TypeError：添加的层必须是 class 层的实例。 找到：Tensor(“input_1:0”, shape=(None, 64, 64, 3), dtype=float32) -Python

Question

I actually try to make a convolutional neural network in order to classify dogs and cat ( i'm newbie in Machine Learning so don't judge me too bad:) ). I got the exactly the same error from the title of this post. To be honest, i tried to learn myself from Keras API documentation, tried to catch some tips from stackoverflow,github,towardsdatascience and others. Some said that error belongs to different versions of tensorflow and keras libraries,others said that it belongs to syntax. I will leave my code here,tell me where i made mistakes,i'm open to learn new tips.

#IMPORTING LIBRARIES
import tensorflow as tf
import pandas as pd
import keras
from keras.preprocessing.image import ImageDataGenerator



#IMAGE DATA PREPROCESSING

#preprocessing the training set
train_datagen = ImageDataGenerator(
        rescale=1./255,
        shear_range=0.2,
        zoom_range=0.2,
        horizontal_flip=True)
training_set = train_datagen.flow_from_directory(
        directory = r"C:\Users\Cucu\Downloads\training_set",
        target_size=(64 , 64),
        batch_size=32,
        class_mode='binary')

#preprocessing the test set
test_datagen = ImageDataGenerator(rescale=1./255)
test_set = test_datagen.flow_from_directory(
        directory = r"C:\Users\Cucu\Downloads\test_set",
        target_size=(64 , 64),
        batch_size=32,
        class_mode='binary')


 
#BULDING THE CNN
#
#
#initialising the cnn
cnn = tf.keras.models.Sequential()


#convolution
cnn.add(tf.keras.layers.Conv2D(filters = 32 , kernel_size = 3 , activation = 'relu' ))
cnn.add(keras.Input(shape=(64, 64, 3)))

#pooling
cnn.add(tf.keras.layers.MaxPool2D( pool_size = 2 , strides = 2))


#adding a SECOND CONVOLUTIONAL LAYER
cnn.add(tf.keras.layers.Conv2D(filters = 32 , kernel_size = 3 , activation = 'relu'))
cnn.add(tf.keras.layers.MaxPool2D( pool_size = 2 , strides = 2))


#flattening
cnn.add(tf.keras.layers.Flatten())


#full connection
cnn.add(tf.keras.layers.Dense(units = 128 , activation = 'relu'))


#adding the output layer
cnn.add(tf.keras.layers.Dense(units = 4 , activation = 'sigmoid'))

and the error(exactly as the title) is:

TypeError: The added layer must be an instance of class Layer. Found: Tensor("input_1:0", shape=(None, 64, 64, 3), dtype=float32)

Massive apreciation to those who can give me some tips. I know this is an extra full beginner level,but you know,sometimes you have to learn along the way of practical experience:)

Answer 1

replace:

#convolution
cnn.add(tf.keras.layers.Conv2D(filters = 32 , kernel_size = 3 , activation = 'relu' ))
cnn.add(keras.Input(shape=(64, 64, 3)))

by:

cnn.add(tf.keras.Input(shape=(64, 64, 3)))
cnn.add(tf.keras.layers.Conv2D(filters = 32 , kernel_size = 3 , activation = 'relu' ))

Usually, the Input layer is the first one of your network and you should choose between keras and tf.keras (the second one preferably)