VGG16 in TensorFlow

Note

You can follow along with the code in the Jupyter notebook ch-12a_VGG16_TensorFlow.

For all examples of VGG16 in TensorFlow, we first download the checkpoint file from http://download.tensorflow.org/models/vgg_16_2016_08_28.tar.gz and initialize variables with the following code:

model_name='vgg_16'
model_url='http://download.tensorflow.org/models/'
model_files=['vgg_16_2016_08_28.tar.gz']
model_home=os.path.join(models_root,model_name) 

dsu.download_dataset(source_url=model_url,
    source_files=model_files,
    dest_dir = model_home,
    force=False,
    extract=True)

We also define some common imports and variables:

from tensorflow.contrib import slim
from tensorflow.contrib.slim.nets import vgg
image_height=vgg.vgg_16.default_image_size
image_width=vgg.vgg_16.default_image_size

Image classification using pre-trained VGG16 in TensorFlow

Now let us first try to predict the classes of our test images, without retraining. First, we clear the default graph and define a...