logits 和 labels 必須具有相同的第一維，得到 logits shape [327680,7] 和 labels shape [983040]

Question

我正在嘗試使用 U-Net 架構執行語義分割。 當我適合 model 時： history = model.fit(imgs_train, masks_train,
batch_size= 5, epochs = 5) 我不斷收到以下錯誤。 imgs_train.shape: (1500, 256, 256, 3) masks_train.shape: (1500, 256, 256, 3)

# Building Unet using encoder and decoder blocks
from keras.models import Model
from keras.layers import Input, Conv2D, MaxPooling2D,  concatenate, Conv2DTranspose, 

BatchNormalization, Dropout, Lambda
from keras.layers import Activation, MaxPool2D, Concatenate


def conv_block(input, num_filters=64):
  # first conv layer
  x = Conv2D(num_filters, kernel_size = (3,3), padding='same')(input)
  x = BatchNormalization()(x)
  x = Activation('relu')(x)

  # second conv layer
  x = Conv2D(num_filters, kernel_size= (3,3), padding='same')(x)
  x = BatchNormalization()(x)
  x = Activation('relu')(x)

  return x

def encoder_block(input, num_filters=64):
  # conv block
  x = conv_block(input,num_filters)
  # maxpooling 
  p = MaxPool2D(strides = (2,2))(x)
  p = Dropout(0.4)(p)
  return x,p

    def decoder_block(input, skip_features, num_filters=64):
    x = Conv2DTranspose(num_filters, (2,2), strides=2, padding='same')(input)
  x = Concatenate()([x, skip_features])
  x = conv_block(x, num_filters)
  return x


num_classes=7
def unet_architect(input_shape=(256,256,3)):

  """ Input Layer """
  inputs = Input(input_shape)

  """ Encoder """
  s1,p1 = encoder_block(inputs, 64)
  s2,p2 = encoder_block(p1,128)
  s3,p3 = encoder_block(p2, 256)
  s4,p4 = encoder_block(p3, 512)



""" Bridge """
  b1 = conv_block(p4,1024)

  """ Decoder """ 
  d1 = decoder_block(b1, s4, 512)
  d2 = decoder_block(d1, s3, 256)
  d3 = decoder_block(d2, s2, 128)
  d4 = decoder_block(d3, s1, 64)

  """ Output Layer """
  outputs = Conv2D(num_classes, (1,1), padding='same', activation = 'softmax')(d4)

  model = Model(inputs, outputs, name='U-Net')

return model
model = unet_architect()
model.compile(optimizer = 'adam' , 
              loss = 'sparse_categorical_crossentropy',
              metrics=['accuracy'])

我試圖將 sparse_categorical_crossentropy 更改為 categorical_cross_entropy，出現另一個錯誤。

當我在擬合 model 時更改批量大小時，logits.shape 和 labels.shape 會相應更改。

錯誤

Epoch 1/5
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-35-4c0704d8f65d> in <module>()
      2                     masks_train,
      3                     batch_size= 10,
----> 4                     epochs = 5)

1 frames
/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/func_graph.py in autograph_handler(*args, **kwargs)
   1145           except Exception as e:  # pylint:disable=broad-except
   1146             if hasattr(e, "ag_error_metadata"):
-> 1147               raise e.ag_error_metadata.to_exception(e)
   1148             else:
   1149               raise

ValueError: in user code:

    File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 1021, in train_function  *
        return step_function(self, iterator)
    File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 1010, in step_function  **
        outputs = model.distribute_strategy.run(run_step, args=(data,))
    File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 1000, in run_step  **
        outputs = model.train_step(data)
    File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 860, in train_step
        loss = self.compute_loss(x, y, y_pred, sample_weight)
    File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 919, in compute_loss
        y, y_pred, sample_weight, regularization_losses=self.losses)
    File "/usr/local/lib/python3.7/dist-packages/keras/engine/compile_utils.py", line 201, in __call__
        loss_value = loss_obj(y_t, y_p, sample_weight=sw)
    File "/usr/local/lib/python3.7/dist-packages/keras/losses.py", line 141, in __call__
        losses = call_fn(y_true, y_pred)
File "/usr/local/lib/python3.7/dist-packages/keras/losses.py", line 245, in call  **
        return ag_fn(y_true, y_pred, **self._fn_kwargs)
    File "/usr/local/lib/python3.7/dist-packages/keras/losses.py", line 1863, in sparse_categorical_crossentropy
        y_true, y_pred, from_logits=from_logits, axis=axis)
    File "/usr/local/lib/python3.7/dist-packages/keras/backend.py", line 5203, in sparse_categorical_crossentropy
        labels=target, logits=output)

    ValueError: `labels.shape` must equal `logits.shape` except for the last dimension. Received: labels.shape=(1966080,) and logits.shape=(655360, 7)

筆記本鏈接： https://github.com/Tamimi123600/Deep-Learning/blob/main/Image_Segmentation1.ipynb

提前致謝

Answer 1

為什么您的蒙版圖像（GT 目標）的形狀是1500, 256, 256, 3而不是1500, 256, 256 ？ 你有num_classes=7所以你的 GT 圖像應該有一個通道，其值{0...6}代表每個像素的 class。

請檢查您如何加載和處理目標圖像——問題就在那里。