我的残差神经网络给出了一个非常奇怪的深度图作为输出。我不知道如何改进我的模型？

Question

我从残差模型得到的输出是一个上面有小方块的图像（一个分辨率很低的图像），但它应该给我一个深度图。图像中的对象丢失了，只有那些小方块可见。我不知道如何即兴创作？

def mini_model(input_shape) :

# Define the input as a tensor with shape input_shape
X_input = Input(input_shape)

# Zero_Padding
X = ZeroPadding2D((3,3))(X_input)
#stage_1
X = Conv2D(64,(7,7),strides = (2,2),name = 'conv1')(X)
X = BatchNormalization(axis = 3,name = 'bn_conv1')(X)
X = Activation('relu')(X)
X = MaxPooling2D((3,3),strides = (2,2))(X)
# Stage 2
X = convolutional_block(X, f = 3, filters = [64, 64, 256], stage = 2, block='a', s = 1)
X = identity_block(X, 3, [64, 64, 256], stage=2, block='b')
X = identity_block(X, 3, [64, 64, 256], stage=2, block='c')

#stage3
X = convolutional_block(X,f = 3 , filters = [128,128,512],stage = 3,block = 'a', s = 2)
X = identity_block(X,3,[128,128,512],stage = 3,block='b')
X = identity_block(X,3,[128,128,512],stage = 3 , block = 'c')
X = identity_block(X,3,[128,128,512],stage = 3 , block = 'd')

#stage 4
X = convolutional_block(X,f = 3 , filters = [256,256,1024],stage = 4,block = 'a', s = 2)
X = identity_block(X,3,[256,256,1024],stage = 4,block='b')
X = identity_block(X,3,[256,256,1024],stage = 4,block='c')
X = identity_block(X,3,[256,256,1024],stage = 4,block='d')
X = identity_block(X,3,[256,256,1024],stage = 4,block='e')
X = identity_block(X,3,[256,256,1024],stage = 4,block='f')
X = identity_block(X,3,[256,256,1024],stage = 4,block='g')
X = identity_block(X,3,[256,256,1024],stage = 4,block='h')
X = identity_block(X,3,[256,256,1024],stage = 4,block='i')
X = identity_block(X,3,[256,256,1024],stage = 4,block='j')
X = identity_block(X,3,[256,256,1024],stage = 4,block='k')
X = identity_block(X,3,[256,256,1024],stage = 4,block='l')

#stage 5
X = convolutional_block(X,f = 3 , filters = [512,512,2048],stage = 5,block = 'a', s = 2)
X = identity_block(X,3,[512,512,2048],stage = 5,block='b')
X = identity_block(X,3,[512,512,2048],stage = 5,block='c')

# AVGPOOL

    X = Conv2D(3,kernel_size=(3,3), padding = 'same',use_bias = False)(X)
    X = UpSampling2D(size=2)(X)
    X = UpSampling2D(size=2)(X)
    X = UpSampling2D(size=2)(X)
    X = UpSampling2D(size=2)(X)
X = UpSampling2D(size=2)(X)

# Create model
model = Model(inputs = X_input, outputs = X)
return(model)

我的残差模型！！输入图像形状 = (480,640,3)

实际效果：图像由小方块组成，具有不同的灰度等级。预期结果：图像应该是与输入相同大小的深度图 (480,640,3)

Answer 1

你有五个顺序的上采样层。这正是人们所期望的。 32 像素的大方块。 (2^5 = 32)

您可能应该阅读有关 U-net 的内容，在上采样和从 resnet 到上采样结果的连接之间创建更多卷积。

我的残差神经网络给出了一个非常奇怪的深度图作为输出。我不知道如何改进我的模型？

My residual neural network is giving a very strange depth map as output .I dont know how to improve my model?

keras

deep-learning

deep-residual-networks