Daniel Voigt Godoy - Deep Learning with PyTorch Step-by-Step A Beginner’s Guide-leanpub
41 optimizer.zero_grad() 34243 print(b, w)1 Defining an optimizer2 New "Step 4 - Updating Parameters" using the optimizer3 New "gradient zeroing" using the optimizerLet’s inspect our two parameters just to make sure everything is still working fine:Outputtensor([1.0235], device='cuda:0', requires_grad=True)tensor([1.9690], device='cuda:0', requires_grad=True)Cool! We’ve optimized the optimization process :-) What’s left?LossWe now tackle the loss computation. As expected, PyTorch has us covered onceagain. There are many loss functions to choose from, depending on the task athand. Since ours is a regression, we are using the mean squared error (MSE) as loss,and thus we need PyTorch’s nn.MSELoss():# Defines an MSE loss functionloss_fn = nn.MSELoss(reduction='mean')loss_fnOutputMSELoss()Notice that nn.MSELoss() is NOT the loss function itself: We do not passpredictions and labels to it! Instead, as you can see, it returns another function,which we called loss_fn: That is the actual loss function. So, we can pass aprediction and a label to it and get the corresponding loss value:Loss | 99
# This is a random example to illustrate the loss functionpredictions = torch.tensor(0.5, 1.0)labels = torch.tensor(2.0, 1.3)loss_fn(predictions, labels)Outputtensor(1.1700)Moreover, you can also specify a reduction method to be applied;that is, how do you want to aggregate the errors for individualpoints? You can average them (reduction=“mean”) or simply sumthem up (reduction=“sum”). In our example, we use the typicalmean reduction to compute MSE. If we had used sum as reduction,we would actually be computing SSE (sum of squared errors).Technically speaking, nn.MSELoss() is a higher-order function.If you’re not familiar with the concept, I will explain it briefly inChapter 2.We then use the created loss function in the code below, at line 29, to compute theloss, given our predictions and our labels:100 | Chapter 1: A Simple Regression Problem
- Page 74 and 75: true_b = 1true_w = 2N = 100# Data G
- Page 76 and 77: Let’s look at the cross-sections
- Page 78 and 79: Zero Mean and Unit Standard Deviati
- Page 80 and 81: Sure, in the real world, you’ll n
- Page 82 and 83: computing the loss, as shown in the
- Page 84 and 85: • visualizing the effects of usin
- Page 86 and 87: If you’re using Jupyter’s defau
- Page 88 and 89: Notebook Cell 1.1 - Splitting synth
- Page 90 and 91: Step 2# Step 2 - Computing the loss
- Page 92 and 93: Output[0.49671415] [-0.1382643][0.8
- Page 94 and 95: Notebook Cell 1.2 - Implementing gr
- Page 96 and 97: # Sanity Check: do we get the same
- Page 98 and 99: Outputtensor(3.1416)tensor([1, 2, 3
- Page 100 and 101: Outputtensor([[1., 2., 1.],[1., 1.,
- Page 102 and 103: dummy_array = np.array([1, 2, 3])du
- Page 104 and 105: n_cudas = torch.cuda.device_count()
- Page 106 and 107: back_to_numpy = x_train_tensor.nump
- Page 108 and 109: I am assuming you’d like to use y
- Page 110 and 111: Outputtensor([0.1940], device='cuda
- Page 112 and 113: print(error.requires_grad, yhat.req
- Page 114 and 115: Output(tensor([0.], device='cuda:0'
- Page 116 and 117: 56 # need to tell it to let it go..
- Page 118 and 119: computation.If you chose "Local Ins
- Page 120 and 121: Figure 1.6 - Now parameter "b" does
- Page 122 and 123: There are many optimizers: SGD is t
- Page 126 and 127: Notebook Cell 1.8 - PyTorch’s los
- Page 128 and 129: Outputarray(0.00804466, dtype=float
- Page 130 and 131: Let’s build a proper (yet simple)
- Page 132 and 133: "What do we need this for?"It turns
- Page 134 and 135: 1 Instantiating a model2 What IS th
- Page 136 and 137: In the __init__() method, we create
- Page 138 and 139: LayersA Linear model can be seen as
- Page 140 and 141: There are MANY different layers tha
- Page 142 and 143: We use magic, just like that:%run -
- Page 144 and 145: • Step 1: compute model’s predi
- Page 146 and 147: RecapFirst of all, congratulations
- Page 148 and 149: Chapter 2Rethinking the Training Lo
- Page 150 and 151: Let’s take a look at the code onc
- Page 152 and 153: Higher-Order FunctionsAlthough this
- Page 154 and 155: def exponentiation_builder(exponent
- Page 156 and 157: Apart from returning the loss value
- Page 158 and 159: Our code should look like this; see
- Page 160 and 161: There is no need to load the whole
- Page 162 and 163: but if we want to get serious about
- Page 164 and 165: How does this change our code so fa
- Page 166 and 167: Run - Model Training V2%run -i mode
- Page 168 and 169: piece of code that’s going to be
- Page 170 and 171: for it. We could do the same for th
- Page 172 and 173: EvaluationHow can we evaluate the m
# This is a random example to illustrate the loss function
predictions = torch.tensor(0.5, 1.0)
labels = torch.tensor(2.0, 1.3)
loss_fn(predictions, labels)
Output
tensor(1.1700)
Moreover, you can also specify a reduction method to be applied;
that is, how do you want to aggregate the errors for individual
points? You can average them (reduction=“mean”) or simply sum
them up (reduction=“sum”). In our example, we use the typical
mean reduction to compute MSE. If we had used sum as reduction,
we would actually be computing SSE (sum of squared errors).
Technically speaking, nn.MSELoss() is a higher-order function.
If you’re not familiar with the concept, I will explain it briefly in
Chapter 2.
We then use the created loss function in the code below, at line 29, to compute the
loss, given our predictions and our labels:
100 | Chapter 1: A Simple Regression Problem