在TensorFlow上的RESNETV250模型之后，我的二进制分类模型的运行传输学习：值错误

Question

我正在尝试将转移学习（ResnETV250＆amp;效率网络B0）应用于我的二进制图像分类模型，但在拟合模型时遇到了值误差。

我添加了最后一层，其中包括以下参数 - ＆gt; layers.dense（num_classes，activation ='sigmoid'，name ='output_layer'）其中使用num_classes = 1，并使用lose ='binary_crossentropy编译模型/代码>。

我有以下错误：

valueerror：logits和标签必须具有相同的形状，接收到 （（无，2）vs（none，1））。

欢迎任何帮助/建议：

# Resnet 50 V2 feature vector
resnet_url = "https://tfhub.dev/google/imagenet/resnet_v2_50/feature_vector/4"

# Original: EfficientNetB0 feature vector (version 1)
efficientnet_url = "https://tfhub.dev/tensorflow/efficientnet/b0/feature-vector/1"
-----------------------------------------------------------------------------------------
def create_model(model_url, num_classes=1):

  # Download the pretrained model and save it as a Keras layer
  feature_extractor_layer = hub.KerasLayer(model_url,
                                           trainable=False, # freeze the underlying patterns
                                           name='feature_extraction_layer',
                                           input_shape=IMAGE_SHAPE+(3,)) # define the input image shape
  
  # Create our own model
  model = tf.keras.Sequential([
    feature_extractor_layer, # use the feature extraction layer as the base
    layers.Dense(num_classes, activation='sigmoid', name='output_layer') # create our own output layer      
  ])

  return model
-----------------------------------------------------------------------------------------------------
# Create model
resnet_model = create_model(resnet_url, num_classes=train_data.num_classes)

# Compile
resnet_model.compile(loss='binary_crossentropy',
                     optimizer=tf.keras.optimizers.Adam(),
                     metrics=['accuracy'])

------------------------------------------------------------------------------------------------------
# Fit the model
resnet_history = resnet_model.fit(train_data,
                                  epochs=5,
                                  steps_per_epoch=len(train_data),
                                  validation_data=val_data,
                                  validation_steps=len(val_data),
                                  # Add TensorBoard callback to model (callbacks parameter takes a list)
                                  callbacks=[create_tensorboard_callback(dir_name="tensorflow_hub", # save experiment logs here
                                                                         experiment_name="resnet50V2")]) # name of log files

我遇到的错误：

Saving TensorBoard log files to: tensorflow_hub/resnet50V2/20220418-221123
Epoch 1/5
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-24-196f7d30141c> in <module>()
      7                                   # Add TensorBoard callback to model (callbacks parameter takes a list)
      8                                   callbacks=[create_tensorboard_callback(dir_name="tensorflow_hub", # save experiment logs here
----> 9                                                                          experiment_name="resnet50V2")]) # name of log files

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 1932, in binary_crossentropy
        backend.binary_crossentropy(y_true, y_pred, from_logits=from_logits),
    File "/usr/local/lib/python3.7/dist-packages/keras/backend.py", line 5247, in binary_crossentropy
        return tf.nn.sigmoid_cross_entropy_with_logits(labels=target, logits=output)

    ValueError: `logits` and `labels` must have the same shape, received ((None, 2) vs (None, 1)).

Answer 1

对于二进制分类，您无需在每个类的密集层中使用单位，因为这是多余的。在这种情况下，您首先无法这样做，因为您使用binary_crossentropy损失。尝试调整layers.dense（num_classes） to layers.dense（1）。