RuntimeError: expected a non-empty list of Tensors

[hareeshdevarakonda]

Traceback (most recent call last):
File "main.py", line 129, in
train_logger, train_batch_logger)
File "/home/hareesh/Downloads/3D-ResNets-PyTorch-master/train.py", line 22, in train_epoch
for i, (inputs, targets) in enumerate(data_loader):
File "/home/hareesh/.local/lib/python3.5/site-packages/torch/utils/data/dataloader.py", line 286, in next
return self._process_next_batch(batch)
File "/home/hareesh/.local/lib/python3.5/site-packages/torch/utils/data/dataloader.py", line 307, in _process_next_batch
raise batch.exc_type(batch.exc_msg)
RuntimeError: Traceback (most recent call last):
File "/home/hareesh/.local/lib/python3.5/site-packages/torch/utils/data/dataloader.py", line 57, in _worker_loop
samples = collate_fn([dataset[i] for i in batch_indices])
File "/home/hareesh/.local/lib/python3.5/site-packages/torch/utils/data/dataloader.py", line 57, in
samples = collate_fn([dataset[i] for i in batch_indices])
File "/home/hareesh/Downloads/3D-ResNets-PyTorch-master/datasets/ucf101.py", line 193, in getitem
clip = torch.stack(clip, 0).permute(1, 0, 2, 3)
RuntimeError: expected a non-empty list of Tensors

Please let me know cause of this error.

[kenshohara]

Did you correctly set video_path?

[hareeshdevarakonda]

Yeah, Video path is fine added one function in code its running now

##Added Funtion

def loadImages(path, indecies):
# return array of images

loadedImages = []
#print ("path",path," indecies",indecies)
for image in indecies:
    if image < 10:
        img = PImage.open(path + '/' + 'frame00000' + str(image) + '.jpg')    
    elif image < 100:
        img = PImage.open(path + '/' + 'frame0000' + str(image) + '.jpg')
    elif image < 1000:
        img = PImage.open(path + '/' + 'frame000' + str(image) + '.jpg')
    elif image < 10000:
        img = PImage.open(path + '/' + 'frame00' + str(image) + '.jpg')
    else:
        img = PImage.open(path + '/' + 'frame0' + str(image) + '.jpg')

    loadedImages.append(img)

return loadedImages

[ll490187880]

Hello~Where to put your new function? @hareeshdevarakonda

[hareeshdevarakonda]

@ll490187880 No need to keep any new function keep running the same code on pythorch 0.4 version n make sure of your annotation of the images i have annotations like "frame000000" according to this code annotations are like "image_000000". please make sure of these things

[gycka]

@hareeshdevarakonda I tried with the original code and with the included function; however, I got the same error. My path to files is correct, the names are also correct (frame000000). Any suggestions for moving forward (I understand it has been a year since your comment).

[shadsakib]

Hi. Was the problem solved? Thank you.

[TitaniumOne]

I meet the same problem. How do you solve it? Thank you!

[liuzhaoo]

I meet the same problem. How do you solve it? Thank you!
Hi，buddy，Do you have any solution？

[TitaniumOne]

有点忘记了，可能是在get training data里面改一些东西。用print检查检查 | | lh 邮箱：liuhao610216579@163.com | 签名由 网易邮箱大师 定制 On 10/15/2020 11:15, 刘钊 wrote: I meet the same problem. How do you solve it? Thank you! Hi，buddy，Do you have any solution？ — You are receiving this because you commented. Reply to this email directly, view it on GitHub, or unsubscribe.

[liuzhaoo]

在训练的时候是没问题的，但是每个epoch训练完进行验证的时候就会报错。我在VideoDatasetMultiClips 里的__getitem__中打印clips  但是输出并没有这一项。如果你能想起更多东西，麻烦告诉我一下，谢谢！ 415091lz 邮箱415091lz@gmail.com 签名由 网易邮箱大师 定制 On 10/15/2020 11:32, Hao Liu wrote: 有点忘记了，可能是在get training data里面改一些东西。用print检查检查 | | lh 邮箱：liuhao610216579@163.com | 签名由 网易邮箱大师 定制 On 10/15/2020 11:15, 刘钊 wrote: I meet the same problem. How do you solve it? Thank you! Hi，buddy，Do you have any solution？ — You are receiving this because you commented. Reply to this email directly, view it on GitHub, or unsubscribe. — You are receiving this because you commented. Reply to this email directly, view it on GitHub, or unsubscribe.