Error while running scripts for "Tissuemnist" and "Organamnist" benchmark

[Muhammad-Huzaifaa]

Scripts used for running:

bash ./script_tissuemnist.sh ewc 0 fixd ../resutls/tissuemnist
bash ./script_organamnist.sh ewc 0 fixd ../resutls/organamnist

Error Message:

Using downloaded and verified file: ../data/tissuemnist/tissuemnist.npz
Using downloaded and verified file: ../data/tissuemnist/tissuemnist.npz
[(0, 2), (1, 2), (2, 2), (3, 2)]

---

Task 0

---

Traceback (most recent call last):
File "/home/muhammad.huzaifa/Documents/LifeLonger/src/main_incremental.py", line 348, in
main()
File "/home/muhammad.huzaifa/Documents/LifeLonger/src/main_incremental.py", line 294, in main
appr.train(t, trn_loader[t], val_loader[t])
File "/home/muhammad.huzaifa/Documents/LifeLonger/src/approach/incremental_learning.py", line 56, in train
self.train_loop(t, trn_loader, val_loader)
File "/home/muhammad.huzaifa/Documents/LifeLonger/src/approach/ewc.py", line 112, in train_loop
super().train_loop(t, trn_loader, val_loader)
File "/home/muhammad.huzaifa/Documents/LifeLonger/src/approach/incremental_learning.py", line 111, in train_loop
self.train_epoch(t, trn_loader)
File "/home/muhammad.huzaifa/Documents/LifeLonger/src/approach/incremental_learning.py", line 170, in train_epoch
outputs = self.model(images.to(self.device))
File "/home/muhammad.huzaifa/.conda/envs/lifelonger/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/muhammad.huzaifa/Documents/LifeLonger/src/networks/network.py", line 67, in forward
x = self.model(x)
File "/home/muhammad.huzaifa/.conda/envs/lifelonger/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/muhammad.huzaifa/.conda/envs/lifelonger/lib/python3.8/site-packages/torchvision/models/resnet.py", line 220, in forward
return self._forward_impl(x)
File "/home/muhammad.huzaifa/.conda/envs/lifelonger/lib/python3.8/site-packages/torchvision/models/resnet.py", line 203, in _forward_impl
x = self.conv1(x)
File "/home/muhammad.huzaifa/.conda/envs/lifelonger/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/muhammad.huzaifa/.conda/envs/lifelonger/lib/python3.8/site-packages/torch/nn/modules/conv.py", line 423, in forward
return self._conv_forward(input, self.weight)
File "/home/muhammad.huzaifa/.conda/envs/lifelonger/lib/python3.8/site-packages/torch/nn/modules/conv.py", line 419, in _conv_forward
return F.conv2d(input, weight, self.bias, self.stride,
RuntimeError: Given groups=1, weight of size [64, 3, 7, 7], expected input[32, 1, 32, 32] to have 3 channels, but got 1 channels instead

[samjavadinia]

you should change the dataset-config to have 'extend_channel': 3 inside those datasets config