xiaomengyc / spg Goto Github PK

Epoch: [0][20/300] Time 0.925 (0.968) ETA 00:28:44(00:04:50) Loss 5.3001 (5.6576) Prec@1 0.000 (0.000) Prec@5 0.000 (0.000)
Epoch: [0][40/300] Time 0.912 (0.943) ETA 00:27:40(00:04:42) Loss 5.4433 (5.5504) Prec@1 0.000 (0.000) Prec@5 0.000 (0.000)
Epoch: [0][60/300] Time 0.920 (0.937) ETA 00:27:11(00:04:41) Loss 5.4316 (5.4998) Prec@1 0.000 (0.000) Prec@5 0.000 (0.000)
Epoch: [0][80/300] Time 0.923 (0.937) ETA 00:26:52(00:04:41) Loss 5.6090 (5.4800) Prec@1 0.000 (0.000) Prec@5 0.000 (0.000)
Epoch: [0][100/300] Time 0.941 (0.934) ETA 00:26:28(00:04:40) Loss 5.3967 (5.4582) Prec@1 0.000 (0.000) Prec@5 0.000 (0.000)
Epoch: [0][120/300] Time 0.938 (0.934) ETA 00:26:09(00:04:40) Loss 5.3338 (5.4500) Prec@1 0.000 (0.000) Prec@5 0.000 (0.000)
Epoch: [0][140/300] Time 0.943 (0.938) ETA 00:25:58(00:04:41) Loss 5.3689 (5.4394) Prec@1 0.000 (0.000) Prec@5 0.000 (0.000)
Epoch: [0][160/300] Time 1.014 (0.941) ETA 00:25:43(00:04:42) Loss 5.4100 (5.4387) Prec@1 0.000 (0.000) Prec@5 0.000 (0.000)
Epoch: [0][180/300] Time 0.942 (0.942) ETA 00:25:26(00:04:42) Loss 5.3895 (5.4408) Prec@1 0.000 (0.000) Prec@5 0.000 (0.000)
Epoch: [0][200/300] Time 0.939 (0.942) ETA 00:25:08(00:04:42) Loss 5.9786 (5.4488) Prec@1 0.000 (0.000) Prec@5 0.000 (0.000)
Epoch: [0][220/300] Time 0.942 (0.942) ETA 00:24:49(00:04:42) Loss 5.5643 (5.4577) Prec@1 0.000 (0.000) Prec@5 0.000 (0.000)
Epoch: [0][240/300] Time 0.947 (0.943) ETA 00:24:32(00:04:42) Loss 5.5316 (5.4707) Prec@1 0.000 (0.000) Prec@5 0.000 (0.000)
Epoch: [0][260/300] Time 0.948 (0.943) ETA 00:24:13(00:04:43) Loss 5.6451 (5.4792) Prec@1 0.000 (0.000) Prec@5 0.000 (0.000)
Epoch: [0][280/300] Time 0.945 (0.944) ETA 00:23:55(00:04:43) Loss 5.8763 (5.4896) Prec@1 0.000 (0.000) Prec@5 0.000 (0.000)
Epoch: [0][0/300] Time 0.679 (0.943) ETA 00:23:35(00:04:42) Loss 5.6554 (5.4943) Prec@1 0.000 (0.000) Prec@5 0.000 (0.000)
0,5.4943,0.000,0.000

=> loaded checkpoint '/user/pytorch/SPG-master/vgg16-397923af.pth'
Max iter: 320295
Traceback (most recent call last):
File "train_frame.py", line 194, in
train(args)
File "train_frame.py", line 120, in train
res = my_optim.reduce_lr(args, optimizer, current_epoch)
File "/user/pytorch/SPG-master/exper/my_optim.py", line 75, in reduce_lr
if change_points is not None and epoch in change_points:
File "/user/pytorch/SPG-master/exper/my_optim.py", line 71, in
change_points = map(lambda x: int(x.strip()), values)
ValueError: invalid literal for int() with base 10: 'none'

Hi, Thank you for sharing the code.

I have checked your code and realized there is no metric to measure top1-localization accuracy.
Also, val_list.txt for both cub and imagenet only contain class label not bounding box information.
Can you please explain how you evaluate the performance of top1-loc?
For example, where the bounding box information is or where the top1-loc metric is measured.
Thank you in advance!

Can you please provide a pre trained model for CUB-200-2011?

IOError: [Errno 2] No such file or directory: '/home/ltc/SPG/data/ILSVRC/Data/CLS-LOC/train/n03692522/n03692522_14326.JPEG'

when I run sh val_imagenet_full.sh

An error happened.

NameError: name 'inceptionv3_spg' is not defined

I saw you define inception3_spg in models/google/inception3_spg.py

So here the --arch should be inception3_spg

@xiaomengyc
Hi, the whole framework adopts modified Inception v3 as the backbone, but why the weights of pre-trained VGG-16 is restored in the training command line here?
I suppose the correct model path is "~/.torch/models/inception_v3_google-1a9a5a14.pth"?

../models/google/inception3_spg.py:137: UserWarning: nn.init.xavier_uniform is now deprecated in favor of nn.init.xavier_uniform_.
nn.init.xavier_uniform(m.weight.data)
=> loading checkpoint '../models/inception_v3_google-1a9a5a14.pth'
KeyError
Traceback (most recent call last):
File "../utils/Restore.py", line 24, in restore
args.current_epoch = checkpoint['epoch'] + 1
KeyError: 'epoch'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "train_frame.py", line 194, in
train(args)
File "train_frame.py", line 98, in train
model, optimizer= get_model(args)
File "train_frame.py", line 88, in get_model
restore(args, model, optimizer, including_opt=False)
File "../utils/Restore.py", line 38, in restore
_model_load(model, checkpoint)
File "../utils/Restore.py", line 51, in _model_load
if model_dict.keys()[0].startswith('module.'):
TypeError: 'odict_keys' object is not subscriptable

Which folder should I put the pre-training model “cub_epoch_100_glo_step_20200.pth.zip” and “imagenet_epoch_2_glo_step_128118.pth.zip” in？

HI!XiaoMeng!
The problem occurs when I load the pretrain model you provide at (https://drive.google.com/open?id=1EwRuqfGASarGidutnYB8rXLSuzYpEoSM). the model named imagenet_epoch_2_glo_step_128118.pth.tar.
error:
Missing key(s) in state_dict: "Conv2d_1a_3x3.conv.weight", "Conv2d_1a_3x3.bn.weight", "Conv2d_1a_3x3.bn.bias", "Conv2d_1a_3x3.bn.running_mean", "Conv2d_1a_3x3.bn.running_var", "Conv2d_2a_3x3.conv.weight", "Conv2d_2a_3x3.bn.weight", "Conv2d_2a_3x3.bn.bias", "Conv2d_2a_3x3.bn.running_mean", "Conv2d_2a_3x3.bn.running_var", "Conv2d_2b_3x3.conv.weight", "Conv2d_2b_3x3.bn.weight", "Conv2d_2b_3x3.bn.bias", "Conv2d_2b_3x3.bn.running_mean", "Conv2d_2b_3x3.bn.running_var", "Conv2d_3b_1x1.conv.weight", "Conv2d_3b_1x1.bn.weight", "Conv2d_3b_1x1.bn.bias", "Conv2d_3b_1x1.bn.running_mean", "Conv2d_3b_1x1.bn.running_var", "Conv2d_4a_3x3.conv.weight", "Conv2d_4a_3x3.bn.weight", "Conv2d_4a_3x3.bn.bias", "Conv2d_4a_3x3.bn.running_mean", "Conv2d_4a_3x3.bn.running_var", "Mixed_5b.branch1x1.conv.weight", "Mixed_5b.branch1x1.bn.weight", "Mixed_5b.branch1x1.bn.bias", "Mixed_5b.branch1x1.bn.running_mean", "Mixed_5b.branch1x1.bn.running_var", "Mixed_5b.branch5x5_1.conv.weight", "Mixed_5b.branch5x5_1.bn.weight", "Mixed_5b.branch5x5_1.bn.bias", "Mixed_5b.branch5x5_1.bn.running_mean", "Mixed_5b.branch5x5_1.bn.running_var", "Mixed_5b.branch5x5_2.conv.weight", "Mixed_5b.branch5x5_2.bn.weight", "Mixed_5b.branch5x5_2.bn.bias", "Mixed_5b.branch5x5_2.bn.running_mean", "Mixed_5b.branch5x5_2.bn.running_var", "Mixed_5b.branch3x3dbl_1.conv.weight", "Mixed_5b.branch3x3dbl_1.bn.weight", "Mixed_5b.branch3x3dbl_1.bn.bias", "Mixed_5b.branch3x3dbl_1.bn.running_mean", "Mixed_5b.branch3x3dbl_1.bn.running_var", "Mixed_5b.branch3x3dbl_2.conv.weight", "Mixed_5b.branch3x3dbl_2.bn.weight", "Mixed_5b.branch3x3dbl_2.bn.bias", "Mixed_5b.branch3x3dbl_2.bn.running_mean", "Mixed_5b.branch3x3dbl_2.bn.running_var", "Mixed_5b.branch3x3dbl_3.conv.weight", "Mixed_5b.branch3x3dbl_3.bn.weight", "Mixed_5b.branch3x3dbl_3.bn.bias", "Mixed_5b.branch3x3dbl_3.bn.running_mean", "Mixed_5b.branch3x3dbl_3.bn.running_var", "Mixed_5b.branch_pool.conv.weight", "Mixed_5b.branch_pool.bn.weight", "Mixed_5b.branch_pool.bn.bias", "Mixed_5b.branch_pool.bn.running_mean", "Mixed_5b.branch_pool.bn.running_var", "Mixed_5c.branch1x1.conv.weight", "Mixed_5c.branch1x1.bn.weight", "Mixed_5c.branch1x1.bn.bias", "Mixed_5c.branch1x1.bn.running_mean", "Mixed_5c.branch1x1.bn.running_var", "Mixed_5c.branch5x5_1.conv.weight", "Mixed_5c.branch5x5_1.bn.weight", "Mixed_5c.branch5x5_1.bn.bias", "Mixed_5c.branch5x5_1.bn.running_mean", "Mixed_5c.branch5x5_1.bn.running_var", "Mixed_5c.branch5x5_2.conv.weight", "Mixed_5c.branch5x5_2.bn.weight", "Mixed_5c.branch5x5_2.bn.bias", "Mixed_5c.branch5x5_2.bn.running_mean", "Mixed_5c.branch5x5_2.bn.running_var", "Mixed_5c.branch3x3dbl_1.conv.weight", "Mixed_5c.branch3x3dbl_1.bn.weight", "Mixed_5c.branch3x3dbl_1.bn.bias", "Mixed_5c.branch3x3dbl_1.bn.running_mean", "Mixed_5c.branch3x3dbl_1.bn.running_var", "Mixed_5c.branch3x3dbl_2.conv.weight", "Mixed_5c.branch3x3dbl_2.bn.weight", "Mixed_5c.branch3x3dbl_2.bn.bias", "Mixed_5c.branch3x3dbl_2.bn.running_mean", "Mixed_5c.branch3x3dbl_2.bn.running_var", "Mixed_5c.branch3x3dbl_3.conv.weight", "Mixed_5c.branch3x3dbl_3.bn.weight", "Mixed_5c.branch3x3dbl_3.bn.bias", "Mixed_5c.branch3x3dbl_3.bn.running_mean", "Mixed_5c.branch3x3dbl_3.bn.running_var", "Mixed_5c.branch_pool.conv.weight", "Mixed_5c.branch_pool.bn.weight", "Mixed_5c.branch_pool.bn.bias", "Mixed_5c.branch_pool.bn.running_mean", "Mixed_5c.branch_pool.bn.running_var", "Mixed_5d.branch1x1.conv.weight", "Mixed_5d.branch1x1.bn.weight",
........

it reveal the the model cant match the net defined. Is there some mistake in the model I downloaded?Please enlighten me. Thank you very much!

@xiaomengyc
Hi, thanks for releasing the wonderful implementation of your work!
I noticed from this snippet since https://github.com/xiaomengyc/SPG/blob/master/exper/my_optim.py#L12, you try to multiply the lr for the last conv layer before GAP in the main branch by 10. But the model's parameters don't include one with 'cls' in its name, maybe 'classifier_1' should be considered?

Hi ,

I am running

python demo_image.py --image_name 'ILSVRC2012_val_00000004.JPEG'

and I am getting an error

Namespace(image_name='ILSVRC2012_val_00000004.JPEG', img_dir='examples/', input_size=321, num_classes=1000, save_dir='examples/results/', save_spg_c=True, snapshots='snapshots/imagenet_epoch_2_glo_step_128118.pth.tar', top_k=1)
Traceback (most recent call last):
  File "demo_image.py", line 69, in <module>
    model = load_model(args)
  File "demo_image.py", line 39, in load_model
    model = inceptionv3_spg.Inception3(num_classes=args.num_classes, threshold=0.5)
  File "/home/rahul/ActiveShuttle/WSOL/ACOL_SPG/SPG-master/models/google/inception3_spg.py", line 93, in __init__
    self.num_classes = args.num_classes
AttributeError: 'NoneType' object has no attribute 'num_classes'

Can anyone please help to find the problem ?

Thanks
Rahul

HI, can you provide the links to download the datasets? I am not sure which version of imagenet is used in this project.

For us to freely use your code.