Automated tutorials push

Author: pytorchbot

_downloads/0080a38f22bd92aa2613545074840623/export_control_flow_model_to_onnx_tutorial.zip

@@ -53,8 +53,8 @@
     "# Create Tensors to hold input and outputs.\n",
     "# By default, requires_grad=False, which indicates that we do not need to\n",
     "# compute gradients with respect to these Tensors during the backward pass.\n",
-    "x = torch.linspace(-math.pi, math.pi, 2000, dtype=dtype)\n",
-    "y = torch.sin(x)\n",
+    "x = torch.linspace(-1, 1, 2000, dtype=dtype)\n",
+    "y = torch.exp(x) # A Taylor expansion would be 1 + x + (1/2) x**2 + (1/3!) x**3 + ...\n",
     "\n",
     "# Create random Tensors for weights. For a third order polynomial, we need\n",
     "# 4 weights: y = a + b x + c x^2 + d x^3\n",
@@ -65,17 +65,23 @@
     "c = torch.randn((), dtype=dtype, requires_grad=True)\n",
     "d = torch.randn((), dtype=dtype, requires_grad=True)\n",
     "\n",
-    "learning_rate = 1e-6\n",
-    "for t in range(2000):\n",
+    "initial_loss = 1.\n",
+    "learning_rate = 1e-5\n",
+    "for t in range(5000):\n",
     "    # Forward pass: compute predicted y using operations on Tensors.\n",
     "    y_pred = a + b * x + c * x ** 2 + d * x ** 3\n",
     "\n",
     "    # Compute and print loss using operations on Tensors.\n",
     "    # Now loss is a Tensor of shape (1,)\n",
     "    # loss.item() gets the scalar value held in the loss.\n",
     "    loss = (y_pred - y).pow(2).sum()\n",
+    "\n",
+    "    # Calculare initial loss, so we can report loss relative to it\n",
+    "    if t==0:\n",
+    "        initial_loss=loss.item()\n",
+    "\n",
     "    if t % 100 == 99:\n",
-    "        print(t, loss.item())\n",
+    "        print(f'Iteration t = {t:4d}  loss(t)/loss(0) = {round(loss.item()/initial_loss, 6):10.6f}  a = {a.item():10.6f}  b = {b.item():10.6f}  c = {c.item():10.6f}  d = {d.item():10.6f}')\n",
     "\n",
     "    # Use autograd to compute the backward pass. This call will compute the\n",
     "    # gradient of loss with respect to all Tensors with requires_grad=True.\n",