fchollet / deep-learning-with-python-notebooks

Jupyter notebooks for the code samples of the book "Deep Learning with Python"
MIT License
18.44k stars 8.58k forks source link

5.3-using-a-pretrained-convnet #41

Open snowformatics opened 6 years ago

snowformatics commented 6 years ago

Hi,

I am trying to run the 5.3-using-a-pretrained-convnet notebook with my set of images (50x180, RGB) but I get the following error:

train_features, train_labels = extract_features(train_dir, 25000) File "F:/Experiments/CNN_chollet/exp02.py", line 156, in extract_features features[i * batch_size : (i + 1) * batch_size] = features_batch ValueError: could not broadcast input array from shape (20,1,5,512) into shape (20,4,4,512) Exception ignored in: <bound method BaseSession.__del__ of <tensorflow.python.client.session.Session object at 0x000000000921FEF0>> Traceback (most recent call last): File "D:\Users\lueck\Anaconda2\envs\tensorflow\lib\site-packages\tensorflow\python\client\session.py", line 582, in __del__ UnboundLocalError: local variable 'status' referenced before assignment

Any suggestion what I am doing wrong?

Thanks in advance