ml-lab / animal_human_kp

Contact: Maheen Rashid ([email protected]) ##Getting Started

Download the code from GitHub:

git clone https://github.com/menoRashid/animal_human_kp
cd animal_human_kp

Install Torch. Instructions are here

Install Torch requirements:

• torchx

luarocks install torchx

• npy4th (You may need to checkout commit from 5-10-16)

git clone https://github.com/htwaijry/npy4th.git
cd npy4th
luarocks make

Install Python requirements if needed:

• numpy
• scipy
• matplotlib
• PIL

Install the Spatial Tranformer module provided:

cd stnbhwd-master
luarocks make

It is a modification of the code from Spatial Transformer Network (Jaderberg et al.) and includes a Thin Plate Spline grid generator layer.

##Dataset Download the Horse Dataset (580 MB)

Run the following commands

cd data
unzip <path to data zip file>

##Models To download all the pretrained and untrained models go here (8.6 GB)

Run the following commands

cd models
unzip <path to models zip file>

Otherwise add the individual models to models/

• Full model for horses with tps warping(4.4 GB)
• Full model for horses with affine warping(4.4 GB)
• TPS Warping model for horses(738 MB)
• Affine Warping model for horses(764 MB)
• Keypoint network trained on human faces(3.4 GB)
• Untrained TPS Warping model(111 MB)
• Untrained Affine Warping model(121 MB)

##Testing To test pretrained model run the following commands

cd torch
th test.th -out_dir_images <path to results directory>
python ../python/visualize_results.py --test_dir <path to results directory> 

after replacing with the path to the folder where you would like the output images to be saved.

A webpage with the results would be in the results directory.

<path to results directory>/results.html

##Training The file for training the full model is

torch/train_full_model.th

For details on training run

cd torch
th train_full_model.th -help

To train the model with affine warping uncomment lines 373-375. Currently, all parameters are the parameters used in the paper.

The file for training the warping network is

torch/train_warping_net.th

For details on training run

cd torch
th train_warping_net.th -help

To train the model with affine warping uncomment lines 313-314.