Shortcuts

RNNBase

class torch.nn.RNNBase(mode, input_size, hidden_size, num_layers=1, bias=True, batch_first=False, dropout=0.0, bidirectional=False, proj_size=0)[source]
flatten_parameters()[source]

Resets parameter data pointer so that they can use faster code paths.

Right now, this works only if the module is on the GPU and cuDNN is enabled. Otherwise, it’s a no-op.

Docs

Access comprehensive developer documentation for PyTorch

View Docs

Tutorials

Get in-depth tutorials for beginners and advanced developers

View Tutorials

Resources

Find development resources and get your questions answered

View Resources