I would like to apply grid search to Resnet18 model.Can anyone help me about it?
skorch is a scikit-learn compatible PyTorch wrapper and provides examples on how to perform Grid search.
Thank you for your response. I am wondering how can change this code for implementing Resnet 18 ?
def init(self, num_units=10, nonlin=F.relu):
self.dense0 = nn.Linear(20, num_units) self.nonlin = nonlin self.dropout = nn.Dropout(0.5) self.dense1 = nn.Linear(num_units, 10) self.output = nn.Linear(10, 2) def forward(self, X, **kwargs): X = self.nonlin(self.dense0(X)) X = self.dropout(X) X = F.relu(self.dense1(X)) X = F.softmax(self.output(X)) return X
You would have to change the entire model architecture and either implement the resnet from scratch or you could use other implementations for a resnet from e.g.