ValueError：logits 和标签必须具有相同的形状 ((None, 124, 124, 3) vs (None, 2))

Question

I am developing a image classification model. I have my input shape of image as (128,128,3) but when I am running the model.fit it is giving an error. My input data is

real_data = [f for f in os.listdir(data_dir+'/test') if f.endswith('.png')]
fake_data = [f for f in os.listdir(data_dir+'/test_f') if f.endswith('.png')]
print(real_data)
X = []
Y = []

for img in real_data:
    X.append(img_to_array(load_img(data_dir+'/test/'+img)) / 255.0)
    Y.append(1)
for img in fake_data:
    X.append(img_to_array(load_img(data_dir+'/test_f/'+img)) / 255.0)
    Y.append(0)

Y_val_org = Y
X = np.array(X)
Y = to_categorical(Y, 2)
print(X)
print(Y)

My model is

model = Sequential()
model.add(Conv2D(16, kernel_size=(3,3), activation='relu',input_shape=(128,128,3)))
model.add(Conv2D(16, kernel_size=(3,3), activation='relu'))
model.add(Dense(units=3, activation='softmax'))
model.compile(loss='binary_crossentropy',
              optimizer=optimizers.Adam(lr=1e-5, beta_1=0.9, beta_2=0.999, epsilon=None, decay=0.0, amsgrad=False),
              metrics=['accuracy'])
#model.build(input_shape=(128,128,3))
model.summary()

And model summary is

   Model: "sequential_80"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv2d_892 (Conv2D)          (None, 126, 126, 16)      448       
_________________________________________________________________
conv2d_893 (Conv2D)          (None, 124, 124, 16)      2320      
_________________________________________________________________
dense_48 (Dense)             (None, 124, 124, 3)       51        
=================================================================
Total params: 2,819
Trainable params: 2,819
Non-trainable params: 0
_________________________________________________________________

When I am fitting the model through model.fit()

early_stopping = EarlyStopping(monitor='val_loss', min_delta=0, patience=2, mode='auto')
EPOCHS = 20
BATCH_SIZE = 100
history = model.fit(X_train, Y_train, batch_size = BATCH_SIZE, epochs = EPOCHS, validation_data = (X_val, Y_val))

This is the error I am getting

Epoch 1/20
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-168-b3e2ed37ed88> in <module>()
      2 EPOCHS = 20
      3 BATCH_SIZE = 100
----> 4 history = model.fit(X_train, Y_train, batch_size = BATCH_SIZE, epochs = EPOCHS, validation_data = (X_val, Y_val))

9 frames
/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/func_graph.py in wrapper(*args, **kwargs)
    975           except Exception as e:  # pylint:disable=broad-except
    976             if hasattr(e, "ag_error_metadata"):
--> 977               raise e.ag_error_metadata.to_exception(e)
    978             else:
    979               raise

ValueError: in user code:

    /usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/training.py:805 train_function  *
        return step_function(self, iterator)
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/training.py:795 step_function  **
        outputs = model.distribute_strategy.run(run_step, args=(data,))
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/distribute/distribute_lib.py:1259 run
        return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/distribute/distribute_lib.py:2730 call_for_each_replica
        return self._call_for_each_replica(fn, args, kwargs)
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/distribute/distribute_lib.py:3417 _call_for_each_replica
        return fn(*args, **kwargs)
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/training.py:788 run_step  **
        outputs = model.train_step(data)
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/training.py:756 train_step
        y, y_pred, sample_weight, regularization_losses=self.losses)
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/compile_utils.py:203 __call__
        loss_value = loss_obj(y_t, y_p, sample_weight=sw)
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/losses.py:152 __call__
        losses = call_fn(y_true, y_pred)
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/losses.py:256 call  **
        return ag_fn(y_true, y_pred, **self._fn_kwargs)
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/util/dispatch.py:201 wrapper
        return target(*args, **kwargs)
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/losses.py:1608 binary_crossentropy
        K.binary_crossentropy(y_true, y_pred, from_logits=from_logits), axis=-1)
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/util/dispatch.py:201 wrapper
        return target(*args, **kwargs)
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/backend.py:4979 binary_crossentropy
        return nn.sigmoid_cross_entropy_with_logits(labels=target, logits=output)
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/util/dispatch.py:201 wrapper
        return target(*args, **kwargs)
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/ops/nn_impl.py:174 sigmoid_cross_entropy_with_logits
        (logits.get_shape(), labels.get_shape()))

    ValueError: logits and labels must have the same shape ((None, 124, 124, 3) vs (None, 2))

Answer 1

Change your model into:

model.add(Conv2D(16, kernel_size=(3,3), activation='relu'))
model.add(Flatten()) # added flatten before dense
model.add(Dense(units=2, activation='softmax'))

Last output should be 2 units because you have 2 classes. Also change your loss to:

loss='categorical_crossentropy'

because you applied to_categorical() .