Sequential(
(0): Input(BDHW->BDHW torch.float32 (0, 1) cuda:0 [None, 1, None, None])
(1): KeepSize(
(sub): Sequential(
(0): Conv2d(1, 50, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): BatchNorm2d(50, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU()
(3): Conv2d(50, 50, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(4): BatchNorm2d(50, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(5): ReLU()
(6): Conv2d(50, 50, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(7): BatchNorm2d(50, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(8): ReLU()
(9): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(10): Conv2d(50, 100, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(11): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(12): ReLU()
(13): Conv2d(100, 100, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(14): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(15): ReLU()
(16): Conv2d(100, 100, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(17): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(18): ReLU()
(19): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(20): Conv2d(100, 200, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(21): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(22): ReLU()
(23): Conv2d(200, 200, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(24): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(25): ReLU()
(26): Conv2d(200, 200, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(27): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(28): ReLU()
(29): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
)
)
(2): Conv2d(200, 400, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
(3): BatchNorm2d(400, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(4): ReLU()
(5): Conv2d(400, 3, kernel_size=(3, 3), stride=(1, 1))
)