What is the default batch size of pytorch SGD?

Question

What does pytorch SGD do if I feed the whole data and do not specify the batch size? I don't see any "stochastic" or "randomness" in the case. For example, in the following simple code, I feed the whole data (x,y) into a model.

optimizer = torch.optim.SGD(model.parameters(), lr=0.1)  
for epoch in range(5):
    y_pred = model(x_data)
    loss = criterion(y_pred, y_data)
    optimizer.zero_grad()
    loss.backward()
    optimizer.step()

Suppose there are 100 data pairs (x,y), i.e. x_data and y_data each has 100 elements.

Question: It seems to me that all the 100 gradients are calculated before one update of parameters. Size of a "mini_batch" is 100, not 1. So there is no randomness, am I right? At first, I think SGD means randomly choose 1 data point and calculate its gradient, which will be used as an approximation of the true gradient from all data.

Answer 1

The SGD optimizer in PyTorch is just gradient descent. The stocastic part comes from how you usually pass a random subset of your data through the network at a time (i.e. a mini-batch or batch). The code you posted passes the entire dataset through on each epoch before doing backprop and stepping the optimizer so you're really just doing regular gradient descent.