I'm using MONAI on Spyder Anaconda to build a U-Net network. I want to add/modify layers starting from this baseline.
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = nets.UNet( spatial_dims = 2, in_channels = 3, out_channels = 1, channels = (4, 8, 16, 32, 64), strides = (2, 2, 2, 2), num_res_units = 3, norm = layers.Norm.BATCH, kernel_size=3,).to(device)
loss_function = losses.DiceLoss()
torch.backends.cudnn.benchmark = True
optimizer = torch.optim.Adam(model.parameters(), lr = 1e-4, weight_decay = 0)
post_pred = Compose([EnsureType(), Activations(sigmoid = True), AsDiscrete(threshold=0.5)])
post_label = Compose([EnsureType()])
inferer = SimpleInferer()
utils.set_determinism(seed=46)My final aim is to create a MultiResUNet that has different layers such as:
class Conv2d_batchnorm(torch.nn.Module): ''' 2D Convolutional layers Arguments: num_in_filters {int} -- number of input filters num_out_filters {int} -- number of output filters kernel_size {tuple} -- size of the convolving kernel stride {tuple} -- stride of the convolution (default: {(1, 1)}) activation {str} -- activation function (default: {'relu'}) ''' def __init__(self, num_in_filters, num_out_filters, kernel_size, stride = (1,1), activation = 'relu'): super().__init__() self.activation = activation self.conv1 = torch.nn.Conv2d(in_channels=num_in_filters, out_channels=num_out_filters, kernel_size=kernel_size, stride=stride, padding = 'same') self.batchnorm = torch.nn.BatchNorm2d(num_out_filters) def forward(self,x): x = self.conv1(x) x = self.batchnorm(x) if self.activation == 'relu': return torch.nn.functional.relu(x) else: return xThis is just an example of a different Conv2d layer that I would use instead of the native one of the baseline.
Hope some of you can figure out how to proceed.
Thanks, Fede
Related questions 2 Kubernetes - PersistentVolumeClaim failed 21 GKE clusterrolebinding for cluster-admin fails with permission error 2 Using sysctls in Google Kubernetes Engine (GKE) Related questions 2 Kubernetes - PersistentVolumeClaim failed 21 GKE clusterrolebinding for cluster-admin fails with permission error 2 Using sysctls in Google Kubernetes Engine (GKE) 0 kubectl exec: Permission denied 5 kubelet Error while processing event /sys/fs/cgroup/memory/libcontainer_10010_systemd_test_default.slice 2 Error: Flag --allowed-unsafe-sysctls has been deprecated 3 Google Kubernetes Engine (GKE) cluster `error while creating mount source path` due to `read-only file system` 0 Can't deploy to GKE by a specific linux user 3 Is it possible to install the Sysbox container runtime on GKE? 0 kubectl - Error from server (Forbidden): users "[email protected]" is forbidden: User "system:serviceaccount:gke-connect:connect-agent-sa" Load 7 more related questions Show fewer related questions Reset to default
