Created
March 11, 2022 09:49
-
-
Save sonsongithub/a21980f5bdbd6d6e98f77a2c3bda5084 to your computer and use it in GitHub Desktop.
VAEを作ったときのサイズを合わせるためのツールスクリプト
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import numpy as np | |
class Sequential: | |
def __init__(self, channel=0, height=0, width=0, layers=[], source=True): | |
print('--------------------------------') | |
if source: | |
for layer in layers: | |
(channel, height, width) = layer.source(channel, height, width) | |
else: | |
for layer in layers: | |
(channel, height, width) = layer.size(channel, height, width) | |
print((channel, height, width)) | |
class Conv2d: | |
def __init__(self, channel_input, channel_output, stride, kernel, padding, dialation=(1,1)): | |
self.channel_input = channel_input | |
self.channel_output = channel_output | |
self.stride = stride | |
self.kernel = kernel | |
self.padding = padding | |
self.dialation = dialation | |
self.name = "Conv2d " | |
def through(self, height, width): | |
temp = (height + 2 * self.padding[0] - self.dialation[0] * (self.kernel[0] - 1) - 1) | |
height_output = int(temp / self.stride[0]) + 1 | |
temp = (width + 2 * self.padding[1] - self.dialation[1] * (self.kernel[1] - 1) - 1) | |
width_output = int(temp / self.stride[1]) + 1 | |
return (height_output, width_output) | |
def source(self, channel_input, height_input, width_input): | |
(height_output, width_output) = self.through(height_input, width_input) | |
value = (channel_input, self.channel_output, self.padding[0], self.padding[1], self.kernel[0], self.kernel[1], self.stride[0], self.stride[1]) | |
print("nn.Conv2d(%3d, %d, padding=(%d, %d), kernel_size=(%d, %d), stride=(%d, %d))," % value) | |
return (self.channel_output, height_output, width_output) | |
def size(self, channel_input, height_input, width_input): | |
(height_output, width_output) = self.through(height_input, width_input) | |
print("%s%3dx%3dx%3d -> %3dx%3dx%3d" % (self.name, channel_input, height_input, width_input, self.channel_output, height_output, width_output)) | |
return (self.channel_output, height_output, width_output) | |
class ConvTranspose2d: | |
def __init__(self, channel_input, channel_output, stride, kernel, padding, dialation=(1,1)): | |
self.channel_input = channel_input | |
self.channel_output = channel_output | |
self.stride = stride | |
self.kernel = kernel | |
self.padding = padding | |
self.dialation = dialation | |
self.name = "ConvTranspose2d " | |
def through(self, height, width): | |
height_output = (height - 1) * self.stride[0] - 2 * self.padding[0] + self.dialation[0] * (self.kernel[0] - 1) + self.padding[0] + 1 | |
width_output = (width - 1) * self.stride[1] - 2 * self.padding[1] + self.dialation[1] * (self.kernel[1] - 1) + self.padding[1] + 1 | |
return (height_output, width_output) | |
def source(self, channel_input, height_input, width_input): | |
(height_output, width_output) = self.through(height_input, width_input) | |
value = (channel_input, self.channel_output, self.padding[0], self.padding[1], self.kernel[0], self.kernel[1], self.stride[0], self.stride[1]) | |
print("nn.ConvTranspose2d(%3d, %3d, padding=(%d, %d), kernel_size=(%d, %d), stride=(%d, %d))," % value) | |
return (self.channel_output, height_output, width_output) | |
def size(self, channel_input, height_input, width_input): | |
(height_output, width_output) = self.through(height_input, width_input) | |
print("%s%3dx%3dx%3d -> %3dx%3dx%3d" % (self.name, channel_input, height_input, width_input, self.channel_output, height_output, width_output)) | |
return (self.channel_output, height_output, width_output) | |
class Upsample: | |
def __init__(self, scale): | |
self.scale = scale | |
self.name = "Upsample " | |
def through(self, channel, height, width): | |
channel_output = channel | |
height_output = height * self.scale | |
width_output = width * self.scale | |
return (channel_output, height_output, width_output) | |
def source(self, channel_input, height_input, width_input): | |
(channel_output, height_output, width_output) = self.through(channel_input, height_input, width_input) | |
print("nn.Upsample(scale_factor=%d, mode='bilinear', align_corners=True)," % self.scale) | |
return (channel_output, height_output, width_output) | |
def size(self, channel_input, height_input, width_input): | |
(channel_output, height_output, width_output) = self.through(channel_input, height_input, width_input) | |
print("%s%3dx%3dx%3d -> %3dx%3dx%3d" % (self.name, channel_input, height_input, width_input, channel_output, height_output, width_output)) | |
return (channel_output, height_output, width_output) | |
class ReLU: | |
def __init__(self): | |
self.name = "ReLU " | |
def through(self, height, width): | |
height_output = height | |
width_output = width | |
return (height_output, width_output) | |
def source(self, channel_input, height_input, width_input): | |
(height_output, width_output) = self.through(height_input, width_input) | |
print("nn.ReLU(),") | |
return (channel_input, height_output, width_output) | |
def size(self, channel_input, height_input, width_input): | |
(height_output, width_output) = self.through(height_input, width_input) | |
print("%s%3dx%3dx%3d -> %3dx%3dx%3d" % (self.name, channel_input, height_input, width_input, channel_input, height_output, width_output)) | |
return (channel_input, height_output, width_output) | |
for source_flag in [False, True]: | |
Sequential( | |
channel=3, | |
height=128, | |
width=128, | |
source=source_flag, | |
layers=[ | |
Conv2d( 3, 32, stride=(2, 2), kernel=(4, 4), padding=(1, 1)), ReLU(), | |
Conv2d( 32, 64, stride=(2, 2), kernel=(4, 4), padding=(1, 1)), ReLU(), | |
Conv2d( 64,128, stride=(2, 2), kernel=(4, 4), padding=(1, 1)), ReLU(), | |
Conv2d(128,128, stride=(2, 2), kernel=(4, 4), padding=(1, 1)), ReLU(), | |
Conv2d(128,128, stride=(2, 2), kernel=(4, 4), padding=(1, 1)), ReLU(), | |
Conv2d(128,128, stride=(2, 2), kernel=(4, 4), padding=(1, 1)), ReLU(), | |
] | |
) | |
Sequential( | |
channel=512, | |
height=1, | |
width=1, | |
source=source_flag, | |
layers=[ | |
ConvTranspose2d(512, 256, stride=(1, 1), kernel=(4, 4), padding=(0, 0)), ReLU(), | |
Upsample(2), ReLU(), | |
Conv2d(256,256, stride=(1, 1), kernel=(3, 3), padding=(1, 1)), ReLU(), | |
Upsample(2), ReLU(), | |
Conv2d(256,256, stride=(1, 1), kernel=(3, 3), padding=(1, 1)), ReLU(), | |
Upsample(2), ReLU(), | |
Conv2d(256,256, stride=(1, 1), kernel=(3, 3), padding=(1, 1)), ReLU(), | |
Upsample(2), ReLU(), | |
Conv2d(256,256, stride=(1, 1), kernel=(3, 3), padding=(1, 1)), ReLU(), | |
Upsample(2), ReLU(), | |
Conv2d(256,3, stride=(1, 1), kernel=(3, 3), padding=(1, 1)), ReLU(), | |
] | |
) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment