updates files

sekyondaMeta · Mar 7, 2023 · 98c3bb1 · 98c3bb1
1 parent 4331035
commit 98c3bb1
Show file tree

Hide file tree

Showing 13 changed files with 844 additions and 348 deletions.
diff --git a/docs/02-Quickstart.md b/docs/02-Quickstart.md
@@ -229,78 +229,78 @@ print("Done!")
 
     Epoch 1
     -------------------------------
-    loss: 2.300704  [    0/60000]
-    loss: 2.294491  [ 6400/60000]
-    loss: 2.270792  [12800/60000]
-    loss: 2.270757  [19200/60000]
-    loss: 2.246651  [25600/60000]
-    loss: 2.223734  [32000/60000]
-    loss: 2.230299  [38400/60000]
-    loss: 2.197789  [44800/60000]
-    loss: 2.186385  [51200/60000]
-    loss: 2.171854  [57600/60000]
+    loss: 2.300994  [    0/60000]
+    loss: 2.289627  [ 6400/60000]
+    loss: 2.278757  [12800/60000]
+    loss: 2.273481  [19200/60000]
+    loss: 2.260533  [25600/60000]
+    loss: 2.230715  [32000/60000]
+    loss: 2.240870  [38400/60000]
+    loss: 2.210235  [44800/60000]
+    loss: 2.205794  [51200/60000]
+    loss: 2.179301  [57600/60000]
     Test Error: 
-     Accuracy: 40.4%, Avg loss: 2.158354 
+     Accuracy: 42.7%, Avg loss: 2.175595 
 
     Epoch 2
     -------------------------------
-    loss: 2.157282  [    0/60000]
-    loss: 2.157837  [ 6400/60000]
-    loss: 2.098653  [12800/60000]
-    loss: 2.123712  [19200/60000]
-    loss: 2.070209  [25600/60000]
-    loss: 2.017735  [32000/60000]
-    loss: 2.044564  [38400/60000]
-    loss: 1.971302  [44800/60000]
-    loss: 1.963748  [51200/60000]
-    loss: 1.920766  [57600/60000]
+    loss: 2.179688  [    0/60000]
+    loss: 2.170581  [ 6400/60000]
+    loss: 2.125383  [12800/60000]
+    loss: 2.134987  [19200/60000]
+    loss: 2.104071  [25600/60000]
+    loss: 2.039638  [32000/60000]
+    loss: 2.065766  [38400/60000]
+    loss: 1.994649  [44800/60000]
+    loss: 1.991123  [51200/60000]
+    loss: 1.927214  [57600/60000]
     Test Error: 
-     Accuracy: 55.5%, Avg loss: 1.902382 
+     Accuracy: 56.1%, Avg loss: 1.929943 
 
     Epoch 3
     -------------------------------
-    loss: 1.919148  [    0/60000]
-    loss: 1.903148  [ 6400/60000]
-    loss: 1.782882  [12800/60000]
-    loss: 1.834309  [19200/60000]
-    loss: 1.722989  [25600/60000]
-    loss: 1.676954  [32000/60000]
-    loss: 1.698752  [38400/60000]
-    loss: 1.602475  [44800/60000]
-    loss: 1.614792  [51200/60000]
-    loss: 1.532669  [57600/60000]
+    loss: 1.957387  [    0/60000]
+    loss: 1.929036  [ 6400/60000]
+    loss: 1.825893  [12800/60000]
+    loss: 1.850506  [19200/60000]
+    loss: 1.775094  [25600/60000]
+    loss: 1.708617  [32000/60000]
+    loss: 1.727947  [38400/60000]
+    loss: 1.628896  [44800/60000]
+    loss: 1.653404  [51200/60000]
+    loss: 1.548985  [57600/60000]
     Test Error: 
-     Accuracy: 61.7%, Avg loss: 1.533873 
+     Accuracy: 60.7%, Avg loss: 1.570322 
 
     Epoch 4
     -------------------------------
-    loss: 1.585873  [    0/60000]
-    loss: 1.560321  [ 6400/60000]
-    loss: 1.407954  [12800/60000]
-    loss: 1.488211  [19200/60000]
-    loss: 1.364034  [25600/60000]
-    loss: 1.362447  [32000/60000]
-    loss: 1.370802  [38400/60000]
-    loss: 1.302972  [44800/60000]
-    loss: 1.327800  [51200/60000]
-    loss: 1.235748  [57600/60000]
+    loss: 1.634544  [    0/60000]
+    loss: 1.598077  [ 6400/60000]
+    loss: 1.457816  [12800/60000]
+    loss: 1.511364  [19200/60000]
+    loss: 1.425202  [25600/60000]
+    loss: 1.398494  [32000/60000]
+    loss: 1.412483  [38400/60000]
+    loss: 1.328141  [44800/60000]
+    loss: 1.371268  [51200/60000]
+    loss: 1.270080  [57600/60000]
     Test Error: 
-     Accuracy: 63.4%, Avg loss: 1.260575 
+     Accuracy: 63.2%, Avg loss: 1.298073 
 
     Epoch 5
     -------------------------------
-    loss: 1.331637  [    0/60000]
-    loss: 1.313866  [ 6400/60000]
-    loss: 1.153163  [12800/60000]
-    loss: 1.257744  [19200/60000]
-    loss: 1.137783  [25600/60000]
-    loss: 1.162715  [32000/60000]
-    loss: 1.172138  [38400/60000]
-    loss: 1.120971  [44800/60000]
-    loss: 1.149632  [51200/60000]
-    loss: 1.069323  [57600/60000]
+    loss: 1.375485  [    0/60000]
+    loss: 1.353134  [ 6400/60000]
+    loss: 1.197045  [12800/60000]
+    loss: 1.282228  [19200/60000]
+    loss: 1.185837  [25600/60000]
+    loss: 1.195442  [32000/60000]
+    loss: 1.213788  [38400/60000]
+    loss: 1.140980  [44800/60000]
+    loss: 1.188507  [51200/60000]
+    loss: 1.102179  [57600/60000]
     Test Error: 
-     Accuracy: 64.6%, Avg loss: 1.093657 
+     Accuracy: 64.6%, Avg loss: 1.124997 
 
     Done!
 

diff --git a/docs/03-Tensors.md b/docs/03-Tensors.md
@@ -73,8 +73,8 @@ print(f"Random Tensor: \n {x_rand} \n")
             [1, 1]]) 
 
     Random Tensor: 
-     tensor([[0.0504, 0.9505],
-            [0.6485, 0.6105]]) 
+     tensor([[0.7786, 0.0142],
+            [0.3120, 0.9157]]) 
 
 
 
@@ -97,8 +97,8 @@ print(f"Zeros Tensor: \n {zeros_tensor}")
 ```
 
     Random Tensor: 
-     tensor([[0.6582, 0.2838, 0.1244],
-            [0.1692, 0.0394, 0.2638]]) 
+     tensor([[0.7263, 0.5640, 0.3222],
+            [0.9226, 0.3125, 0.3739]]) 
 
     Ones Tensor: 
      tensor([[1., 1., 1.],

diff --git a/docs/04-Data.md b/docs/04-Data.md
@@ -1,8 +1,3 @@
-```python
-%matplotlib inline
-```
-
-
 [Learn the Basics](intro.html) ||
 [Quickstart](quickstart_tutorial.html) ||
 [Tensors](tensorqs_tutorial.html) ||
@@ -49,6 +44,8 @@ We load the [FashionMNIST Dataset](https://pytorch.org/vision/stable/datasets.ht
 
 
 ```python
+%matplotlib inline
+
 import torch
 from torch.utils.data import Dataset
 from torchvision import datasets
@@ -106,7 +103,7 @@ plt.show()
 
 
 
-![png](../docs/04-Data_files/../docs/04-Data_6_0.png)
+![png](../docs/04-Data_files/../docs/04-Data_5_0.png)
 
 
 
@@ -268,11 +265,11 @@ print(f"Label: {label}")
 
 
 
-![png](../docs/04-Data_files/../docs/04-Data_21_1.png)
+![png](../docs/04-Data_files/../docs/04-Data_20_1.png)
 
 
 
-    Label: 1
+    Label: 3
 
 
 --------------

diff --git a/docs/06-BuildModel.md b/docs/06-BuildModel.md
@@ -115,7 +115,7 @@ y_pred = pred_probab.argmax(1)
 print(f"Predicted class: {y_pred}")
 ```
 
-    Predicted class: tensor([9])
+    Predicted class: tensor([1])
 
 
 --------------
@@ -191,30 +191,26 @@ hidden1 = nn.ReLU()(hidden1)
 print(f"After ReLU: {hidden1}")
 ```
 
-    Before ReLU: tensor([[-5.5712e-01,  4.1135e-01, -7.4510e-03, -5.4891e-02,  7.3538e-02,
-              4.6617e-01,  5.3287e-01,  7.2283e-02, -3.7471e-01, -3.9285e-01,
-             -6.7889e-01,  2.1088e-01,  1.8742e-01,  4.0150e-01, -5.6422e-02,
-             -4.8977e-02, -1.6230e-01,  3.0556e-01, -7.1455e-01, -6.6180e-02],
-            [-4.2601e-01,  6.2487e-01, -5.9415e-02,  2.3934e-02,  3.9810e-01,
-              3.2441e-01,  7.0026e-01, -1.2423e-01, -5.2260e-01, -1.7234e-01,
-             -5.5835e-01,  2.2128e-01,  2.7830e-01,  2.4191e-01, -7.7681e-02,
-             -2.4954e-01,  1.5836e-01,  1.9990e-01, -1.1715e-01, -3.2138e-01],
-            [-4.9225e-01,  4.1050e-01, -1.5492e-01,  8.9106e-03,  3.5985e-01,
-              3.1355e-01,  6.2615e-01, -1.9053e-04, -5.7080e-01, -1.7064e-01,
-             -6.5802e-01,  3.3700e-01,  4.5726e-01,  3.1022e-01, -4.0316e-01,
-             -3.8029e-01, -1.2243e-01,  3.6732e-01, -5.6789e-01, -9.4490e-02]],
-           grad_fn=<AddmmBackward0>)
+    Before ReLU: tensor([[-0.6535,  0.0475,  0.2762,  0.2739,  0.3857,  0.1837, -0.1904, -0.3036,
+             -0.0609, -0.2871,  0.0446,  0.2365, -0.2100,  0.3802,  0.1994, -0.4515,
+              0.1591,  0.1378,  0.1966, -0.0231],
+            [-0.7906,  0.0717,  0.3879,  0.0195,  0.2133,  0.4331,  0.1080, -0.3002,
+             -0.0044, -0.3400,  0.2174,  0.4808, -0.1150,  0.2409,  0.3484, -0.0483,
+              0.3890,  0.1460,  0.1570,  0.1086],
+            [-0.8346,  0.3771,  0.3634, -0.3699,  0.5272, -0.2396, -0.4630, -0.0269,
+             -0.0439, -0.4653,  0.1175,  0.4506, -0.1127,  0.1764,  0.1627,  0.0395,
+              0.4420,  0.1518,  0.0156,  0.0423]], grad_fn=<AddmmBackward0>)
 
 
-    After ReLU: tensor([[0.0000, 0.4113, 0.0000, 0.0000, 0.0735, 0.4662, 0.5329, 0.0723, 0.0000,
-             0.0000, 0.0000, 0.2109, 0.1874, 0.4015, 0.0000, 0.0000, 0.0000, 0.3056,
-             0.0000, 0.0000],
-            [0.0000, 0.6249, 0.0000, 0.0239, 0.3981, 0.3244, 0.7003, 0.0000, 0.0000,
-             0.0000, 0.0000, 0.2213, 0.2783, 0.2419, 0.0000, 0.0000, 0.1584, 0.1999,
-             0.0000, 0.0000],
-            [0.0000, 0.4105, 0.0000, 0.0089, 0.3599, 0.3136, 0.6262, 0.0000, 0.0000,
-             0.0000, 0.0000, 0.3370, 0.4573, 0.3102, 0.0000, 0.0000, 0.0000, 0.3673,
-             0.0000, 0.0000]], grad_fn=<ReluBackward0>)
+    After ReLU: tensor([[0.0000, 0.0475, 0.2762, 0.2739, 0.3857, 0.1837, 0.0000, 0.0000, 0.0000,
+             0.0000, 0.0446, 0.2365, 0.0000, 0.3802, 0.1994, 0.0000, 0.1591, 0.1378,
+             0.1966, 0.0000],
+            [0.0000, 0.0717, 0.3879, 0.0195, 0.2133, 0.4331, 0.1080, 0.0000, 0.0000,
+             0.0000, 0.2174, 0.4808, 0.0000, 0.2409, 0.3484, 0.0000, 0.3890, 0.1460,
+             0.1570, 0.1086],
+            [0.0000, 0.3771, 0.3634, 0.0000, 0.5272, 0.0000, 0.0000, 0.0000, 0.0000,
+             0.0000, 0.1175, 0.4506, 0.0000, 0.1764, 0.1627, 0.0395, 0.4420, 0.1518,
+             0.0156, 0.0423]], grad_fn=<ReluBackward0>)
 
 
 ### nn.Sequential
@@ -281,23 +277,23 @@ for name, param in model.named_parameters():
     )
 
 
-    Layer: linear_relu_stack.0.weight | Size: torch.Size([512, 784]) | Values : tensor([[ 0.0211,  0.0168,  0.0334,  ..., -0.0151, -0.0033,  0.0032],
-            [-0.0022,  0.0293, -0.0090,  ..., -0.0044, -0.0147, -0.0251]],
+    Layer: linear_relu_stack.0.weight | Size: torch.Size([512, 784]) | Values : tensor([[ 0.0007,  0.0351,  0.0290,  ...,  0.0157, -0.0041, -0.0052],
+            [ 0.0163, -0.0053,  0.0237,  ..., -0.0294,  0.0200,  0.0072]],
            grad_fn=<SliceBackward0>) 
 
-    Layer: linear_relu_stack.0.bias | Size: torch.Size([512]) | Values : tensor([0.0128, 0.0086], grad_fn=<SliceBackward0>) 
+    Layer: linear_relu_stack.0.bias | Size: torch.Size([512]) | Values : tensor([-0.0143, -0.0101], grad_fn=<SliceBackward0>) 
 
-    Layer: linear_relu_stack.2.weight | Size: torch.Size([512, 512]) | Values : tensor([[-0.0165, -0.0068, -0.0016,  ..., -0.0098,  0.0119,  0.0326],
-            [ 0.0330, -0.0306, -0.0129,  ..., -0.0371, -0.0291, -0.0273]],
+    Layer: linear_relu_stack.2.weight | Size: torch.Size([512, 512]) | Values : tensor([[-0.0091,  0.0016,  0.0303,  ...,  0.0147,  0.0108,  0.0114],
+            [-0.0018,  0.0363, -0.0248,  ..., -0.0332,  0.0185,  0.0011]],
            grad_fn=<SliceBackward0>) 
 
-    Layer: linear_relu_stack.2.bias | Size: torch.Size([512]) | Values : tensor([ 0.0024, -0.0164], grad_fn=<SliceBackward0>) 
+    Layer: linear_relu_stack.2.bias | Size: torch.Size([512]) | Values : tensor([0.0409, 0.0064], grad_fn=<SliceBackward0>) 
 
-    Layer: linear_relu_stack.4.weight | Size: torch.Size([10, 512]) | Values : tensor([[ 0.0046,  0.0249,  0.0123,  ...,  0.0352, -0.0170,  0.0232],
-            [ 0.0038,  0.0283,  0.0235,  ..., -0.0416,  0.0304,  0.0217]],
+    Layer: linear_relu_stack.4.weight | Size: torch.Size([10, 512]) | Values : tensor([[ 0.0349, -0.0004,  0.0420,  ..., -0.0023,  0.0277,  0.0173],
+            [ 0.0015, -0.0185,  0.0072,  ..., -0.0159, -0.0068,  0.0271]],
            grad_fn=<SliceBackward0>) 
 
-    Layer: linear_relu_stack.4.bias | Size: torch.Size([10]) | Values : tensor([0.0118, 0.0417], grad_fn=<SliceBackward0>) 
+    Layer: linear_relu_stack.4.bias | Size: torch.Size([10]) | Values : tensor([-0.0129,  0.0260], grad_fn=<SliceBackward0>) 
 
 
 

diff --git a/docs/07-Autograd.md b/docs/07-Autograd.md
@@ -1,8 +1,3 @@
-```python
-%matplotlib inline
-```
-
-
 [Learn the Basics](intro.html) ||
 [Quickstart](quickstart_tutorial.html) ||
 [Tensors](tensorqs_tutorial.html) ||
@@ -31,6 +26,8 @@ PyTorch in the following manner:
 
 
 ```python
+%matplotlib inline
+
 import torch
 
 x = torch.ones(5)  # input tensor
@@ -77,8 +74,8 @@ print(f"Gradient function for z = {z.grad_fn}")
 print(f"Gradient function for loss = {loss.grad_fn}")
 ```
 
-    Gradient function for z = <AddBackward0 object at 0x10fa1ee80>
-    Gradient function for loss = <BinaryCrossEntropyWithLogitsBackward0 object at 0x10fa1e430>
+    Gradient function for z = <AddBackward0 object at 0x10427e550>
+    Gradient function for loss = <BinaryCrossEntropyWithLogitsBackward0 object at 0x10427e670>
 
 
 ## Computing Gradients
@@ -101,12 +98,12 @@ print(w.grad)
 print(b.grad)
 ```
 
-    tensor([[0.3244, 0.2353, 0.0700],
-            [0.3244, 0.2353, 0.0700],
-            [0.3244, 0.2353, 0.0700],
-            [0.3244, 0.2353, 0.0700],
-            [0.3244, 0.2353, 0.0700]])
-    tensor([0.3244, 0.2353, 0.0700])
+    tensor([[0.1692, 0.2790, 0.2088],
+            [0.1692, 0.2790, 0.2088],
+            [0.1692, 0.2790, 0.2088],
+            [0.1692, 0.2790, 0.2088],
+            [0.1692, 0.2790, 0.2088]])
+    tensor([0.1692, 0.2790, 0.2088])
 
 
 <div class="alert alert-info"><h4>Note</h4><p>- We can only obtain the ``grad`` properties for the leaf