Update README.md

README.md

@@ -41,7 +41,22 @@ FAQ (as the author imagines):
 
 Instead of the `bottleneck` block of ResNet50 which consists of 1x1, 3x3, 1x1 in succession, this simplest version of QLNet does a 1x1, splits into two equal halves and **multiplies** them, then applies a 3x3 (depthwise), and a 1x1, *all without activation functions* except at the end of the block, where a "radial" activation function that we call `hardball` is applied.
 
-
+```python
+class QLNet(nn.Module:
+  ...
+
+  def forward(self, x):
+    x0 = self.skip(x)
+    x = self.conv1(x)  # 1x1
+    C = x.size(1) // 2
+    x = x[:, :C, :, :] * x[:, C:, :, :]
+    x = self.conv2(x)  # 3x3
+    x = self.conv3(x)  # 1x1
+    x += x0
+    if self.act3 is not None:
+        x = self.act3(x)
+    return x
+```
 
 - **Developed by:** Yao Liu 刘杳
 - **Model type:** Convolutional Neural Network (ConvNet)