train.py run ValueError: Expected more than 1 value per channel when training, got input size [1, 64, 1, 1]

[Gavin666Github]

Traceback (most recent call last): File "train.py", line 286, in <module> x_hat, tran_hat, atp_hat, dehaze21 = netG(input) File "/home/gavin/.local/lib/python3.5/site-packages/torch/nn/modules/module.py", line 477, in __call__ result = self.forward(*input, **kwargs) File "/home/gavin/MyProject/python/image_inpainting/De-haze/DCPDN/models/dehaze22.py", line 696, in forward atp= self.atp_est(x) File "/home/gavin/.local/lib/python3.5/site-packages/torch/nn/modules/module.py", line 477, in __call__ result = self.forward(*input, **kwargs) File "/home/gavin/MyProject/python/image_inpainting/De-haze/DCPDN/models/dehaze22.py", line 473, in forward out7 = self.layer7(out6) File "/home/gavin/.local/lib/python3.5/site-packages/torch/nn/modules/module.py", line 477, in __call__ result = self.forward(*input, **kwargs) File "/home/gavin/.local/lib/python3.5/site-packages/torch/nn/modules/container.py", line 91, in forward input = module(input) File "/home/gavin/.local/lib/python3.5/site-packages/torch/nn/modules/module.py", line 477, in __call__ result = self.forward(*input, **kwargs) File "/home/gavin/.local/lib/python3.5/site-packages/torch/nn/modules/batchnorm.py", line 66, in forward exponential_average_factor, self.eps) File "/home/gavin/.local/lib/python3.5/site-packages/torch/nn/functional.py", line 1251, in batch_norm raise ValueError('Expected more than 1 value per channel when training, got input size {}'.format(size)) ValueError: Expected more than 1 value per channel when training, got input size [1, 64, 1, 1] Exception ignored in: <bound method _DataLoaderIter.__del__ of <torch.utils.data.dataloader._DataLoaderIter object at 0x7f0b2d4afdd8>> Traceback (most recent call last): File "/home/gavin/.local/lib/python3.5/site-packages/torch/utils/data/dataloader.py", line 399, in __del__ File "/home/gavin/.local/lib/python3.5/site-packages/torch/utils/data/dataloader.py", line 378, in _shutdown_workers File "/usr/lib/python3.5/multiprocessing/queues.py", line 345, in get File "<frozen importlib._bootstrap>", line 969, in _find_and_load File "<frozen importlib._bootstrap>", line 954, in _find_and_load_unlocked File "<frozen importlib._bootstrap>", line 887, in _find_spec TypeError: 'NoneType' object is not iterable Is anybody experiencing this problem? batchSize was set to 1.

[hezhangsprinter]

What is your input size ?

[Gavin666Github]

@hezhangsprinter Thank you for your reply! the input parameters are like this:

BTW,I generate the sample using 'create_train.py' ( download the NYU-depth @ http://horatio.cs.nyu.edu/mit/silberman/nyu_depth_v2/nyu_depth_v2_labeled.mat)

[hezhangsprinter]

I mean, what is your input size? 512X512 or ???

[Gavin666Github]

@hezhangsprinter sorry, I use the dataset 'NYU-Depth' ,and I didn't change any size after run 'create_train.py', here I print(input.size()):

it's 224X224. As shown in the above figure,the input parameters are like this: python3 train.py --dataroot ./facades/train --valDataroot ./facades/test --exp ./checkpoints_new Namespace(annealEvery=400, annealStart=0, batchSize=1, beta1=0.5, dataroot='./facades/train', dataset='pix2pix', display=5, evalIter=50, exp='./checkpoints_new', imageSize=256, inputChannelSize=3, lambdaGAN=0.35, lambdaIMG=1, lrD=0.0002, lrG=0.0002, mode='B2A', ndf=64, netD='', netG='', ngf=64, niter=400, originalSize=286, outputChannelSize=3, poolSize=50, valBatchSize=150, valDataroot='./facades/test', wd=0.0, workers=1) Do you mean that I can adjust the input size and retrain,but where to modify this parameter?

Thank you again. I look forward to your reply.

[hezhangsprinter]

You should use size 512x512 for input or any size which is the multiplier of 128 (or 64). Please go over my model to check the reason.

[Gavin666Github]

Thank you very much.