defdraw_graph(model:nn.Module,input_data:INPUT_DATA_TYPE|None=None,input_size:INPUT_SIZE_TYPE|None=None,graph_name:str='model',depth:int|float=3,device:torch.device|str|None=None,dtypes:list[torch.dtype]|None=N
[batch, seconds*32000] sampling rate is 32k model.train() model_graph = draw_graph( model, input_size=( 4, 32000 * 10 ), # # Graph left-to-right: https://github.com/mert-kurttutan/torchview/issues/56 graph_dir="LR", depth=3, roll=True, expand_nested=True, # save_graph=True...
Just merged the code that introduced feature (see PR#60), with parameters,graph_dirwith options'TB', 'LR', 'BT', 'RL'as specified in doc string of the functiondraw_graph Example output can be seen in the tests/test_output directory This is a typical ensemble model:...