I am new to pytorch. I am looking to create a model fully connected, 512 hidden layer neurons and dropout rate of 10% with ReLU nonlinearity.
This is the model I created :
torch.nn.Sequential(
torch.nn.Linear(512,4),
torch.nn.ReLU(),
torch.nn.Dropout(0.10),
)
Not sure if this correct.
Keras equivalent :
Sequential([
Dense(512, input_dim=64),
Activation(‘relu’),
Dropout(0.1),
Dense(4)
])
Any help on how to approach this would be appreciated.