Change activation function

[josel9393]

Hi, im new in Monai , im using UNET but I want to change the originial activation function from the default PRELU to Swish or Mish.

from monai.networks.layers.factories import Act
m = Act'swish'

Can someone explain me how to do this? Please

model=UNet(
spatial_dims=2,
in_channels=3,
out_channels=1,
channels=(4, 8, 16, 32, 64,128,256,512),
strides=(2, 2, 2, 2,2,2,2),
# act=("mish", {}),
).to(device)

Net(
(model): Sequential(
(0): Convolution(
(conv): Conv2d(3, 4, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
(adn): ADN(
(N): InstanceNorm2d(4, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
(D): Dropout(p=0.0, inplace=False)
(A): PReLU(num_parameters=1)
)
)
(1): SkipConnection(
(submodule): Sequential(
(0): Convolution(
(conv): Conv2d(4, 8, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
(adn): ADN(
(N): InstanceNorm2d(8, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
(D): Dropout(p=0.0, inplace=False)
(A): PReLU(num_parameters=1)
)
)
(1): SkipConnection(
(submodule): Sequential(
(0): Convolution(
(conv): Conv2d(8, 16, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
(adn): ADN(
(N): InstanceNorm2d(16, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
(D): Dropout(p=0.0, inplace=False)
(A): PReLU(num_parameters=1)
)
)
(1): SkipConnection(
(submodule): Sequential(
(0): Convolution(
(conv): Conv2d(16, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
(adn): ADN(
(N): InstanceNorm2d(32, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
(D): Dropout(p=0.0, inplace=False)
(A): PReLU(num_parameters=1)
)
)
(1): SkipConnection(
(submodule): Sequential(
(0): Convolution(
(conv): Conv2d(32, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
(adn): ADN(
(N): InstanceNorm2d(64, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
(D): Dropout(p=0.0, inplace=False)
(A): PReLU(num_parameters=1)
)
)
(1): SkipConnection(
(submodule): Sequential(
(0): Convolution(
(conv): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
(adn): ADN(
(N): InstanceNorm2d(128, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
(D): Dropout(p=0.0, inplace=False)
(A): PReLU(num_parameters=1)
)
)
(1): SkipConnection(
(submodule): Sequential(
(0): Convolution(
(conv): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
(adn): ADN(
(N): InstanceNorm2d(256, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
(D): Dropout(p=0.0, inplace=False)
(A): PReLU(num_parameters=1)
)
)
(1): SkipConnection(
(submodule): Convolution(
(conv): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(adn): ADN(
(N): InstanceNorm2d(512, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
(D): Dropout(p=0.0, inplace=False)
(A): PReLU(num_parameters=1)
)
)
)
(2): Convolution(
(conv): ConvTranspose2d(768, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), output_padding=(1, 1))
(adn): ADN(
(N): InstanceNorm2d(128, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
(D): Dropout(p=0.0, inplace=False)
(A): PReLU(num_parameters=1)
)
)
)
)
(2): Convolution(
(conv): ConvTranspose2d(256, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), output_padding=(1, 1))
(adn): ADN(
(N): InstanceNorm2d(64, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
(D): Dropout(p=0.0, inplace=False)
(A): PReLU(num_parameters=1)
)
)
)
)
(2): Convolution(
(conv): ConvTranspose2d(128, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), output_padding=(1, 1))
(adn): ADN(
(N): InstanceNorm2d(32, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
(D): Dropout(p=0.0, inplace=False)
(A): PReLU(num_parameters=1)
)
)
)
)
(2): Convolution(
(conv): ConvTranspose2d(64, 16, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), output_padding=(1, 1))
(adn): ADN(
(N): InstanceNorm2d(16, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
(D): Dropout(p=0.0, inplace=False)
(A): PReLU(num_parameters=1)
)
)
)
)
(2): Convolution(
(conv): ConvTranspose2d(32, 8, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), output_padding=(1, 1))
(adn): ADN(
(N): InstanceNorm2d(8, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
(D): Dropout(p=0.0, inplace=False)
(A): PReLU(num_parameters=1)
)
)
)
)
(2): Convolution(
(conv): ConvTranspose2d(16, 4, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), output_padding=(1, 1))
(adn): ADN(
(N): InstanceNorm2d(4, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
(D): Dropout(p=0.0, inplace=False)
(A): PReLU(num_parameters=1)
)
)
)
)
(2): Convolution(
(conv): ConvTranspose2d(8, 1, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), output_padding=(1, 1))
)
)
)

[josel9393]

model=UNet(
spatial_dims=2,
in_channels=3,
out_channels=1,
channels=(4, 8, 16, 32, 64,128,256,512),
strides=(2, 2, 2, 2,2,2,2),
act=monai.networks.layers.Act.MISH
).to(device)