def test():
x = torch.randn(4, 3, 256, 256)
tests = {
"unet_vgg11": unet_vgg11(),
"unet_vgg11_bn": unet_vgg11_bn(),
"unet_vgg13": unet_vgg13(),
"unet_vgg13_bn": unet_vgg13_bn(),
"unet_vgg16": unet_vgg16(),
"unet_vgg16_bn": unet_vgg16_bn(),
"unet_vgg19": unet_vgg19(),
"unet_vgg19_bn": unet_vgg19_bn(),
"unet_mobilenetv2": unet_mobilenetv2(),
"unet_resnet18": unet_resnet18(),
"unet_resnet34": unet_resnet34(),
"unet_resnet50": unet_resnet50(),
"unet_resnet101": unet_resnet101(),
"unet_resnet152": unet_resnet152(),
}
for key, value in tests.items():
model = tests[key]
y = model(x)
print("Model name: ", model.name)
print("Trainable parameters: ", get_num_parameters(model))
print("in shape: ", x.shape, ", out shape: ", y.shape)
# test()
def test():
x = torch.randn(4, 3, 224, 224)
model = mobilenet_v3_small()
y = model(x)
print("Trainable parameters: ", get_num_parameters(model))
print("in shape: ", x.shape, ", out shape: ", y.shape)
def test():
x = torch.randn(1, 3, 224, 224)
model = SqueezeNet()
y = model(x)
print("Trainable parameters: ", get_num_parameters(model))
print("in shape: ", x.shape, ", out shape: ", y.shape)
def test():
x = torch.randn(1, 3, 224, 224)
model = shufflenet_v2_x0_5()
y = model(x)
print("Trainable parameters: ", get_num_parameters(model))
print("in shape: ", x.shape, ", out shape: ", y.shape)
def test():
x = torch.randn(1, 3, 224, 224)
model = alexnet(n_classes=3)
y = model(x)
print("Trainable parameters: ", get_num_parameters(model))
print("in shape: ", x.shape, ", out shape: ", y.shape)
# test()
def test(convnet="resnet18"):
x = torch.randn(1, 3, 224, 224)
tests = {
"resnet18": resnet18(),
"resnet34": resnet34(),
"resnet50": resnet50(),
"resnet101": resnet101(),
"resnet152": resnet152()
}
model = tests[convnet]
y = model(x)
print("Trainable parameters: ", get_num_parameters(model, True))
print("in shape: ", x.shape, ", out shape: ", y.shape)
def test(convnet="vgg11"):
x = torch.randn(1, 3, 224, 224)
tests = {
"vgg11": vgg11(),
"vgg11_bn": vgg11_bn(),
"vgg13": vgg13(),
"vgg13_bn": vgg13_bn(),
"vgg16": vgg16(),
"vgg16_bn": vgg16_bn(),
"vgg19": vgg19(),
"vgg19_bn": vgg19_bn()
}
model = tests[convnet]
y = model(x)
print("Trainable parameters: ", get_num_parameters(model))
print("in shape: ", x.shape, ", out shape: ", y.shape)
def test():
x = torch.randn(4, 3, 256, 256)
tests = {
"deeplabv3_mobilenetv2": deeplabv3_mobilenetv2(),
"deeplabv3_resnet18": deeplabv3_resnet18(),
"deeplabv3_resnet34": deeplabv3_resnet34(),
"deeplabv3_resnet50": deeplabv3_resnet50(),
"deeplabv3_resnet101": deeplabv3_resnet101(),
"deeplabv3_resnet152": deeplabv3_resnet152(),
}
for key, value in tests.items():
model = tests[key]
y = model(x)
print("Model name: ", model.name)
print("Trainable parameters: ", get_num_parameters(model))
print("in shape: ", x.shape, ", out shape: ", y.shape)
# test()
