I have met this error when run train.py ... #5

bemoregt · 2019-04-23T08:50:11Z

Hi, @owang @sridharmahadevan @akanimax @huangzh13

I have met this error when run train.py ...
What's wrong to me?

oem@sgi:~/BMSG-GAN/sourcecode$ python3 train.py --depth=7 --latent_size=128 --images_dir='../data/celebJapan/train' --sample_dir=samples/exp_2 --model_dir=models/exp_2
Total number of images in the dataset: 6604

error message -
Starting the training process ...

Epoch: 1
Elapsed [0:00:04.581270] batch: 1 d_loss: 4.346926 g_loss: 6.674685
Traceback (most recent call last):
File "train.py", line 254, in
main(parse_arguments())
File "train.py", line 248, in main
start=args.start
File "/home/oem/BMSG-GAN/sourcecode/MSG_GAN/GAN.py", line 482, in train
gen_img_files)
File "/home/oem/BMSG-GAN/sourcecode/MSG_GAN/GAN.py", line 345, in create_grid
samples = [Generator.adjust_dynamic_range(sample) for sample in samples]
File "/home/oem/BMSG-GAN/sourcecode/MSG_GAN/GAN.py", line 345, in
samples = [Generator.adjust_dynamic_range(sample) for sample in samples]
File "/home/oem/BMSG-GAN/sourcecode/MSG_GAN/GAN.py", line 96, in adjust_dynamic_range
data = data * scale + bias
TypeError: mul() received an invalid combination of arguments - got (numpy.float32), but expected one of:

(Tensor other)
didn't match because some of the arguments have invalid types: (numpy.float32)
(Number other)
didn't match because some of the arguments have invalid types: (numpy.float32)

Thanks in advance ~

akanimax · 2019-04-23T08:56:42Z

Could you please show what is the version of your python, torch and numpy?
Please try updating to the latest versions for torch and numpy.
The code is tested for python == 3.6.5.
Please let me know if you still face this issue.

bemoregt · 2019-04-23T08:58:15Z

Hi, @owang @sridharmahadevan @akanimax @huangzh13

My Environment:

Ubuntu 17.x x64, Python 3.6.7, CUDA 10.1, Pytorch 0.4.1, numpy 1.15.4

Thanks.

akanimax · 2019-04-23T08:58:43Z

Could you please try again with python 3.6?
The error comes after the first training log itself.

bemoregt · 2019-04-23T09:03:33Z

Hi, @owang @sridharmahadevan @akanimax @huangzh13

It's same at python3.6 ...

What's wrong to me?

Thanks at any rate .... _;

akanimax · 2019-04-23T09:06:24Z

Could you try updating pytorch to 1.0.0? I hope this solves the problem.

bemoregt · 2019-04-23T09:11:08Z

OK, I'll try that...

bemoregt · 2019-04-23T12:25:30Z

It works , Thanks a lot.

from @bemoregt

akanimax · 2019-04-23T12:33:38Z

@bemoregt,

I am glad that it is working now. Just wanted to point out that since you are synthesizing Japanese celebs at 256 x 256 resolution, the latent_size = 128 might not be enough to make the generator expressive enough. Please try to use latent_size=512.

Also, if you are able to get good results, please feel free to share these with us, I'll be happy to include them on the readme like @huangzh13's cartoons 😄.

Hope this helps.

👍
Best regards,
@akanimax

bemoregt · 2019-04-23T12:50:57Z

But, ...

Elapsed [0:04:07.511359] batch: 108 d_loss: 0.040370 g_loss: 18.472263
Elapsed [0:04:15.999767] batch: 112 d_loss: 0.000000 g_loss: 12.169998
Elapsed [0:04:24.425038] batch: 116 d_loss: 0.053961 g_loss: 16.491339
Elapsed [0:04:32.862795] batch: 120 d_loss: 0.000000 g_loss: 11.238050
Traceback (most recent call last):
File "train.py", line 254, in
main(parse_arguments())
File "train.py", line 248, in main
start=args.start
File "/home/oem/BMSG-GAN/sourcecode/MSG_GAN/GAN.py", line 417, in train
for (i, batch) in enumerate(data, 1):
File "/usr/local/lib/python3.6/dist-packages/torch/utils/data/dataloader.py", line 637, in next
return self._process_next_batch(batch)
File "/usr/local/lib/python3.6/dist-packages/torch/utils/data/dataloader.py", line 658, in _process_next_batch
raise batch.exc_type(batch.exc_msg)
RuntimeError: Traceback (most recent call last):
File "/usr/local/lib/python3.6/dist-packages/torch/utils/data/dataloader.py", line 138, in _worker_loop
samples = collate_fn([dataset[i] for i in batch_indices])
File "/usr/local/lib/python3.6/dist-packages/torch/utils/data/dataloader.py", line 209, in default_collate
return torch.stack(batch, 0, out=out)
RuntimeError: invalid argument 0: Sizes of tensors must match except in dimension 0. Got 3 and 1 in dimension 1 at /pytorch/aten/src/TH/generic/THTensorMoreMath.cpp:1307

another error happens ..

akanimax · 2019-04-23T13:04:02Z

@bemoregt,

I see. There is no handling of Grayscale image case. I'll fix this by tomorrow when I get access to my code (I am currently travelling). For now, could you please remove all the grayscale (black and white) images from your dataset?

Thanks.
@akanimax

bemoregt · 2019-04-23T13:59:51Z

Hi, @akanimax

OK, I see.

I could understand my data's problems...

My images include some rotated & zero-padded images.

Because of those images, May be It happens...

Many Thanks ~

bemoregt · 2019-04-25T00:12:14Z

@akanimax

At current sample state
epoch=227

https://3.bp.blogspot.com/-KY44bqw_nd8/XMD7JNG-6SI/AAAAAAABAkY/lI9VEv8nhWw4xbMFh4RI8tb8nhkjZuImACLcBGAs/s1600/epoch227.png

bemoregt · 2019-04-25T00:28:41Z

Hi, @akanimax celebJapan, epoch=230.., TitanXP + 1080ti [image: epoch227.png] Thanks .. from @bemoregt. 2019년 4월 23일 (화) 오후 6:06, Animesh Karnewar <[email protected]>님이 작성:

…

Could you try updating pytorch to 1.0.0? I hope this solves the problem. — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub <#5 (comment)>, or mute the thread <https://github.com/notifications/unsubscribe-auth/AEUCIZBH7TADL274J3TWE73PR3GRDANCNFSM4HHV3VGA> .

huangzh13 · 2019-04-25T02:50:26Z

Hi, @bemoregt
Could you tell me something about your celebJapan dataset?

Best regards.

bemoregt · 2019-04-25T03:59:00Z

Hi, @huangzh13 @akanimax

Ok, My celebJapan dataset's information is..

Total 3,591 images, including Horizontal Flipped Augmented.
100x100 sized Color Image
about 20KB file size
jpg+png format.

Is this too small dataset for MSG-GAN?

Thanks.

akanimax · 2019-04-25T04:41:16Z

@bemoregt,
The results seem good to me given the size of your dataset. BTW, could you share a full size sheet of the generated images. The one you shared seems to be a screenshot of the image viewer. I think you should let it train for longer and one more thing you could try is to calculate the FID of the models for an objective evalutaion. The data size ok for the resolution. Also try increasing the latent size.
Hope this helps.

Best regards,
@akanimax

bemoregt · 2019-04-25T09:32:40Z

Hi, @akanimax @huangzh13 @owang @sridharmahadevan

It seems that rotated face is very weak for generation using MSG-GAN.

What is the image augmentation technics suitable for face generating GAN?

Thanks .

from @bemoregt

Pascal900 · 2019-04-30T13:44:30Z

@bemoregt,

I see. There is no handling of Grayscale image case. I'll fix this by tomorrow when I get access to my code (I am currently travelling). For now, could you please remove all the grayscale (black and white) images from your dataset?

Thanks.
@akanimax

Hi, @akanimax

I'd be happy to test MSG-GAN on radiology data.

Is there a way to allow for output grayscale images in your next update?

Thanks!

akanimax · 2019-05-02T04:22:22Z

@Pascal900,

Great to hear that you would like to use the MSG-GAN for radiology data. Earlier when I said that I'll handle the Grayscale case, I meant just ignoring the grayscale images from the dataset. But for your case, it seems that all the images in the dataset would be grayscale. Will create a new branch for this development. It is a new addition to the network. Till then one thing you could try is to make RGB images from your gray-scale ones. The network will just learn to output the same values for the R, G and B channels. I have tried it before on MNIST data, it worked pretty well.

Please feel free to ask if you have any more queries.

Best regards,
@akanimax

The expected number of image channels can now be expressed through the "--img_channels" option. This option changes the generator and discriminator architectures to generate/expect the given channel count and changes the data loading mechanism to expect and - if necessary - convert images to have this number of channels. - Fixes the issue with occasional grayscale images in RGB photo data sets reported in akanimax#5 because if --img_channels=3 (default), grayscale images are automatically converted to RGB in preprocessing. - Adds support for training with grayscale images, as requested in akanimax#5. - Makes it easier to implement training with multi-channel images that have more than 3 channels (which I'm planning to try soon). - Enables training with RGB data sets in grayscale mode by simply setting --img_channels=1.

mdraw · 2019-05-31T22:15:58Z

Since I am also working on grayscale radiology data and needed support for that immediately, I've implemented this in #14. @Pascal900, maybe you can try my branch if this use case is still relevant to you. I'd be happy to hear feedback.

The expected number of image channels can now be expressed through the "--img_channels" option. This option changes the generator and discriminator architectures to generate/expect the given channel count and changes the data loading mechanism to expect and - if necessary - convert images to have this number of channels. - Fixes the issue with occasional grayscale images in RGB photo data sets reported in akanimax#5 because if --img_channels=3 (default), grayscale images are automatically converted to RGB in preprocessing. - Adds support for training with grayscale images, as requested in akanimax#5. - Makes it easier to implement training with multi-channel images that have more than 3 channels (which I'm planning to try soon). - Enables training with RGB data sets in grayscale mode by simply setting --img_channels=1.

mdraw mentioned this issue May 31, 2019

Support non-RGB images with --img_channels option #14

Open

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

I have met this error when run train.py ... #5

I have met this error when run train.py ... #5

bemoregt commented Apr 23, 2019

akanimax commented Apr 23, 2019

bemoregt commented Apr 23, 2019 •

edited

Loading

akanimax commented Apr 23, 2019 •

edited

Loading

bemoregt commented Apr 23, 2019

akanimax commented Apr 23, 2019

bemoregt commented Apr 23, 2019

bemoregt commented Apr 23, 2019

akanimax commented Apr 23, 2019

bemoregt commented Apr 23, 2019

akanimax commented Apr 23, 2019

bemoregt commented Apr 23, 2019

bemoregt commented Apr 25, 2019 •

edited

Loading

bemoregt commented Apr 25, 2019 via email

huangzh13 commented Apr 25, 2019

bemoregt commented Apr 25, 2019 •

edited

Loading

akanimax commented Apr 25, 2019

bemoregt commented Apr 25, 2019

Pascal900 commented Apr 30, 2019

akanimax commented May 2, 2019

mdraw commented May 31, 2019

I have met this error when run train.py ... #5

I have met this error when run train.py ... #5

Comments

bemoregt commented Apr 23, 2019

akanimax commented Apr 23, 2019

bemoregt commented Apr 23, 2019 • edited Loading

akanimax commented Apr 23, 2019 • edited Loading

bemoregt commented Apr 23, 2019

akanimax commented Apr 23, 2019

bemoregt commented Apr 23, 2019

bemoregt commented Apr 23, 2019

akanimax commented Apr 23, 2019

bemoregt commented Apr 23, 2019

akanimax commented Apr 23, 2019

bemoregt commented Apr 23, 2019

bemoregt commented Apr 25, 2019 • edited Loading

bemoregt commented Apr 25, 2019 via email

huangzh13 commented Apr 25, 2019

bemoregt commented Apr 25, 2019 • edited Loading

akanimax commented Apr 25, 2019

bemoregt commented Apr 25, 2019

Pascal900 commented Apr 30, 2019

akanimax commented May 2, 2019

mdraw commented May 31, 2019

bemoregt commented Apr 23, 2019 •

edited

Loading

akanimax commented Apr 23, 2019 •

edited

Loading

bemoregt commented Apr 25, 2019 •

edited

Loading

bemoregt commented Apr 25, 2019 •

edited

Loading