Итак, я работаю с медицинскими изображениями, у которых каждый образец и наземная правда имеют форму 320,320,20, где 20 - это количество срезов. проблема в том, что y_true и y_pred не совпадают, если я изменю форму или выполню другую задачу. Любое предложение будет оценено.
Y_train = keras.utils.to_categorical(Y_train, num_classes=12, dtype=np.uint8)
inputs = tf.keras.layers.Input((320, 320,20))
smooth = 1.
s = tf.keras.layers.Lambda(lambda x: x / 255)(inputs)
c1 = tf.keras.layers.Conv2D(16, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(
s) # Kernelsize : start with some weights initial value
c1 = tf.keras.layers.Dropout(0.1)(c1)
c1 = tf.keras.layers.Conv2D(16, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(
c1) # Kernelsize : start with some weights initial value
p1 = tf.keras.layers.MaxPool2D((2, 2))(c1)
c2 = tf.keras.layers.Conv2D(32, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(
p1) # Kernelsize : start with some weights initial value
c2 = tf.keras.layers.Dropout(0.1)(c2)
c2 = tf.keras.layers.Conv2D(32, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(
c2) # Kernelsize : start with some weights initial value
p2 = tf.keras.layers.MaxPool2D((2, 2))(c2)
c3 = tf.keras.layers.Conv2D(64, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(
p2) # Kernelsize : start with some weights initial value
c3 = tf.keras.layers.Dropout(0.1)(c3)
c3 = tf.keras.layers.Conv2D(64, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(
c3) # Kernelsize : start with some weights initial value
p3 = tf.keras.layers.MaxPool2D((2, 2))(c3)
c4 = tf.keras.layers.Conv2D(128, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(
p3) # Kernelsize : start with some weights initial value
c4 = tf.keras.layers.Dropout(0.1)(c4)
c4 = tf.keras.layers.Conv2D(128, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(
c4) # Kernelsize : start with some weights initial value
p4 = tf.keras.layers.MaxPool2D((2, 2))(c4)
c5 = tf.keras.layers.Conv2D(256, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(
p4) # Kernelsize : start with some weights initial value
c5 = tf.keras.layers.Dropout(0.1)(c5)
c5 = tf.keras.layers.Conv2D(256, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(
c5) # Kernelsize : start wi
u6 = tf.keras.layers.Conv2DTranspose(128, (2, 2), strides=(2, 2), padding='same')(c5)
u6 = tf.keras.layers.concatenate([u6, c4])
c6 = tf.keras.layers.Conv2D(128, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(u6)
c6 = tf.keras.layers.Dropout(0.2)(c6)
c6 = tf.keras.layers.Conv2D(128, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(c6)
u7 = tf.keras.layers.Conv2DTranspose(64, (2, 2), strides=(2, 2), padding='same')(c6)
u7 = tf.keras.layers.concatenate([u7, c3])
c7 = tf.keras.layers.Conv2D(64, (2, 2), activation='relu', kernel_initializer='he_normal', padding='same')(u7)
c7 = tf.keras.layers.Dropout(0.2)(c7)
c7 = tf.keras.layers.Conv2D(64, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(c7)
u8 = tf.keras.layers.Conv2DTranspose(32, (2, 2), strides=(2, 2), padding='same')(c7)
u8 = tf.keras.layers.concatenate([u8, c2])
c8 = tf.keras.layers.Conv2D(32, (2, 2), activation='relu', kernel_initializer='he_normal', padding='same')(u8)
c8 = tf.keras.layers.Dropout(0.1)(c8)
c8 = tf.keras.layers.Conv2D(32, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(c8)
u9 = tf.keras.layers.Conv2DTranspose(16, (2, 2), strides=(2, 2), padding='same')(c8)
u9 = tf.keras.layers.concatenate([u9, c1], axis=3)
c9 = tf.keras.layers.Conv2D(16, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(u9)
c9 = tf.keras.layers.Dropout(0.1)(c9)
c9 = tf.keras.layers.Conv2D(16, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(c9)
outputs = tf.keras.layers.Conv2D(12, (1, 1), activation='softmax')(c9)
#op = tf.keras.layers.Reshape((82944,12))(outputs)
model = tf.keras.Model(inputs=[inputs], outputs=[outputs])
, когда я пытаюсь соответствовать модели, я получаю эту ошибку:
ValueError: Dimensions must be equal, but are 20 and 320 for 'loss/conv2d_18_loss/mul' (op: 'Mul') with input shapes: [1,320,320,20,12], [1,320,320,12].
Резюме
Модель: "модель"
________________________
Layer (type) Output Shape Param # Connected to
==================================================================================================
input_1 (InputLayer) [(None, 320, 320, 20 0
__________________________________________________________________________________________________
lambda (Lambda) (None, 320, 320, 20) 0 input_1[0][0]
__________________________________________________________________________________________________
conv2d (Conv2D) (None, 320, 320, 16) 2896 lambda[0][0]
__________________________________________________________________________________________________
dropout (Dropout) (None, 320, 320, 16) 0 conv2d[0][0]
__________________________________________________________________________________________________
conv2d_1 (Conv2D) (None, 320, 320, 16) 2320 dropout[0][0]
__________________________________________________________________________________________________
max_pooling2d (MaxPooling2D) (None, 160, 160, 16) 0 conv2d_1[0][0]
__________________________________________________________________________________________________
conv2d_2 (Conv2D) (None, 160, 160, 32) 4640 max_pooling2d[0][0]
__________________________________________________________________________________________________
dropout_1 (Dropout) (None, 160, 160, 32) 0 conv2d_2[0][0]
__________________________________________________________________________________________________
conv2d_3 (Conv2D) (None, 160, 160, 32) 9248 dropout_1[0][0]
__________________________________________________________________________________________________
max_pooling2d_1 (MaxPooling2D) (None, 80, 80, 32) 0 conv2d_3[0][0]
__________________________________________________________________________________________________
conv2d_4 (Conv2D) (None, 80, 80, 64) 18496 max_pooling2d_1[0][0]
__________________________________________________________________________________________________
dropout_2 (Dropout) (None, 80, 80, 64) 0 conv2d_4[0][0]
__________________________________________________________________________________________________
conv2d_5 (Conv2D) (None, 80, 80, 64) 36928 dropout_2[0][0]
__________________________________________________________________________________________________
max_pooling2d_2 (MaxPooling2D) (None, 40, 40, 64) 0 conv2d_5[0][0]
__________________________________________________________________________________________________
conv2d_6 (Conv2D) (None, 40, 40, 128) 73856 max_pooling2d_2[0][0]
__________________________________________________________________________________________________
dropout_3 (Dropout) (None, 40, 40, 128) 0 conv2d_6[0][0]
__________________________________________________________________________________________________
conv2d_7 (Conv2D) (None, 40, 40, 128) 147584 dropout_3[0][0]
__________________________________________________________________________________________________
max_pooling2d_3 (MaxPooling2D) (None, 20, 20, 128) 0 conv2d_7[0][0]
__________________________________________________________________________________________________
conv2d_8 (Conv2D) (None, 20, 20, 256) 295168 max_pooling2d_3[0][0]
__________________________________________________________________________________________________
dropout_4 (Dropout) (None, 20, 20, 256) 0 conv2d_8[0][0]
__________________________________________________________________________________________________
conv2d_9 (Conv2D) (None, 20, 20, 256) 590080 dropout_4[0][0]
__________________________________________________________________________________________________
conv2d_transpose (Conv2DTranspo (None, 40, 40, 128) 131200 conv2d_9[0][0]
__________________________________________________________________________________________________
concatenate (Concatenate) (None, 40, 40, 256) 0 conv2d_transpose[0][0]
conv2d_7[0][0]
__________________________________________________________________________________________________
conv2d_10 (Conv2D) (None, 40, 40, 128) 295040 concatenate[0][0]
__________________________________________________________________________________________________
dropout_5 (Dropout) (None, 40, 40, 128) 0 conv2d_10[0][0]
__________________________________________________________________________________________________
conv2d_11 (Conv2D) (None, 40, 40, 128) 147584 dropout_5[0][0]
__________________________________________________________________________________________________
conv2d_transpose_1 (Conv2DTrans (None, 80, 80, 64) 32832 conv2d_11[0][0]
__________________________________________________________________________________________________
concatenate_1 (Concatenate) (None, 80, 80, 128) 0 conv2d_transpose_1[0][0]
conv2d_5[0][0]
__________________________________________________________________________________________________
conv2d_12 (Conv2D) (None, 80, 80, 64) 32832 concatenate_1[0][0]
__________________________________________________________________________________________________
dropout_6 (Dropout) (None, 80, 80, 64) 0 conv2d_12[0][0]
__________________________________________________________________________________________________
conv2d_13 (Conv2D) (None, 80, 80, 64) 36928 dropout_6[0][0]
__________________________________________________________________________________________________
conv2d_transpose_2 (Conv2DTrans (None, 160, 160, 32) 8224 conv2d_13[0][0]
__________________________________________________________________________________________________
concatenate_2 (Concatenate) (None, 160, 160, 64) 0 conv2d_transpose_2[0][0]
conv2d_3[0][0]
__________________________________________________________________________________________________
conv2d_14 (Conv2D) (None, 160, 160, 32) 8224 concatenate_2[0][0]
__________________________________________________________________________________________________
dropout_7 (Dropout) (None, 160, 160, 32) 0 conv2d_14[0][0]
__________________________________________________________________________________________________
conv2d_15 (Conv2D) (None, 160, 160, 32) 9248 dropout_7[0][0]
__________________________________________________________________________________________________
conv2d_transpose_3 (Conv2DTrans (None, 320, 320, 16) 2064 conv2d_15[0][0]
__________________________________________________________________________________________________
concatenate_3 (Concatenate) (None, 320, 320, 32) 0 conv2d_transpose_3[0][0]
conv2d_1[0][0]
__________________________________________________________________________________________________
conv2d_16 (Conv2D) (None, 320, 320, 16) 4624 concatenate_3[0][0]
__________________________________________________________________________________________________
dropout_8 (Dropout) (None, 320, 320, 16) 0 conv2d_16[0][0]
__________________________________________________________________________________________________
conv2d_17 (Conv2D) (None, 320, 320, 16) 2320 dropout_8[0][0]
__________________________________________________________________________________________________
conv2d_18 (Conv2D) (None, 320, 320, 12) 204 conv2d_17[0][0]
==================================================================================================
Total params: 1,892,540
Trainable params: 1,892,540
Non-trainable params: 0
Так как я только тестирую, я добавил только 2 изображения для образца и 2 для GT:
X-train shape: (2, 320, 320, 20)
X-train max: 255
X-train min: 0
X-train average: 45.08897802734375
Y-train shape: (2, 320, 320, 20)
Y-train max: 11
Y-train min: 0
Y-train average: 0.84169189453125