pose-transfer

KO | EN

gitlite — search

#javascript #python #llm #rust #deep-learning #linux #docker #macos #java #nodejs #awesome #pytorch #ios #openai

(★ 81)

PyTorch Implementation of Deformable GAN https://arxiv.org/abs/1801.00055

pose-transfer 최신버젼 다운로드

최종 버전 다운로드 (.zip)

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# Pose-Transfer

PyTorch Implementation of Deformable GAN https://arxiv.org/abs/1801.00055

Also check out the original repo in Keras, by AliaksandrSiarohin - https://github.com/AliaksandrSiarohin/pose-gan

![alt text](https://github.com/AliaksandrSiarohin/pose-gan/blob/master/sup-mat/teaser.jpg)

## Baseline Model ( run in src_baseline )

### Fasion :

CUDA_VISIBLE_DEVICES=1 python main.py --l1_penalty_weight 10 --batch_size 4 --number_of_epochs 90 --gen_type baseline --expID baseline_fasion --pose_dim 18 --dataset fasion

### Human 3.6 :

CUDA_VISIBLE_DEVICES=0 python main.py --l1_penalty_weight 10 --batch_size 4 --number_of_epochs 90 --gen_type baseline --expID baseline_h36m --dataset h36m

## Deformable Model ( run in src_deformable )

### Fasion :

CUDA_VISIBLE_DEVICES=1 python main.py --warp_skip mask --l1_penalty_weight 0.01 --batch_size 2 --number_of_epochs 90 --gen_type baseline --expID full_fasion --pose_dim 18 --dataset fasion --nn_loss_area_size 5 --batch_size 2 --content_loss_layer block1_conv2

### Human 3.6 :

CUDA_VISIBLE_DEVICES=1 python main.py --warp_skip mask --l1_penalty_weight 0.01 --batch_size 2 --number_of_epochs 90 --gen_type baseline --expID full_h36m --dataset h36m --nn_loss_area_size 5 --batch_size 2 --content_loss_layer block1_conv2

Specify data directory by passing data_Dir option.

## ToDo :

-> Add code for loading annotations and train/test pairs for Fasion and Human 3.6 dataset.

pose-transfer

pose-transfer 최신버젼 다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

pose-transfer

pose-transfer 최신버젼 다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

Download README