add rnn-lstm-gru tutorial

rnn-lstm-gru/README.md

@@ -0,0 +1,25 @@
+## PyTorch Tutorial - RNN & LSTM & GRU
+Implement a Recurrent Neural Net (RNN) in PyTorch! Learn how we can use the nn.RNN module and work with an input sequence. I also show you how easily we can switch to a gated recurrent unit (GRU) or long short-term memory (LSTM) RNN.
+
+## Watch the Tutorial
+  [![Alt text](https://img.youtube.com/vi/0_PgWWmauHk/hqdefault.jpg)](https://youtu.be/0_PgWWmauHk)
+
+## Resources
+Beginner PyTorch Course:  
+https://github.com/python-engineer/pytorchTutorial
+
+RNN:  
+https://pytorch.org/docs/stable/generated/torch.nn.RNN.html
+
+LSTM:  
+https://pytorch.org/docs/stable/generated/torch.nn.LSTM.html
+
+GRU:  
+https://pytorch.org/docs/stable/generated/torch.nn.GRU.html
+
+
+Further Readings:
+
+- https://karpathy.github.io/2015/05/21/rnn-effectiveness/
+- https://stanford.edu/~shervine/teaching/cs-230/cheatsheet-recurrent-neural-networks#architecture
+- https://pytorch.org/tutorials/intermediate/char_rnn_classification_tutorial.html

rnn-lstm-gru/main.py

@@ -0,0 +1,120 @@
+import torch
+import torch.nn as nn
+import torchvision
+import torchvision.transforms as transforms
+
+# Device configuration
+device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+
+# Hyper-parameters 
+# input_size = 784 # 28x28
+num_classes = 10
+num_epochs = 2
+batch_size = 100
+learning_rate = 0.001
+
+input_size = 28
+sequence_length = 28
+hidden_size = 128
+num_layers = 2
+
+# MNIST dataset 
+train_dataset = torchvision.datasets.MNIST(root='./data', 
+                                           train=True, 
+                                           transform=transforms.ToTensor(),  
+                                           download=True)
+
+test_dataset = torchvision.datasets.MNIST(root='./data', 
+                                          train=False, 
+                                          transform=transforms.ToTensor())
+
+# Data loader
+train_loader = torch.utils.data.DataLoader(dataset=train_dataset, 
+                                           batch_size=batch_size, 
+                                           shuffle=True)
+
+test_loader = torch.utils.data.DataLoader(dataset=test_dataset, 
+                                          batch_size=batch_size, 
+                                          shuffle=False)
+
+
+# Fully connected neural network with one hidden layer
+class RNN(nn.Module):
+    def __init__(self, input_size, hidden_size, num_layers, num_classes):
+        super(RNN, self).__init__()
+        self.num_layers = num_layers
+        self.hidden_size = hidden_size
+        self.rnn = nn.RNN(input_size, hidden_size, num_layers, batch_first=True)
+        # -> x needs to be: (batch_size, seq, input_size)
+
+        # or:
+        #self.gru = nn.GRU(input_size, hidden_size, num_layers, batch_first=True)
+        #self.lstm = nn.LSTM(input_size, hidden_size, num_layers, batch_first=True)
+        self.fc = nn.Linear(hidden_size, num_classes)
+
+    def forward(self, x):
+        # Set initial hidden states (and cell states for LSTM)
+        h0 = torch.zeros(self.num_layers, x.size(0), self.hidden_size).to(device) 
+        #c0 = torch.zeros(self.num_layers, x.size(0), self.hidden_size).to(device) 
+
+        # x: (n, 28, 28), h0: (2, n, 128)
+
+        # Forward propagate RNN
+        out, _ = self.rnn(x, h0)  
+        # or:
+        #out, _ = self.lstm(x, (h0,c0))  
+
+        # out: tensor of shape (batch_size, seq_length, hidden_size)
+        # out: (n, 28, 128)
+
+        # Decode the hidden state of the last time step
+        out = out[:, -1, :]
+        # out: (n, 128)
+
+        out = self.fc(out)
+        # out: (n, 10)
+        return out
+
+model = RNN(input_size, hidden_size, num_layers, num_classes).to(device)
+
+# Loss and optimizer
+criterion = nn.CrossEntropyLoss()
+optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)  
+
+# Train the model
+n_total_steps = len(train_loader)
+for epoch in range(num_epochs):
+    for i, (images, labels) in enumerate(train_loader):  
+        # origin shape: [N, 1, 28, 28]
+        # resized: [N, 28, 28]
+        images = images.reshape(-1, sequence_length, input_size).to(device)
+        labels = labels.to(device)
+
+        # Forward pass
+        outputs = model(images)
+        loss = criterion(outputs, labels)
+
+        # Backward and optimize
+        optimizer.zero_grad()
+        loss.backward()
+        optimizer.step()
+
+        if (i+1) % 100 == 0:
+            print (f'Epoch [{epoch+1}/{num_epochs}], Step [{i+1}/{n_total_steps}], Loss: {loss.item():.4f}')
+
+# Test the model
+# In test phase, we don't need to compute gradients (for memory efficiency)
+with torch.no_grad():
+    n_correct = 0
+    n_samples = 0
+    for images, labels in test_loader:
+        images = images.reshape(-1, sequence_length, input_size).to(device)
+        labels = labels.to(device)
+        outputs = model(images)
+        # max returns (value ,index)
+        _, predicted = torch.max(outputs.data, 1)
+        n_samples += labels.size(0)
+        n_correct += (predicted == labels).sum().item()
+
+    acc = 100.0 * n_correct / n_samples
+    print(f'Accuracy of the network on the 10000 test images: {acc} %')