CODEWITHSUNDEEP
tensorflowkerasdeep-learninggpu
Yoo
Yoo

Reputation: 11

multi_gpu_model : object of type 'NoneType' has no len()

I am getting this error while using keras multi_gpu_model. The code run fines if I eliminate this line. Also, with CNN model it works fines, it's just that while dense network it gives the error. Could you please help me to solve this issue. Thanks.

import numpy as np
import numpy as np
import matplotlib.pyplot as plt
import tensorflow as tf
from keras.models import Sequential
from keras.layers import Dense, Dropout
from keras.layers import LSTM, BatchNormalization,Flatten
from keras.utils.vis_utils import model_to_dot
from keras.optimizers import adam
from keras.models import load_model
import pylab
from sklearn.model_selection import train_test_split
from keras.utils import multi_gpu_model 

from scipy.io import wavfile
X=np.ones(10000)
y=np.zeros(100)
x_train=X
y_train=y
x_train=np.array(x_train)
y_train=np.array(y_train)
x_train.shape=(1,10000)
y_train.shape=(1,100)
model = Sequential()
model.add(Dense(500,activation = 'tanh'))
model.add(Dense(450, activation = 'tanh'))
model.add(Dense(412, activation = 'tanh'))
model.add(Dense(100, activation = 'tanh'))
opt = adam(lr=0.002, decay=1e-6)
model = multi_gpu_model(model, gpus=4)
model.compile(loss='mae', optimizer=opt, metrics=['accuracy'])
model.fit(x_train,y_train,epochs=50, batch_size = 40000)

Error: Traceback (most recent call last):
  File "p.py", line 37, in <module>
    model = multi_gpu_model(model, gpus=4)
  File "/home/ENG/benipas1/anaconda3/envs/new/lib/python3.7/site-packages/keras/utils/multi_gpu_utils.py", line 203, in multi_gpu_model
    for i in range(len(model.outputs)):
TypeError: object of type 'NoneType' has no len()

Upvotes: 1

Views: 1515

Answers (1)

Dr. Snoopy
Dr. Snoopy

Reputation: 56347

The problem is here:

model = Sequential()
model.add(Dense(500,activation = 'tanh'))

You are not giving an input shape to the first layer, so the outputs of the model are completely undefined and model.outputs is None. If you provide the input shape to the first layer, then the outputs are defined and it should work fine. You are probably providing the input shape to your CNN models and that is why it works:

model.add(Dense(500,activation = 'tanh', input_shape=(something,)))

Upvotes: 1

Related Questions