Keras错误拟合模型：提供的元素太多

Question

Goal: Evaluate a set of 5 images and produce an image as the output.

Problem: I am currently getting an error Too many elements provided.

Disclaimer: I'm new to Keras and Deep learning as a whole, I fully expect that this approach is wrong but I would like to understand why I'm getting this error

The shape of the output and input look correct to me.

I have tried making the output just a Dense layer with a shape of (None,6912.)
I have tried having the output be a Conv2d but then I get the following error, I am unsure why the output is (46,46,3) and not (48,48,3)

Error when checking target: expected conv2d_1 to have shape (None, 46, 46, 3) but got array with shape (379, 48, 48, 3)

Code:

width = 48
height = 48
png = []

for image_path in glob.glob(r"D:\temp\*.png"):
   png.append(misc.imread(image_path))

im = np.asarray(png)
print ('dataset: ', im.shape)

window = 6
dataset = np.zeros([len(im) - window, window,width,height,3])
for i in range(len(dataset)):
    dataset[i, :] = im[i:i + window]
x_train = dataset[:,:-1]
y_train = dataset[:,-1]
y_train1 = y_train.reshape(-1,width*height*3)

print("x_train: ", x_train.shape)
print("y_train:" ,y_train.shape)
print("y_train1:" ,y_train1.shape)

model = Sequential()
model.add(Conv3D(filters=40,
               kernel_size=(5,10,10),
               input_shape=(5,width,height,3),
               padding='same',
               activation='relu'))
model.add(Activation('relu'))
model.add(Conv3D(filters=40,
               kernel_size=(3,3,3),
               padding='same',
               activation='relu'))

model.add(Flatten())
model.add(Dropout(0.5))
model.add(Dense(width * height * 3, activation='softmax'))
model.add(Reshape((48,48,3)))

model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])

print("model Input: " ,model.input_shape)
print("model output:", model.output_shape)

model.fit(x_train, y_train, batch_size=10, epochs=300, validation_split=0.05)

Output:

Using TensorFlow backend.
dataset:  (385, 48, 48, 3)
x_train:  (379, 5, 48, 48, 3)
y_train: (379, 48, 48, 3)
y_train1: (379, 6912)
model Input:  (None, 5, 48, 48, 3)
model output: (None, 48, 48, 3)
Traceback (most recent call last):
  ....
  File "D:\Program Files\Python35\lib\site-packages\tensorflow\python\framework\tensor_util.py", line 424, in make_tensor_proto
    (shape_size, nparray.size))
ValueError: Too many elements provided. Needed at most -1109917696, but received 1

Model Summary:

_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv3d_1 (Conv3D)            (None, 5, 48, 48, 40)     60040     
_________________________________________________________________
activation_1 (Activation)    (None, 5, 48, 48, 40)     0         
_________________________________________________________________
conv3d_2 (Conv3D)            (None, 5, 48, 48, 40)     43240     
_________________________________________________________________
flatten_1 (Flatten)          (None, 460800)            0         
_________________________________________________________________
dropout_1 (Dropout)          (None, 460800)            0         
_________________________________________________________________
dense_1 (Dense)              (None, 6912)              -110991078
_________________________________________________________________
reshape_1 (Reshape)          (None, 48, 48, 3)         0         
=================================================================

Thank in advanced.

Answer 1

In the Conv2D case, you've probably forgotten to use padding = 'same' . A (3,3) kernel removes 2 pixes in each dimension.

And by the negative number of parameters shown in the Dense layer, I believe you've got a model bigger than supported.

Maybe there is a maximum limit of parameters for a single layer. In that case, I'd reduce the number of filters in the convolutions, or sum the channels before the flatten layer.