[FIXED] My neural network gives an error and I don't know why

Issue

I'm relatively new to programming neural networks and have been following a few tutorials about it before deciding to try and learn to program neural networks on my own using what i'd learnt. I've been trying to program a basic neural network just so i can learn how it works, but it keeps giving me an error. I would really appreciate it if someone could help.

Here's my code:

import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout, Activation, Flatten
from tensorflow.keras.layers import Conv2D, MaxPooling2D

import pickle

pickle_in = open("X.pickle","rb")
X = pickle.load(pickle_in)

pickle_in = open("y.pickle","rb")
y = pickle.load(pickle_in)

X = X/255.0

model = Sequential()
model.add(Conv2D(8,(5, 5),padding="same",activation='relu',input_shape=(784,)))
model.add(Conv2D(32, (3, 3), activation='relu', padding='same'))
model.add(Conv2D(64, (3, 3), activation='relu', padding='same'))
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(Conv2D(64, (3, 3), activation='relu', padding='same'))
model.add(Conv2D(64, (3, 3), activation='relu', padding='same'))
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(Conv2D(64, (3, 3), activation='relu', padding='same'))
model.add(Conv2D(64, (3, 3), activation='relu', padding='same'))
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(Conv2D(64, (3, 3), activation='relu', padding='same'))
model.add(Flatten())
model.add(Dense(1))
model.add(Activation('linear'))
model.add(Dense(y.shape[1]))
model.add(Activation('linear'))

model.summary()
model.compile(loss='mean_squared_error',optimizer='adam',metrics=['mae','mse', 'accuracy'])

model.fit(X, y, epochs=20, batch_size=10,verbose=2)

Here's the error message I'm getting:

str(x.shape.as_list()))
ValueError: Input 0 of layer conv2d is incompatible with the layer: expected ndim=4, found ndim=2. Full shape received: [None, 784]

Thanks in advance!

Solution

The error is cause Conv2D expects input shape to be of 4 dimensions i.e. [batch_size, height, width, channels]. You can do one thing i.e. reshape your input to the model.

X = X.reshape(-1, 28, 28, 1) # incase of single channel (grayscale)
# OR
X = X.reshape(-1, 28, 28, 3) # incase of RGB
# and then change the input shape of your `Conv2D` layer accordingly to
model = Sequential()
model.add(Conv2D(8,(5, 5),padding="same",activation='relu',input_shape=(28,28,1)))
# OR
model = Sequential()
model.add(Conv2D(8,(5, 5),padding="same",activation='relu',input_shape=(28,28,3)))

Answered By - Abhishek Prajapat