run0.sh

cd /path/to/demo/data/..  # To be consistent with above.

# If you are on an AWS Deep Learning AMI, Keras must be upgraded to 2.x:
# sudo pip install keras --upgrade --no-deps

curl -o classifier_from_little_data_script_1.py \
  https://gist.githubusercontent.com/fchollet/0830affa1f7f19fd47b06d4cf89ed44d/raw/47d3e33764c902ed33a64f35f5f68d911de05d8d/classifier_from_little_data_script_1.py
 
python2 classifier_from_little_data_script_1.py

Using TensorFlow backend.
Found 2000 images belonging to 2 classes.
Found 888 images belonging to 2 classes.
Epoch 1/5
125/125 [==============================] - 47s - loss: 0.7540 - acc: 0.5235 - val_loss: 0.6897 - val_acc: 0.5750
Epoch 2/5
125/125 [==============================] - 45s - loss: 0.6917 - acc: 0.5410 - val_loss: 0.6809 - val_acc: 0.5288
Epoch 3/5
125/125 [==============================] - 47s - loss: 0.6615 - acc: 0.6215 - val_loss: 0.6464 - val_acc: 0.6225
Epoch 4/5
125/125 [==============================] - 46s - loss: 0.6407 - acc: 0.6445 - val_loss: 0.6345 - val_acc: 0.6730
Epoch 5/5
125/125 [==============================] - 45s - loss: 0.6113 - acc: 0.6675 - val_loss: 0.6442 - val_acc: 0.6313