conv_snn
conv_snn copied to clipboard
RuntimeError: view size is not compatible with input tensor's size and stride (at least one dimension spans across two contiguous subspaces). Use .reshape(...) instead.
Got an error in Training & Testing
(conv_snn) test@test-dual1060:~/Desktop/project/conv_snn/CIFAR10-DVS$ python3 main.py
device cuda
0%| | 0/1750 [00:00<?, ?it/s]
==> Build model and setup loss and optimizer
==> Epoch:[0/500][training stage]
0%| | 0/1750 [00:00<?, ?it/s]
Traceback (most recent call last):
File "main.py", line 231, in <module>
main()
File "main.py", line 65, in main
model.run()
File "main.py", line 124, in run
self.train_1epoch()
File "main.py", line 172, in train_1epoch
prec1, prec5 = accuracy(output.data, label.cuda(), topk=(1, 5))
File "/home/test/Desktop/project/conv_snn/CIFAR10-DVS/utils.py", line 30, in accuracy
correct_k = correct[:k].view(-1).float().sum(0)
RuntimeError: view size is not compatible with input tensor's size and stride (at least one dimension spans across two contiguous subspaces). Use .reshape(...) instead.
what is the dataset?! what are the shapes?! is this the default dataset?! please also provide the pytorch version.
thanks for reply so fast. Training dvs-cifar10 and all settings were default, just following the readme.
pytorch version is 1.7.1
I add contiguous() to line30 in conv_snn/CIFAR10-DVS/utils.py/
and start to train
correct_k = correct[:k].contiguous().view(-1).float().sum(0)
but got another error FileNotFoundError: [Errno 2] No such file or directory: 'record/spatial/rgb_train.csv'
it is my job ;) well it appears there is a difference in view function of newer pytorch versions, the second problem is odd!! ok, i don't have access to my laptop now, it will take approx 12 hours to check this. I will inform you about the problem and the possible fix.