CODEWITHSUNDEEP
pythonnumpytensorflowkerasdeep-learning
Ash Roy
Ash Roy

Reputation: 87

Error 'module 'tensorflow' has no attribute 'get_default_graph'?

I've been getting this error 'module 'tensorflow' has no attribute 'get_default_graph' every time I try to run my model on Keras, and I've tried pretty much everything in previous answers. I'm attempting to create a 3D-CNN using the Keras backend. It worked for the past few days, but yesterday I started to get this error every time I tried to create this model. Here's my code:

# importing important packages

import os
import numpy as np
import tensorflow as tf
import keras 
from keras.models import Sequential, Model
from keras.layers import Dense, Flatten, Conv3D, MaxPooling3D, Dropout, BatchNormalization, LeakyReLU
from tensorflow.python.keras import backend as K
from keras.regularizers import l2
from sklearn.utils import compute_class_weight

#import dataset
import numpy as np
DATA_URL = '/content/drive/My Drive/icafiledata4.npz'
with np.load(DATA_URL) as data:
  X = data['arr_0']
  y = data['arr_1']

BATCH_SIZE = 128
input_shape=(64, 64, 40, 20)


# Create the model
model = Sequential()

model.add(Conv3D(64, kernel_size=(3,3,3), activation='relu', input_shape=input_shape, kernel_regularizer=l2(0.005), bias_regularizer=l2(0.005), data_format = 'channels_first', padding='same'))
model.add(MaxPooling3D(pool_size=(2, 2, 2)))
model.add(Conv3D(64, kernel_size=(3,3,3), activation='relu', input_shape=input_shape, kernel_regularizer=l2(0.005), bias_regularizer=l2(0.005), data_format = 'channels_first', padding='same'))
model.add(MaxPooling3D(pool_size=(2, 2, 2)))
model.add(BatchNormalization(center=True, scale=True))

model.add(Conv3D(64, kernel_size=(3,3,3), activation='relu', input_shape=input_shape, kernel_regularizer=l2(0.005), bias_regularizer=l2(0.005), data_format = 'channels_first', padding='same'))
model.add(MaxPooling3D(pool_size=(2, 2, 2)))
model.add(Conv3D(64, kernel_size=(3,3,3), activation='relu', input_shape=input_shape, kernel_regularizer=l2(0.005), bias_regularizer=l2(0.005), data_format = 'channels_first', padding='same'))
model.add(MaxPooling3D(pool_size=(2, 2, 2)))
model.add(BatchNormalization(center=True, scale=True))

model.add(Flatten())
model.add(BatchNormalization(center=True, scale=True))
model.add(Dense(128, activation='relu', kernel_regularizer=l2(0.01), bias_regularizer=l2(0.01)))
model.add(Dropout(0.5))
model.add(Dense(128, activation='relu', kernel_regularizer=l2(0.01), bias_regularizer=l2(0.01)))
model.add(Dense(1, activation='sigmoid', kernel_regularizer=l2(0.01), bias_regularizer=l2(0.01)))
 
# Compile the model
model.compile(optimizer = tf.keras.optimizers.Adam(lr=0.001), loss='binary_crossentropy', metrics=['accuracy'])

Does anyone have any tips? Thank you so much! Addtional info: Tensorflow 2.2.0, keras 2.3.0

Upvotes: 0

Views: 1956

Answers (1)

Tasnuva Leeya
Tasnuva Leeya

Reputation: 2795

please try:

from tensorflow.keras.models import Sequential, Model
from tensorflow.keras.layers import Dense, Flatten, Conv3D, MaxPooling3D, Dropout, BatchNormalization, LeakyReLU
from tensorflow.keras.regularizers import l2

instead of:

import keras 
from keras.models import Sequential, Model
from keras.layers import Dense, Flatten, Conv3D, MaxPooling3D, Dropout, BatchNormalization, LeakyReLU
from keras.regularizers import l2

TensorFlow 2.0 and above has keras built-in; no need to load Keras separately into your environment, just change the import statements

Upvotes: 2

Related Questions