我正在尝试使用tensorflow和tflearn或Keras执行多类语义分割(我尝试了两个API(。与这里类似的问题(如何在 Keras 中加载图像掩码(标签(以进行图像分割(
我必须用 3 个不同的类别分割图像的不同部分：海(0 级(、船(1 级(、天空(2 级(。
我有 100 张灰度图像(尺寸 400x400(。对于每个图像，我都有 3 个类的相应标签。最后，我有形状(100,400,400(的图像和形状(100,400,400,3(的标签。(如这里解释的：如何实现多类语义分割？
为了能够使用语义分割，我使用了一种热编码(如这里：https://www.jeremyjordan.me/semantic-segmentation/(，最终得到这个：
train_images.shape: (100,400,400,1)
train_labels.shape: (100,400,400,3)
其中标签如下：海 [1,0,0];船 [0,1,0]，天空 [0,0,1]
但是，每次我尝试训练时都会收到此错误：
ValueError: Cannot feed value of shape (22, 240, 240, 3) for Tensor 'TargetsData/Y:0', which has shape '(?, 240, 240, 2)'
我用这个加载模型：
model = TheNet(input_shape=(None, 400, 40, 1))
编辑：这是我使用的模型
使用 TFlearn：
def TheNet(input_size = (80, 400, 400, 2), feature_map=8, kernel_size=5, keep_rate=0.8, lr=0.001, log_dir ="logs",savedir="Results/Session_Dump"): # level 0 input layer_0a_input = tflearn.layers.core.input_data(input_size) #shape=[None,n1,n2,n3,1]) # level 1 down layer_1a_conv = tflearn_conv_2d(net=layer_0a_input, nb_filter=feature_map, kernel=5, stride=1, activation=False) layer_1a_stack = tflearn_merge_2d([layer_0a_input]*feature_map, "concat") layer_1a_stack = tflearn.activations.prelu(layer_1a_stack) layer_1a_add = tflearn_merge_2d([layer_1a_conv,layer_1a_stack], "elemwise_sum") layer_1a_down = tflearn_conv_2d(net=layer_1a_add, nb_filter=feature_map*2, kernel=2, stride=2, dropout=keep_rate) # level 2 down layer_2a_conv = tflearn_conv_2d(net=layer_1a_down, nb_filter=feature_map*2, kernel=kernel_size, stride=1, dropout=keep_rate) layer_2a_conv = tflearn_conv_2d(net=layer_2a_conv, nb_filter=feature_map*2, kernel=kernel_size, stride=1, dropout=keep_rate) layer_2a_add = tflearn_merge_2d([layer_1a_down,layer_2a_conv], "elemwise_sum") layer_2a_down = tflearn_conv_2d(net=layer_2a_add, nb_filter=feature_map*4, kernel=2, stride=2, dropout=keep_rate) # level 3 down layer_3a_conv = tflearn_conv_2d(net=layer_2a_down, nb_filter=feature_map*4, kernel=kernel_size, stride=1, dropout=keep_rate) layer_3a_conv = tflearn_conv_2d(net=layer_3a_conv, nb_filter=feature_map*4, kernel=kernel_size, stride=1, dropout=keep_rate) layer_3a_conv = tflearn_conv_2d(net=layer_3a_conv, nb_filter=feature_map*4, kernel=kernel_size, stride=1, dropout=keep_rate) layer_3a_add = tflearn_merge_2d([layer_2a_down,layer_3a_conv], "elemwise_sum") layer_3a_down = tflearn_conv_2d(net=layer_3a_add, nb_filter=feature_map*8, kernel=2, stride=2, dropout=keep_rate) # level 4 down layer_4a_conv = tflearn_conv_2d(net=layer_3a_down, nb_filter=feature_map*8, kernel=kernel_size, stride=1, dropout=keep_rate) layer_4a_conv = tflearn_conv_2d(net=layer_4a_conv, nb_filter=feature_map*8, kernel=kernel_size, stride=1, dropout=keep_rate) layer_4a_conv = tflearn_conv_2d(net=layer_4a_conv, nb_filter=feature_map*8, kernel=kernel_size, stride=1, dropout=keep_rate) layer_4a_add = tflearn_merge_2d([layer_3a_down,layer_4a_conv], "elemwise_sum") layer_4a_down = tflearn_conv_2d(net=layer_4a_add, nb_filter=feature_map*16,kernel=2,stride=2,dropout=keep_rate) # level 5 layer_5a_conv = tflearn_conv_2d(net=layer_4a_down, nb_filter=feature_map*16, kernel=kernel_size, stride=1, dropout=keep_rate) layer_5a_conv = tflearn_conv_2d(net=layer_5a_conv, nb_filter=feature_map*16, kernel=kernel_size, stride=1, dropout=keep_rate) layer_5a_conv = tflearn_conv_2d(net=layer_5a_conv, nb_filter=feature_map*16, kernel=kernel_size, stride=1, dropout=keep_rate) layer_5a_add = tflearn_merge_2d([layer_4a_down,layer_5a_conv], "elemwise_sum") layer_5a_up = tflearn_deconv_2d(net=layer_5a_add, nb_filter=feature_map*8, kernel=2, stride=2, dropout=keep_rate) # level 4 up layer_4b_concat = tflearn_merge_2d([layer_4a_add,layer_5a_up], "concat") layer_4b_conv = tflearn_conv_2d(net=layer_4b_concat, nb_filter=feature_map*16, kernel=kernel_size, stride=1, dropout=keep_rate) layer_4b_conv = tflearn_conv_2d(net=layer_4b_conv, nb_filter=feature_map*16, kernel=kernel_size, stride=1, dropout=keep_rate) layer_4b_conv = tflearn_conv_2d(net=layer_4b_conv, nb_filter=feature_map*16, kernel=kernel_size, stride=1, dropout=keep_rate) layer_4b_add = tflearn_merge_2d([layer_4b_conv,layer_4b_concat], "elemwise_sum") layer_4b_up = tflearn_deconv_2d(net=layer_4b_add, nb_filter=feature_map*4, kernel=2, stride=2, dropout=keep_rate) # level 3 up layer_3b_concat = tflearn_merge_2d([layer_3a_add,layer_4b_up], "concat") layer_3b_conv = tflearn_conv_2d(net=layer_3b_concat, nb_filter=feature_map*8, kernel=kernel_size, stride=1, dropout=keep_rate) layer_3b_conv = tflearn_conv_2d(net=layer_3b_conv, nb_filter=feature_map*8, kernel=kernel_size, stride=1, dropout=keep_rate) layer_3b_conv = tflearn_conv_2d(net=layer_3b_conv, nb_filter=feature_map*8, kernel=kernel_size, stride=1, dropout=keep_rate) layer_3b_add = tflearn_merge_2d([layer_3b_conv,layer_3b_concat], "elemwise_sum") layer_3b_up = tflearn_deconv_2d(net=layer_3b_add, nb_filter=feature_map*2, kernel=2, stride=2, dropout=keep_rate) # level 2 up layer_2b_concat = tflearn_merge_2d([layer_2a_add,layer_3b_up], "concat") layer_2b_conv = tflearn_conv_2d(net=layer_2b_concat, nb_filter=feature_map*4, kernel=kernel_size, stride=1, dropout=keep_rate) layer_2b_conv = tflearn_conv_2d(net=layer_2b_conv, nb_filter=feature_map*4, kernel=kernel_size, stride=1, dropout=keep_rate) layer_2b_add = tflearn_merge_2d([layer_2b_conv,layer_2b_concat], "elemwise_sum") layer_2b_up = tflearn_deconv_2d(net=layer_2b_add, nb_filter=feature_map, kernel=2, stride=2, dropout=keep_rate) # level 1 up layer_1b_concat = tflearn_merge_2d([layer_1a_add,layer_2b_up], "concat") layer_1b_conv = tflearn_conv_2d(net=layer_1b_concat, nb_filter=feature_map*2, kernel=kernel_size, stride=1, dropout=keep_rate) layer_1b_add = tflearn_merge_2d([layer_1b_conv,layer_1b_concat], "elemwise_sum") # level 0 classifier layer_0b_conv = tflearn_conv_2d(net=layer_1b_add, nb_filter=2, kernel=5, stride=1, dropout=keep_rate) layer_0b_clf = tflearn.layers.conv.conv_2d(layer_0b_conv, 2, 1, 1, activation="softmax") # Optimizer regress = tflearn.layers.estimator.regression(layer_0b_clf, optimizer='adam', loss=dice_loss_2d, learning_rate=lr) # categorical_crossentropy/dice_loss_3d model = tflearn.models.dnn.DNN(regress, tensorboard_dir=log_dir) # Saving the model if not os.path.lexists(savedir+"weights"): os.makedirs(savedir+"weights") model.save(savedir+"weights/weights_session") return model使用Keras：
def TheNet(input_shape, nb_kernel, kernel_size, dropout, lr, log_dir ="logs",savedir="Results/Session_Dump"): layer_0 = keras.Input(shape = input_shape) #LVL 1 Down layer_1_conv = Cust_2D_Conv(layer_0, nb_kernel, kernel_size, stride=1) layer_1_stak = keras.layers.concatenate([layer_0,layer_0,layer_0,layer_0,layer_0,layer_0,layer_0,layer_0]) layer_1_stak = keras.layers.PReLU()(layer_1_stak) layer_1_addd = keras.layers.Multiply()([layer_1_conv,layer_1_stak]) layer_1_down = Cust_2D_Conv(layer_1_addd, nb_kernel=nb_kernel*2, kernel_size=3, stride=2, dropout=0.2) #LVL 2 Down layer_2_conv = Cust_2D_Conv(layer_1_down, nb_kernel=nb_kernel*2, kernel_size=5, stride=1, dropout=0.2) layer_2_conv = Cust_2D_Conv(layer_2_conv, nb_kernel=nb_kernel*2, kernel_size=5, stride=1, dropout=0.2) layer_2_addd = keras.layers.Multiply()([layer_2_conv,layer_1_down]) layer_2_down = Cust_2D_Conv(layer_2_addd, nb_kernel=nb_kernel*4, kernel_size=3, stride=2, dropout=0.2) #LVL 3 Down layer_3_conv = Cust_2D_Conv(layer_2_down, nb_kernel=nb_kernel*4, kernel_size=5, stride=1, dropout=0.2) layer_3_conv = Cust_2D_Conv(layer_3_conv, nb_kernel=nb_kernel*4, kernel_size=5, stride=1, dropout=0.2) layer_3_conv = Cust_2D_Conv(layer_3_conv, nb_kernel=nb_kernel*4, kernel_size=5, stride=1, dropout=0.2) layer_3_addd = keras.layers.Multiply()([layer_3_conv,layer_2_down]) layer_3_down = Cust_2D_Conv(layer_3_addd, nb_kernel=nb_kernel*8, kernel_size=3, stride=2, dropout=0.2) #LVL 4 Down layer_4_conv = Cust_2D_Conv(layer_3_down, nb_kernel=nb_kernel*8, kernel_size=5, stride=1, dropout=0.2) layer_4_conv = Cust_2D_Conv(layer_4_conv, nb_kernel=nb_kernel*8, kernel_size=5, stride=1, dropout=0.2) layer_4_conv = Cust_2D_Conv(layer_4_conv, nb_kernel=nb_kernel*8, kernel_size=5, stride=1, dropout=0.2) layer_4_addd = keras.layers.Multiply()([layer_4_conv,layer_3_down]) layer_4_down = Cust_2D_Conv(layer_4_addd, nb_kernel=nb_kernel*16, kernel_size=3, stride=2, dropout=0.2) #LVL 5 Down layer_5_conv = Cust_2D_Conv(layer_4_down, nb_kernel=nb_kernel*16, kernel_size=5, stride=1, dropout=0.2) layer_5_conv = Cust_2D_Conv(layer_5_conv, nb_kernel=nb_kernel*16, kernel_size=5, stride=1, dropout=0.2) layer_5_conv = Cust_2D_Conv(layer_5_conv, nb_kernel=nb_kernel*16, kernel_size=5, stride=1, dropout=0.2) layer_5_addd = keras.layers.Multiply()([layer_5_conv,layer_4_down]) layer_5_up = Cust_2D_DeConv(layer_5_addd, nb_kernel=nb_kernel*8, kernel_size=3, stride=2, dropout=0.2) #LVL 4 Up layer_4b_concat = keras.layers.concatenate([layer_5_up, layer_4_addd]) layer_4b_conv = Cust_2D_Conv(layer_4b_concat, nb_kernel=nb_kernel*16, kernel_size=5, stride=1, dropout=0.2) layer_4b_conv = Cust_2D_Conv(layer_4b_conv, nb_kernel=nb_kernel*16, kernel_size=5, stride=1, dropout=0.2) layer_4b_conv = Cust_2D_Conv(layer_4b_conv, nb_kernel=nb_kernel*16, kernel_size=5, stride=1, dropout=0.2) layer_4b_addd = keras.layers.Multiply()([layer_4b_conv,layer_4b_concat]) layer_4b_up = Cust_2D_DeConv(layer_4b_addd, nb_kernel=nb_kernel*4, kernel_size=3, stride=2, dropout=0.2) #LVL 3 Up layer_3b_concat = keras.layers.concatenate([layer_4b_up, layer_3_addd]) layer_3b_conv = Cust_2D_Conv(layer_3b_concat, nb_kernel=nb_kernel*8, kernel_size=5, stride=1, dropout=0.2) layer_3b_conv = Cust_2D_Conv(layer_3b_conv, nb_kernel=nb_kernel*8, kernel_size=5, stride=1, dropout=0.2) layer_3b_conv = Cust_2D_Conv(layer_3b_conv, nb_kernel=nb_kernel*8, kernel_size=5, stride=1, dropout=0.2) layer_3b_addd = keras.layers.Multiply()([layer_3b_conv,layer_3b_concat]) layer_3b_up = Cust_2D_DeConv(layer_3b_addd, nb_kernel=nb_kernel*2, kernel_size=3, stride=2, dropout=0.2) #LVL 2 Up layer_2b_concat = keras.layers.concatenate([layer_3b_up, layer_2_addd]) layer_2b_conv = Cust_2D_Conv(layer_2b_concat, nb_kernel=nb_kernel*4, kernel_size=5, stride=1, dropout=0.2) layer_2b_conv = Cust_2D_Conv(layer_2b_conv, nb_kernel=nb_kernel*4, kernel_size=5, stride=1, dropout=0.2) layer_2b_addd = keras.layers.Multiply()([layer_2b_conv,layer_2b_concat]) layer_2b_up = Cust_2D_DeConv(layer_2b_addd, nb_kernel=nb_kernel, kernel_size=3, stride=2, dropout=0.2) #LVL 1 Up layer_1b_concat = keras.layers.concatenate([layer_2b_up, layer_1_addd]) layer_1b_conv = Cust_2D_Conv(layer_1b_concat, nb_kernel=nb_kernel*2, kernel_size=5, stride=1, dropout=0.2) layer_1b_addd = keras.layers.Multiply()([layer_1b_conv,layer_1b_concat]) #LVL 0 layer_0b_conv = Cust_2D_Conv(layer_1b_addd, nb_kernel=2, kernel_size=5, stride=1, dropout=0.2) layer_0b_clf= keras.layers.Conv2D(2, 1, 1, activation="softmax")(layer_0b_conv) model = keras.Model(inputs=layer_0, outputs=layer_0b_clf, name='Keras_model') model.compile(loss=dice_loss_2d, optimizer=keras.optimizers.Adam(), metrics=['accuracy','categorical_accuracy']) return model
我一直在寻找解决方案，但没有什么是很清楚的。
有人有想法或建议吗？
可能面临同样问题的人，我找到了解决方案
问题不在于输入形状。对于输入图像和标签，输入形状必须分别为 (100， 400， 400， 1( 和 (100， 400， 400， 3(。
但是，问题在于模型和模型的输出形状必须与模型的输入相匹配。在原始帖子中显示的代码中，输出形状直接由以下行生成：
layer_0b_clf = tflearn.layers.conv.conv_2d(layer_0b_conv, 2, 1, 1, activation="softmax")
这将产生输出形状 (？，400,400,2(，因此与用于评估的标签形状不匹配(即 (100， 400， 400， 3(。解决方案是改变模型的输出通道数量，例如：
- 对于TFlearn：conv_2d(layer_0b_conv，3,1,1，激活="softmax"(
layer_0b_clf = tflearn.layers.conv.conv_2d(layer_0b_conv, 3, 1, 1, activation="softmax")
- 对于 Keras： Conv2D(3， 1， 1， activation="softmax"(
layer_0b_clf= keras.layers.Conv2D(3, 1, 1, activation="softmax")(layer_0b_conv)
希望它能帮助某人。
感谢您的评论和阅读。