| FullyCNN( | |
| (0): Conv2d(2, 128, kernel_size=(5, 5), stride=(1, 1)) | |
| (1): ReLU() | |
| (2): Conv2d(128, 64, kernel_size=(5, 5), stride=(1, 1)) | |
| (3): ReLU() | |
| (4): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1)) | |
| (5): ReLU() | |
| (6): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1)) | |
| (7): ReLU() | |
| (8): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1)) | |
| (9): ReLU() | |
| (10): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1)) | |
| (11): ReLU() | |
| (12): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1)) | |
| (13): ReLU() | |
| (14): Conv2d(32, 4, kernel_size=(3, 3), stride=(1, 1)) | |
| (final_transformation): SoftPlusTransform(Parameter containing: | |
| tensor(0.1000, requires_grad=True)) | |
| ) |