assigned to /device:GPU:0 but available devices are [ /job:localhost/replica:0/task:0/device:CPU:0, /job:localhost/replica:0/task:0/device:CPU:1, /job:localhost/replica:0/task:0/device:CPU:10, /job:localhost/replica:0/task:0/device:CPU:11, /job:localhost/replica:0/task:0/device:CPU:12, /job:localhost/replica:0/task:0/device:CPU:13, /job:localhost/replica:0/task:0/device:CPU:14, /job:localhost/replica:0/task:0/device:CPU:15, /job:localhost/replica:0/task:0/device:CPU:2, /job:localhost/replica:0/task:0/device:CPU:3, /job:localhost/replica:0/task:0/device:CPU:4, /job:localhost/replica:0/task:0/device:CPU:5, /job:localhost/replica:0/task:0/device:CPU:6, /job:localhost/replica:0/task:0/device:CPU:7, /job:localhost/replica:0/task:0/device:CPU:8, /job:localhost/replica:0/task:0/device:CPU:9, /job:localhost/replica:0/task:0/device:XLA_CPU:0, /job:localhost/replica:0/task:0/device:XLA_GPU:0 ]. Make sure the device specification refers to a valid device.
[[HICO_0/MatMul]]

During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "tools/Train_VCL_ResNet_VCOCO.py", line 109, in
sw.train_model(sess, args.max_iters)
File "/home/kogashi/VCL/tools/../lib/models/train_Solver_VCOCO_MultiGPU.py", line 153, in train_model
self.from_snapshot(sess)
File "/home/kogashi/VCL/tools/../lib/models/train_Solver_VCOCO.py", line 134, in from_snapshot
sess.run(tf.global_variables_initializer())
File "/home/kogashi/miniconda3/envs/VCL/lib/python3.7/site-packages/tensorflow/python/client/session.py", line 950, in run
run_metadata_ptr)
File "/home/kogashi/miniconda3/envs/VCL/lib/python3.7/site-packages/tensorflow/python/client/session.py", line 1173, in _run
feed_dict_tensor, options, run_metadata)
File "/home/kogashi/miniconda3/envs/VCL/lib/python3.7/site-packages/tensorflow/python/client/session.py", line 1350, in _do_run
run_metadata)
File "/home/kogashi/miniconda3/envs/VCL/lib/python3.7/site-packages/tensorflow/python/client/session.py", line 1370, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Cannot assign a device for operation HICO_0/MatMul: node HICO_0/MatMul (defined at /home/kogashi/VCL/tools/../lib/networks/ResNet50_VCOCO.py:150) was explicitly assigned to /device:GPU:0 but available devices are [ /job:localhost/replica:0/task:0/device:CPU:0, /job:localhost/replica:0/task:0/device:CPU:1, /job:localhost/replica:0/task:0/device:CPU:10, /job:localhost/replica:0/task:0/device:CPU:11, /job:localhost/replica:0/task:0/device:CPU:12, /job:localhost/replica:0/task:0/device:CPU:13, /job:localhost/replica:0/task:0/device:CPU:14, /job:localhost/replica:0/task:0/device:CPU:15, /job:localhost/replica:0/task:0/device:CPU:2, /job:localhost/replica:0/task:0/device:CPU:3, /job:localhost/replica:0/task:0/device:CPU:4, /job:localhost/replica:0/task:0/device:CPU:5, /job:localhost/replica:0/task:0/device:CPU:6, /job:localhost/replica:0/task:0/device:CPU:7, /job:localhost/replica:0/task:0/device:CPU:8, /job:localhost/replica:0/task:0/device:CPU:9, /job:localhost/replica:0/task:0/device:XLA_CPU:0, /job:localhost/replica:0/task:0/device:XLA_GPU:0 ]. Make sure the device specification refers to a valid device.
[[HICO_0/MatMul]]

Errors may have originated from an input operation.
Input Source operations connected to node HICO_0/MatMul:
IteratorGetNext (defined at /home/kogashi/VCL/tools/../lib/ult/ult.py:884)
HICO_0/Const (defined at /home/kogashi/VCL/tools/../lib/networks/ResNet50_VCOCO.py:148)

i run the " python tools/Test_VCL_ResNet_VCOCO.py --num_iteration 200000"
the results are a little bit poor

hi, when i run "python tools/Test_ResNet_VCOCO.py --num_iteration 200000", an error has occurred, Have you ever experienced this?
@zhihou7

Hello, I want to migrate your code to my project, but I don’t quite understand what Trainval_GT_VCOCO_obj.pkl and Trainval_Neg_VCOCO_obj.pkl in your code mean, and how to generate the above format using hico-det raw data

你好，我想把您的代码迁移到我的项目中，但是我不是很明白您代码里的Trainval_GT_VCOCO_obj.pkl和Trainval_Neg_VCOCO_obj.pkl是什么意思，使用hico-det原始数据如何生成上述格式

How to split rare first datasets and non-rare datasets on HICO-DET. And please provide Unseen object list for me

Hello:
You job is so cool, I am very glad to try this new project.
I trained a model by coco dataset with Res50. But when I run "Test_VCL_ResNet_VCOCO.py", error will be called. Like:

    "VCL_ResNet50_VCOCO doesn't support pool5_HO
    ......
    Traceback (most recent call last):
         File "tools/Test_VCL_ResNet_VCOCO.py", line 88, in <module>
             net.create_architecture(False)
           >>/lib/networks/ResNet50_VCOCO.py", line 418, in create_architecture
             self.build_network(is_training)
           >>/lib/networks/HOI.py", line 169, in build_network
             fc7_HO_raw = self.res5_ho(pool5_HO, is_training, 'res5')
           >>/lib/networks/HOI.py", line 66, in res5_ho
             scope=self.scope)
    ...
    AttributeError: 'NoneType' object has no attribute 'get_shape' "

Now I have no idea. So could you help me?

Hi,
First of all, kudos to the great work!

I was wondering if you have an idea on the number of parameters (trainable and total) used by your model? I could probably dig into your code to find that but it would help if you have it already!

Looking forward to your reply! Thanks!