classification test

test.py

from keras.applications.inception_v3 import *
from keras.preprocessing import image
from keras.applications.imagenet_utils import decode_predictions
from keras import backend as K
import numpy as np

model = InceptionV3(weights='imagenet')

img_path = 'apple.jpg'
img = image.load_img(img_path, target_size=(299, 299))
x = image.img_to_array(img)
x = np.expand_dims(x, axis=0)
x = preprocess_input(x)

preds = model.predict(x)
print('Predicted:', decode_predictions(preds))

Hi, I have been testing this test.py, but I got the following error message, I am using theano (0.9.0) along with keras(2.0.3). Would you like to share any hint what can cause the problem?

raceback (most recent call last):
File "test.py", line 7, in
model = InceptionV3(weights='imagenet')
File "/tmp/lib/python3.5/site-packages/keras/applications/inception_v3_nourl.py", line 388, in InceptionV3
model.load_weights(weights_path)
File "/tmp/lib/python3.5/site-packages/keras/engine/topology.py", line 2500, in load_weights
load_weights_from_hdf5_group(f, self.layers)
File "/tmp/lib/python3.5/site-packages/keras/engine/topology.py", line 2911, in load_weights_from_hdf5_group
' elements.')
ValueError: Layer #0 (named "conv2d_1" in the current model) was found to correspond to layer convolution2d_1 in the save file. However the new layer conv2d_1 expects 1 weights, but the saved weights have 2 elements.

Install the latest keras version. The problem is solved over there