ValueError：无法为张量“输入/X：0”提供形状（1、50、50、3）的值，其形状为“（？、50、50、1）”

Question

my model input shape is (50,50,1) I am getting the frame by:

 cv2.VideoCapture(0).read()

When I'm using np.reshape() function it does not reshape it the desired shape.

sized_frame = (cv2.resize(frame, (50,50)))

cv2.waitKey(0)
img_data = np.array(photo)
data = tf.reshape(img_data, (1,50,50,3))
model_out = model.predict([img_data])[0]
print(model_out)
if np.argmax(model_out) == 1:
    str_label = 'Dog'
else:
    str_label = 'Cat'

return str_label

This is the error I'm getting:

ValueError: Cannot feed value of shape (1, 50, 50, 3) for Tensor 'input/X:0', which has shape '(?, 50, 50, 1)'

Answer 1

The following code should solve your error

gray = cv2.cvtColor(photo, cv2.COLOR_BGR2GRAY)
img_data = np.array(gray)
data = tf.reshape(img_data, (1,50,50,1))
model_out = model.predict(img_data)[0]

Under the assumption that you trained on Grayscale images