警告：tensorflow：Model 是按形状构造的（无、66、200、3）

Question

I have the following code that is generating an error about a shape:

from keras.layers import Dense, Activation
from keras import Sequential
from keras.models import load_model
from tensorflow.keras.optimizers import Adam
import tensorflow 
import keras
from tensorflow.python.keras.layers import Input, Dense
from tensorflow.keras.optimizers import Adam
from keras.layers import Convolution2D, MaxPooling2D, Dropout, Flatten, Dense

def nvidia_model():
  model = Sequential()
  model.add(Convolution2D(24,(5,5), strides=(2, 2), input_shape=(66, 200, 3), activation='relu'))
  model.add(Convolution2D(36, (5,5), strides=(2, 2), activation='relu'))
  model.add(Convolution2D(48, (5,5), strides=(2, 2), activation='relu'))
  model.add(Convolution2D(64, (3,3), activation='relu'))
  model.add(Convolution2D(64, (3,3), activation='relu'))
  model.add(Flatten())
  model.add(Dense(100, activation = 'relu'))
  model.add(Dense(50, activation = 'relu'))
  model.add(Dense(10, activation = 'relu'))
  model.add(Dense(1))
  
  optimizer = Adam(learning_rate=1e-3)
  model.compile(loss='mse', optimizer=optimizer)
  return model

model = nvidia_model()
print(model.summary())

history = model.fit(X_train, y_train, epochs=30,validation_data=(X_valid,y_valid),batch_size=100,verbose=1,shuffle=1)

However while training the first epoch I get the error that I'm posting below:

Epoch 1/30
WARNING:tensorflow:Model was constructed with shape (None, 66, 200, 3) for input KerasTensor(type_spec=TensorSpec(shape=(None, 66, 200, 3), dtype=tf.float32, name='conv2d_5_input'), name='conv2d_5_input', description="created by layer 'conv2d_5_input'"), but it was called on an input with incompatible shape (None,).
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-42-e7614c3cfda1> in <module>()
----> 1 history = model.fit(X_train, y_train, epochs=30,validation_data=(X_valid,y_valid),batch_size=100,verbose=1,shuffle=1)

1 frames
/usr/local/lib/python3.7/dist-packages/keras/engine/training.py in tf__train_function(iterator)
     13                 try:
     14                     do_return = True
---> 15                     retval_ = ag__.converted_call(ag__.ld(step_function), (ag__.ld(self), ag__.ld(iterator)), None, fscope)
     16                 except:
     17                     do_return = False

ValueError: in user code:

    File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 1160, in train_function  *
        return step_function(self, iterator)
    File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 1146, 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 1135, in run_step  **
        outputs = model.train_step(data)
    File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 993, in train_step
        y_pred = self(x, training=True)
    File "/usr/local/lib/python3.7/dist-packages/keras/utils/traceback_utils.py", line 70, in error_handler
        raise e.with_traceback(filtered_tb) from None
    File "/usr/local/lib/python3.7/dist-packages/keras/engine/input_spec.py", line 251, in assert_input_compatibility
        f'Input {input_index} of layer "{layer_name}" '

    ValueError: Exception encountered when calling layer "sequential_1" "                 f"(type Sequential).
    
    Input 0 of layer "conv2d_5" is incompatible with the layer: expected min_ndim=4, found ndim=1. Full shape received: (None,)
    
    Call arguments received by layer "sequential_1" "                 f"(type Sequential):
      • inputs=tf.Tensor(shape=(None,), dtype=string)
      • training=True
      • mask=None

I also added the code posted here to Codeshare , so you can see my code. Can you help me understand what is going on? Thanks for the help.

Answer 1

In your code you have:

x_train = np.array(list(map(img_preprocess, X_train)))
x_train = np.array(list(map(img_preprocess, X_valid)))

I think this should be:

x_train = np.array(list(map(img_preprocess, X_train)))
x_valid = np.array(list(map(img_preprocess, X_valid)))

However I don't think the error comes from this issue. In fact the input to your network is X_train , and not x_train , I don't know if you are aware of that.

The error definitely comes from a mismatch from the input shape of X_train , and what you decided the input of the model should be, that is (66, 200, 3) .