TensorFlow Feature Extractor
This is a convenient wrapper for feature extraction or classification in TensorFlow. Given well known pre-trained models on ImageNet, the extractor runs over a list or directory of images. Optionally, features can be saved as HDF5 file. It supports all the pre-trained models listed on the official page.
TensorFlow models tested:
- Inception v1-v4
- ResNet v1 and v2
- VGG 16-19
Requirements
- TensorFlow (tested with version 1.8)
- TensorFlow Models
- The usual suspects:
numpy,scipy. - Optionally
h5pyfor saving features to HDF5 file
Setup
- Checkout the TensorFlow
modelsrepository somewhere on your machine. The path where you checkout the repository will be denoted<checkout_dir>/models
git clone https://github.com/tensorflow/models/
- Add the directory
<checkout_dir>/research/slimto the$PYTHONPATHvariable. Or add a line to your.bashrcfile.
export PYTHONPATH="<checkout_dir>/research/slim:$PYTHONPATH"
- Download the model checkpoints from the official page.
Usage
There are two example files, one for classification and one for feature extraction.
Feature Extraction
ResNet-v1-101
example_feat_extract.py
--network resnet_v1_101
--checkpoint ./checkpoints/resnet_v1_101.ckpt
--image_path ./images_dir/
--out_file ./features.h5
--num_classes 1000
--layer_names resnet_v1_101/logits
ResNet-v2-101
example_feat_extract.py
--network resnet_v2_101
--checkpoint ./checkpoints/resnet_v2_101.ckpt
--image_path ./images_dir/
--out_file ./features.h5
--layer_names resnet_v2_101/logits
--preproc_func inception
Inception-v4
example_feat_extract.py
--network inception_v4
--checkpoint ./checkpoints/inception_v4.ckpt
--image_path ./images_dir/
--out_file ./features.h5
--layer_names Logits
Image Classification
example_classification.py
--network resnet_v1_101
--checkpoint ./checkpoints/resnet_v1_101.ckpt
--image_path ./images_dir/
--num_classes 1000
--logits_name resnet_v1_101/logits
Work in Progress
Save image file names to HDF5 fileSupport for multi-threaded preprocessing