New ONNX ops and testsHEADmaster

New ops: Slice, Squeeze, Unsqueeze
New tests based on papers:
 - Wide-to-Deep, Deep-to-Wide Transformation
 - Pruining of stably inactive (always negative) and active (always
   positive) ReLUs

1 files changed, 57 insertions, 0 deletions

diff --git a/examples/iris/iris_stably_inactive.py b/examples/iris/iris_stably_inactive.py
new file mode 100644
index 0000000..684f967
--- /dev/null
+++ b/examples/iris/iris_stably_inactive.py
@@ -0,0 +1,57 @@
+import torch, torch.nn as nn
+from sklearn.datasets import load_iris
+from sklearn.preprocessing import StandardScaler
+from torch.utils.data import DataLoader, TensorDataset
+
+class Iris_MLP(nn.Module):
+    def __init__(self, hidden_dim):
+        super().__init__()
+        self.layers = nn.Sequential(
+            nn.Linear(4, hidden_dim),
+            nn.ReLU(),
+            nn.Linear(hidden_dim, 3),
+        )
+    def forward(self, x):
+        return self.layers(x)
+
+iris = load_iris()
+scaler = StandardScaler()
+X = scaler.fit_transform(iris.data).astype('float32') # pyright: ignore
+y = iris.target.astype('int64') # pyright: ignore
+
+dataset = TensorDataset(torch.from_numpy(X), torch.from_numpy(y))
+trainloader = DataLoader(dataset, batch_size=16, shuffle=True)
+
+def train_model(name: str, dim):
+    net = Iris_MLP(hidden_dim=dim)
+    loss_fn = nn.CrossEntropyLoss()
+    optimizer = torch.optim.Adam(net.parameters(), lr=1e-2)
+
+    print(f"Training {name} ({dim} neurons)...")
+    for epoch in range(100):
+        global loss
+        for data in trainloader:
+            inputs, targets = data
+            optimizer.zero_grad()
+            outputs = net(inputs)
+            loss = loss_fn(outputs, targets)
+            loss.backward()
+            optimizer.step()
+        if (epoch + 1) % 10 == 0:
+            print(f"  Epoch {epoch+1}, Loss: {loss.item():.4f}")
+    return net
+
+if __name__ == "__main__":
+    torch_net_a = train_model("Network A", 10).eval()
+    
+    with torch.no_grad():
+        torch_net_a.layers[0].weight[9] = -1.0 # pyright: ignore
+        torch_net_a.layers[0].bias[9] = -10.0 # pyright: ignore
+        
+        torch_net_b = Iris_MLP(10).eval()
+        torch_net_b.load_state_dict(torch_net_a.state_dict())
+        
+        torch_net_b.layers[2].weight[:, 9] = 0.0 # pyright: ignore
+        
+    torch.onnx.export(torch_net_a, (torch.randn(1, 4),), "iris_a.onnx")
+    torch.onnx.export(torch_net_b, (torch.randn(1, 4),), "iris_b.onnx")