ssrjkk PyTorch
Machine learning framework with dynamic computation graphs.
Quick Start
import torch, torch.nn as nn
model = nn.Sequential(nn.Linear(784, 256), nn.ReLU(), nn.Linear(256, 10), nn.LogSoftmax(dim=1))
optimizer = torch.optim.Adam(model.parameters(), lr=0.001)
for images, labels in dataloader:
output = model(images); loss = nn.CrossEntropyLoss()(output, labels)
loss.backward(); optimizer.step(); optimizer.zero_grad()
Custom Module
class MyCNN(nn.Module):
def __init__(self):
super().__init__()
self.conv1 = nn.Conv2d(1, 32, 3); self.dropout = nn.Dropout2d(0.25)
self.fc1 = nn.Linear(5408, 128)
def forward(self, x):
x = self.conv1(x); x = self.dropout(x); return self.fc1(x)
When to Use
- Deep learning research
- Custom neural architectures
- NLP and computer vision
- GPU-accelerated training
Validation
- Model runs forward pass without error
- Loss decreases during training
- GPU utilization is correct