博客

pytorch与keras的区别

模型输入：

#pytorch
            #批次, 通道, 高， 宽
a = torch.randn(1,4,160,160)


#keras
#形状和批次分开    
a = Input(shape = (160, 160, 4), batch_size = 1)

卷积：

#pytorch
self.conv = Conv2d(in_channels, out_channels, kernel_size, stride, padding=padding, bias=bias)

#keras
output = Conv2D(input.shape[-1] // reduction, kernel = (1,1), padding = "valid", use_bias = False)(output)

反卷积：

#pytorch
self.dconv = nn.ConvTranspose2d(in_channels, out_channels, kernel_size, stride, bias=bias)

#keras
output = Conv2DTranspose(out_channels, kernel_size, stride, use_bias=bias)(input)

上采样：

#pytorch
                                #缩放因子
self.up = nn.UpsamplingBilinear2d(scale_factor=2)

#keras
import tensorflow.compat.v1 as tf
#需要tf1版本里的resize
def my_upsampling(x,img_w,img_h,method=0):
    """0：双线性差值。1：最近邻居法。2：双三次插值法。3：面积插值法"""
    return tf.image.resize_images(x,(img_w,img_h),0)
                                       #输出宽高
output = Lambda(my_upsampling,arguments={'img_w':input.shape[2] * 2,'img_h':input.shape[1] * 2})(input)

池化：

BatchNormalization:

#pytorch
nn.BatchNorm2d(in_size),

#keras
output = BatchNormalization()(output)

激活：

#pytorch
self.act = nn.Sigmoid()
self.act = nn.ReLU


#keras
output = Activation("sigmoid")(output)
output = Activation("relu")(output)

不定期更新。。。