(self, x)
| 42 | self.fc2 = nn.Linear(32, num_classes) |
| 43 | |
| 44 | def forward(self, x): |
| 45 | # Convolution 1 |
| 46 | out = self.conv1(x) |
| 47 | # print('After convolution1:', out.shape) |
| 48 | |
| 49 | out = self.bn1(out) |
| 50 | # print('After bn1:', out.shape) |
| 51 | |
| 52 | out = self.prelu1(out) |
| 53 | out = out.reshape(out.shape[0], out.shape[1], -1) |
| 54 | # print('After prelu1:', out.shape) |
| 55 | |
| 56 | # Convolution 2 |
| 57 | out = self.conv2(out) |
| 58 | out = self.bn2(out) |
| 59 | out = self.prelu2(out) |
| 60 | # print('After convolution2, bn2, prelu2:', out.shape) |
| 61 | |
| 62 | # Convolution 3 |
| 63 | out = self.conv3(out) |
| 64 | out = self.bn3(out) |
| 65 | out = self.prelu3(out) |
| 66 | # print('After convolution3, bn3, prelu3:', out.shape) |
| 67 | |
| 68 | # Convolution 4 |
| 69 | out = self.conv4(out) |
| 70 | out = self.bn4(out) |
| 71 | out = self.prelu4(out) |
| 72 | # print('After convolution4, bn4, prelu4:', out.shape) |
| 73 | |
| 74 | # Convolution 5 |
| 75 | out = self.conv5(out) |
| 76 | out = self.bn5(out) |
| 77 | out = self.prelu5(out) |
| 78 | # print('After convolution5, bn5, prelu5:', out.shape) |
| 79 | |
| 80 | # flatten |
| 81 | out = out.view(out.size(0), -1) |
| 82 | # print('After flatten:', out.shape) |
| 83 | |
| 84 | # Linear function 1 |
| 85 | out = self.fc1(out) |
| 86 | out = self.prelu6(out) |
| 87 | # print('After fc1:', out.shape) |
| 88 | |
| 89 | # Linear function (readout) |
| 90 | out = self.fc2(out) |
| 91 | # print('After fc2:', out.shape) |
| 92 | |
| 93 | return out |
nothing calls this directly
no outgoing calls
no test coverage detected