Removal of unnecessary lines and uncommenting targets_all list variable.

[abhaskumarsinha]

models/Conv_DCFE.py - The main was commented out. It returns an error while running them because of self.coef variable wasn't given to them.

Traceback (most recent call last):
  File "/content/CL_Atom_Swapping/./models/Conv_DCFE.py", line 102, in <module>
    print(layer(data))
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1501, in _call_impl
    return forward_call(*args, **kwargs)
  File "/content/CL_Atom_Swapping/./models/Conv_DCFE.py", line 68, in forward
    coef = self.coef.view(self.out_channels, self.in_channels, self.num_bases)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1614, in __getattr__
    raise AttributeError("'{}' object has no attribute '{}'".format(
AttributeError: 'Conv_DCFDE' object has no attribute 'coef'

models/resnet18_dcf_bsensemble_imgnet.py - Block expand argument was removed. It is useless.

models/resnet32_dcf_bsensemble.py - same as before

train_dcfens_cifar100_CI.py - some code was commented out (probably for debugging purposes) was added in. Unnecessary arguments from add_branch method were removed.

train_dcfens_imgnet100_CI.py - same as before

The code now runs without any error for CIFAR-100 (/content/CL_Atom_Swapping/train_dcfens_cifar100_CI.py)
Example output for first few epochs:

Colab (Please remember to enable GPU runtime from Runtime tab) : https://colab.research.google.com/drive/1XxYXgET7wVibtLy3q-6vuci7bx5qzJSH?usp=sharing

Args:
Namespace(data_path='Datasets/CIFAR100', num_class=100, num_task=6, first_task_cls=50, dataset='cifar100', train_batch=64, test_batch=128, workers=8, random_classes=False, validation=0.0, overflow=False, model='resnet32', lr=0.01, lr_sub=0.01, lr_schedule='100-200', lr_schedule_sub='100-200', total_epoch=250, total_epoch_sub=250, wd=0.005, wd_sub=0.005, optim='sgd', gpu='0', init_with_pre=True, start_from=0, num_bases=12, num_member=2, add_description='', class_per_task=16, model_path='checkpoints/cifar100_6tasks_firstcls50_member2_resnet32_bases12_wd0.005_sgd')

Files already downloaded and verified
Files already downloaded and verified
Order:  [68, 56, 78, 8, 23, 84, 90, 65, 74, 76, 40, 89, 3, 92, 55, 9, 26, 80, 43, 38, 58, 70, 77, 1, 85, 19, 17, 50, 28, 53, 13, 81, 45, 82, 6, 59, 83, 16, 15, 44, 91, 41, 72, 60, 79, 52, 20, 10, 31, 54, 37, 95, 14, 71, 96, 98, 97, 2, 64, 66, 42, 22, 35, 86, 24, 34, 87, 21, 99, 0, 88, 27, 18, 94, 11, 12, 47, 25, 30, 46, 62, 69, 36, 61, 7, 63, 75, 5, 32, 4, 51, 48, 73, 93, 39, 67, 29, 49, 57, 33]
0
[50, 10, 10, 10, 10, 10]
/usr/local/lib/python3.10/dist-packages/torch/utils/data/dataloader.py:560: UserWarning: This DataLoader will create 16 worker processes in total. Our suggested max number of worker in current system is 2, which is smaller than what this DataLoader is going to create. Please be aware that excessive worker creation might get DataLoader running slow or even freeze, lower the worker number to avoid potential slowness/freeze if necessary.
  warnings.warn(_create_warning_msg(
1
[50, 10, 10, 10, 10, 10]
2
[50, 10, 10, 10, 10, 10]
3
[50, 10, 10, 10, 10, 10]
4
[50, 10, 10, 10, 10, 10]
5
[50, 10, 10, 10, 10, 10]
Training Task :---0
***Optimized Parameters:
0.conv_module.0.weight, 0.conv_module.0.bias, 0.conv_module.1.weight, 0.conv_module.1.bias, 1.conv1.bases, 1.bn1.bn0.weight, 1.bn1.bn0.bias, 1.bn1.bn1.weight, 1.bn1.bn1.bias, 1.conv2.bases, 1.bn2.bn0.weight, 1.bn2.bn0.bias, 1.bn2.bn1.weight, 1.bn2.bn1.bias, 2.conv1.bases, 2.bn1.bn0.weight, 2.bn1.bn0.bias, 2.bn1.bn1.weight, 2.bn1.bn1.bias, 2.conv2.bases, 2.bn2.bn0.weight, 2.bn2.bn0.bias, 2.bn2.bn1.weight, 2.bn2.bn1.bias, 3.conv1.bases, 3.bn1.bn0.weight, 3.bn1.bn0.bias, 3.bn1.bn1.weight, 3.bn1.bn1.bias, 3.conv2.bases, 3.bn2.bn0.weight, 3.bn2.bn0.bias, 3.bn2.bn1.weight, 3.bn2.bn1.bias, 4.conv1.bases, 4.bn1.bn0.weight, 4.bn1.bn0.bias, 4.bn1.bn1.weight, 4.bn1.bn1.bias, 4.conv2.bases, 4.bn2.bn0.weight, 4.bn2.bn0.bias, 4.bn2.bn1.weight, 4.bn2.bn1.bias, 5.conv1.bases, 5.bn1.bn0.weight, 5.bn1.bn0.bias, 5.bn1.bn1.weight, 5.bn1.bn1.bias, 5.conv2.bases, 5.bn2.bn0.weight, 5.bn2.bn0.bias, 5.bn2.bn1.weight, 5.bn2.bn1.bias, 6.conv1.bases, 6.bn1.bn0.weight, 6.bn1.bn0.bias, 6.bn1.bn1.weight, 6.bn1.bn1.bias, 6.conv2.bases, 6.bn2.bn0.weight, 6.bn2.bn0.bias, 6.bn2.bn1.weight, 6.bn2.bn1.bias, 6.downsample.0.weight, 6.downsample.1.bn0.weight, 6.downsample.1.bn0.bias, 6.downsample.1.bn1.weight, 6.downsample.1.bn1.bias, 7.conv1.bases, 7.bn1.bn0.weight, 7.bn1.bn0.bias, 7.bn1.bn1.weight, 7.bn1.bn1.bias, 7.conv2.bases, 7.bn2.bn0.weight, 7.bn2.bn0.bias, 7.bn2.bn1.weight, 7.bn2.bn1.bias, 8.conv1.bases, 8.bn1.bn0.weight, 8.bn1.bn0.bias, 8.bn1.bn1.weight, 8.bn1.bn1.bias, 8.conv2.bases, 8.bn2.bn0.weight, 8.bn2.bn0.bias, 8.bn2.bn1.weight, 8.bn2.bn1.bias, 9.conv1.bases, 9.bn1.bn0.weight, 9.bn1.bn0.bias, 9.bn1.bn1.weight, 9.bn1.bn1.bias, 9.conv2.bases, 9.bn2.bn0.weight, 9.bn2.bn0.bias, 9.bn2.bn1.weight, 9.bn2.bn1.bias, 10.conv1.bases, 10.bn1.bn0.weight, 10.bn1.bn0.bias, 10.bn1.bn1.weight, 10.bn1.bn1.bias, 10.conv2.bases, 10.bn2.bn0.weight, 10.bn2.bn0.bias, 10.bn2.bn1.weight, 10.bn2.bn1.bias, 11.conv1.bases, 11.bn1.bn0.weight, 11.bn1.bn0.bias, 11.bn1.bn1.weight, 11.bn1.bn1.bias, 11.conv2.bases, 11.bn2.bn0.weight, 11.bn2.bn0.bias, 11.bn2.bn1.weight, 11.bn2.bn1.bias, 11.downsample.0.weight, 11.downsample.1.bn0.weight, 11.downsample.1.bn0.bias, 11.downsample.1.bn1.weight, 11.downsample.1.bn1.bias, 12.conv1.bases, 12.bn1.bn0.weight, 12.bn1.bn0.bias, 12.bn1.bn1.weight, 12.bn1.bn1.bias, 12.conv2.bases, 12.bn2.bn0.weight, 12.bn2.bn0.bias, 12.bn2.bn1.weight, 12.bn2.bn1.bias, 13.conv1.bases, 13.bn1.bn0.weight, 13.bn1.bn0.bias, 13.bn1.bn1.weight, 13.bn1.bn1.bias, 13.conv2.bases, 13.bn2.bn0.weight, 13.bn2.bn0.bias, 13.bn2.bn1.weight, 13.bn2.bn1.bias, 14.conv1.bases, 14.bn1.bn0.weight, 14.bn1.bn0.bias, 14.bn1.bn1.weight, 14.bn1.bn1.bias, 14.conv2.bases, 14.bn2.bn0.weight, 14.bn2.bn0.bias, 14.bn2.bn1.weight, 14.bn2.bn1.bias, 15.conv1.bases, 15.bn1.bn0.weight, 15.bn1.bn0.bias, 15.bn1.bn1.weight, 15.bn1.bn1.bias, 15.conv2.bases, 15.bn2.bn0.weight, 15.bn2.bn0.bias, 15.bn2.bn1.weight, 15.bn2.bn1.bias, linears.0.weight, linears.0.bias, linears.1.weight, linears.1.bias, coeff_list.0, coeff_list.1, coeff_list.2, coeff_list.3, coeff_list.4, coeff_list.5, coeff_list.6, coeff_list.7, coeff_list.8, coeff_list.9, coeff_list.10, coeff_list.11, coeff_list.12, coeff_list.13, coeff_list.14, coeff_list.15, coeff_list.16, coeff_list.17, coeff_list.18, coeff_list.19, coeff_list.20, coeff_list.21, coeff_list.22, coeff_list.23, coeff_list.24, coeff_list.25, coeff_list.26, coeff_list.27, coeff_list.28, coeff_list.29
LR Drop Schedule:  [100, 200]

Task: 0, Epoch: 0
[Train: ], [0/250: ], [Accuracy: 9.76], [Loss: 6.950796], [Lr: 0.010000]
[Test TI Acc.: 13.38] [Loss: 3.256159] [Correct: 1.000000]
Saving..

Task: 0, Epoch: 1
[Train: ], [1/250: ], [Accuracy: 19.52], [Loss: 5.938179], [Lr: 0.010000]
[Test TI Acc.: 20.70] [Loss: 3.021781] [Correct: 1.000000]
Saving..

Task: 0, Epoch: 2
[Train: ], [2/250: ], [Accuracy: 26.00], [Loss: 5.370432], [Lr: 0.010000]
[Test TI Acc.: 30.60] [Loss: 2.615830] [Correct: 1.000000]
Saving..

Task: 0, Epoch: 3
[Train: ], [3/250: ], [Accuracy: 31.34], [Loss: 4.930373], [Lr: 0.010000]
[Test TI Acc.: 30.52] [Loss: 2.605773] [Correct: 1.000000]