<>1.pytorch报错
Namespace(batchSize=16, gpu='0,1', lr=0.001, nepoch=210, num_workers=8) Epoch:
0 Epoch:0 [0|173089] loss:3.747539 Epoch:0 [1|173089] loss:3.629151 Epoch:0
[2|173089] loss:3.731266 Traceback (most recent call last): File "train.py",
line 81, in <module> train(epoch) File "train.py", line 55, in train for
batch_idx,(img,label) in enumerate(trainloader): File
"/usr/local/lib/python3.5/dist-packages/torch/utils/data/dataloader.py", line
336, in __next__ return self._process_next_batch(batch) File
"/usr/local/lib/python3.5/dist-packages/torch/utils/data/dataloader.py", line
357, in _process_next_batch raise batch.exc_type(batch.exc_msg) RuntimeError:
Traceback (most recent call last): File
"/usr/local/lib/python3.5/dist-packages/torch/utils/data/dataloader.py", line
106, in _worker_loop samples = collate_fn([dataset[i] for i in batch_indices])
File "/usr/local/lib/python3.5/dist-packages/torch/utils/data/dataloader.py",
line 187, in default_collate return [default_collate(samples) for samples in
transposed] File
"/usr/local/lib/python3.5/dist-packages/torch/utils/data/dataloader.py", line
187, in <listcomp> return [default_collate(samples) for samples in transposed]
File "/usr/local/lib/python3.5/dist-packages/torch/utils/data/dataloader.py",
line 164, in default_collate return torch.stack(batch, 0, out=out)
RuntimeError: invalid argument 0: Sizes of tensors must match except in
dimension 0. Got 1 and 3 in dimension 1 at
/pytorch/aten/src/TH/generic/THTensorMath.cpp:3616
<>2. 解决方案

dataloader
def __getitem__(self,index): img_path=self.imgs[index]
label=self.labels[index] data=Image.open(img_path) # data = data.convert('RGB')
data=self.transform(data) return data,label
<>3.错误分析


使用DataLoader加载图像,这些图像中的一些具有3个通道(彩色图像),而其他图像可能具有单个通道(BW图像),由于dim1的尺寸不同,因此无法将它们连接成批次。
尝试将img = img.convert(‘RGB’)添加到数据集中的__getitem__中。

<>4.参考资料

https://discuss.pytorch.org/t/runtimeerror-invalid-argument-0/17919/5
<https://discuss.pytorch.org/t/runtimeerror-invalid-argument-0/17919/5>