Compare commits
8
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 luni
|
2489e28de4 | ||
|
luni
|
6e24c1f41b | ||
|
luni
|
2b8abd776b | ||
|
luni
|
1f8793e4e8 | ||
|
luni
|
0dfe7f7659 | ||
|
luni
|
8c0436cea8 | ||
|
luni
|
ffdc60062d | ||
|
luni
|
73d374401b |
@@ -1,49 +0,0 @@
|
||||
# stylegan2-tf-2.x
|
||||
* This is tensorflow 2.0 based keras subclassing reimplementation of official [StyleGAN2 Repo](https://github.com/NVlabs/stylegan2)
|
||||
|
||||
## Inference from official weights
|
||||
* Please check [how_to_extract_official_weights.md](./how_to_extract_official_weights.md)
|
||||
|
||||
| Official repo result | Official weight copied result from this repo |
|
||||
| :---: | :---: |
|
||||
| ![official_result] | ![restored_result] |
|
||||
|
||||
## Training on 256x256
|
||||
* batch size 32
|
||||
* around 300k steps
|
||||
|
||||
| d_loss | g_loss |
|
||||
| :---: | :---: |
|
||||
| ![256x256_d_loss]| ![256x256_g_loss]|
|
||||
|
||||
* result samples
|
||||
|
||||
| | | |
|
||||
| :---: | :---: | :---: |
|
||||
| ![256x256_result_0]| ![256x256_result_1]| ![256x256_result_2]|
|
||||
|
||||
## Using custom data
|
||||
* Create dataset(tf.data.Dataset) loader which returns
|
||||
* shape: `[None, 3, res, res]` where `res` is desired image resolution
|
||||
* image value range: `[-1, +1]`
|
||||
|
||||
## Etc
|
||||
### Using with pycharm
|
||||
* If .bashrc file's paths don't work in pycharm environment (e.g. `nvcc -h`), open pycharm with following
|
||||
```bash
|
||||
# move to pycharm installed location (location may vary)
|
||||
moono@moono-ubuntu:~$ cd .local/share/JetBrains/Toolbox/apps/PyCharm-P/ch-0/201.7846.77/bin/
|
||||
|
||||
# launch pycharm with .bashrc
|
||||
moono@moono-ubuntu:~/.local/share/JetBrains/Toolbox/apps/PyCharm-P/ch-0/201.7846.77/bin$ bash pycharm.sh
|
||||
```
|
||||
|
||||
[loss_tensorboard]: assets/tf-keras-stylegan2-loss.PNG
|
||||
[generation_tensorboard]: assets/tf-keras-stylegan2-fake-images.PNG
|
||||
[official_result]: assets/seed6600-official.png
|
||||
[restored_result]: assets/seed6600-restored.png
|
||||
[256x256_d_loss]: assets/d_loss_256x256.png
|
||||
[256x256_g_loss]: assets/g_loss_256x256.png
|
||||
[256x256_result_0]: assets/out_256x256_0.png
|
||||
[256x256_result_1]: assets/out_256x256_1.png
|
||||
[256x256_result_2]: assets/out_256x256_2.png
|
||||
+219
@@ -0,0 +1,219 @@
|
||||
nohup python cvae_pyramid.py --name="lhunor_pyr_abl_32_64_e2e_r3" > nohup/review/pyr_abl_32_64_e2e_r3.out 2>&1 &
|
||||
nohup python cvae_pyramid.py --name="lhunor_pyr_abl_32_64_e2e_r3_pre" > nohup/review/pyr_abl_32_64_e2e_r3_pre.out 2>&1 &
|
||||
nohup python cvae_pyramid.py --name="lhunor_pyr_abl_32_64_e2e_r3_fine" > nohup/review/pyr_abl_32_64_e2e_r3_fine.out 2>&1 &
|
||||
nohup python evaluate_ae_pyramid.py --name evaluate_pyr_abl_32_64_e2e_r3 > nohup/evaluate/pyr_abl_32_64_e2e_r3.out 2>&1 &
|
||||
nohup python calculate_error.py --name error_pyr_abl_32_64_e2e_r3 > nohup/error/pyr_abl_32_64_e2e_r3.out 2>&1 &
|
||||
|
||||
|
||||
one final convolutional layer for smoothing, on the final coordinates
|
||||
|
||||
skirts!!!!
|
||||
pyramid next week
|
||||
|
||||
basic final, basic final skirts,
|
||||
basic pyramid
|
||||
|
||||
|
||||
removing curvatures test in ablation
|
||||
|
||||
nohup python cvae_low.py --name="lhunor_cvae_low_4_3_skirt_d32" > nohup/nohup_cvae_low_4_3_skirt_d32.out 2>&1 &
|
||||
nohup python auto_encoder_body.py --name="lhunor_ae_body_post_2" > nohup/post/ae_body_2.out 2>&1 &
|
||||
nohup python auto_encoder_static.py --name="lhunor_ae_static_post_4" > nohup/post/ae_static_4.out 2>&1 &
|
||||
nohup python auto_encoder_curv.py --name="lhunor_ae_curv_post_1" > nohup/post/ae_curv_1.out 2>&1 &
|
||||
nohup python cvae_pyramid.py --name="lhunor_abl_pyr_64_128_3" > nohup/post/abl_pyr_64_128_3.out 2>&1 &
|
||||
|
||||
nohup python cvae_pyramid.py --name="lhunor_abl_pyr_32_64" > nohup/post/abl_pyr_32_64.out 2>&1 &
|
||||
|
||||
nohup python cvae_pyramid.py --name="lhunor_cvae_pyr_3_32_2_64_skirt_test_60k" > nohup/cvae_pyr_3_32_2_64_skirt_test_60k.out 2>&1 &
|
||||
nohup python cvae_pyramid.py --name="lhunor_pyr_abl_32" > nohup/ablation/pyr_abl_32.out 2>&1 &
|
||||
nohup python cvae_pyramid.py --name="lhunor_pyr_abl_32_2" > nohup/ablation/pyr_abl_32_2.out 2>&1 &
|
||||
nohup python cvae_pyramid.py --name="lhunor_pyr_abl_32_skin" > nohup/ablation/pyr_abl_32_skin.out 2>&1 &
|
||||
nohup python cvae_pyramid.py --name="lhunor_pyr_abl_32_skin_offset" > nohup/ablation/pyr_abl_32_skin_offset.out 2>&1 &
|
||||
nohup python cvae_pyramid.py --name="lhunor_pyr_abl_32_skirt" > nohup/ablation/pyr_abl_32_skirt.out 2>&1 &
|
||||
nohup python cvae_pyramid.py --name="lhunor_pyr_abl_32_extra_loss_skirt" > nohup/ablation/pyr_abl_32_extra_loss_skirt.out 2>&1 &
|
||||
nohup python cvae_pyramid.py --name="lhunor_pyr_abl_32_skirt_2" > nohup/ablation/pyr_abl_32_skirt_2.out 2>&1 &
|
||||
nohup python cvae_pyramid.py --name="lhunor_pyr_abl_32_64" > nohup/ablation/pyr_abl_32_64.out 2>&1 &
|
||||
nohup python cvae_pyramid.py --name="lhunor_pyr_abl_32_64_2" > nohup/ablation/pyr_abl_32_64_2.out 2>&1 &
|
||||
nohup python cvae_pyramid.py --name="lhunor_pyr_abl_32_64_skirt" > nohup/ablation/pyr_abl_32_64_skirt.out 2>&1 &
|
||||
nohup python cvae_pyramid.py --name="lhunor_pyr_abl_32_64_skirt_2" > nohup/ablation/pyr_abl_32_64_skirt_2.out 2>&1 &
|
||||
nohup python cvae_pyramid.py --name="lhunor_pyr_abl_64_cape_m" > nohup/ablation/pyr_abl_64_cape_m.out 2>&1 &
|
||||
nohup python cvae_pyramid.py --name="lhunor_pyr_abl_64_cape_f" > nohup/ablation/pyr_abl_64_cape_f.out 2>&1 &
|
||||
nohup python cvae_pyramid.py --name="lhunor_pyr_abl_64_cape_f_2" > nohup/ablation/pyr_abl_64_cape_f_2.out 2>&1 &
|
||||
nohup python cvae_pyramid.py --name="lhunor_pyr_abl_64_128_cape_f" > nohup/ablation/pyr_abl_64_128_cape_f.out 2>&1 &
|
||||
nohup python cvae_pyramid.py --name="lhunor_pyr_abl_64_128_cape_m" > nohup/ablation/pyr_abl_64_128_cape_m.out 2>&1 &
|
||||
nohup python cvae_pyramid.py --name="lhunor_pyr_abl_64_128_256_cape_f_2" > nohup/ablation/pyr_abl_64_128_256_cape_f_2.out 2>&1 &
|
||||
nohup python cvae_pyramid.py --name="lhunor_pyr_abl_64_128_256_512_cape_f" > nohup/ablation/pyr_abl_64_128_256_512_cape_f.out 2>&1 &
|
||||
nohup python cvae_pyramid.py --name="lhunor_pyr_abl_64_128_256_512_cape_f_2" > nohup/ablation/pyr_abl_64_128_256_512_cape_f_2.out 2>&1 &
|
||||
nohup python upscale_test.py --name="lhunor_256_512_skirt" > nohup/up_256_512_skirt.out 2>&1 &
|
||||
nohup python cvae.py --name="lhunor_cvae_v2_7_4_3" > nohup/cvae_v2_7_4_3.out 2>&1 &
|
||||
nohup python cvae.py --name="lhunor_abl_extra_loss" > nohup/ablation/abl_extra_loss.out 2>&1 &
|
||||
nohup python cvae.py --name="lhunor_abl_extra_loss_skirt" > nohup/ablation/abl_extra_loss_skirt.out 2>&1 &
|
||||
nohup python cvae.py --name="lhunor_abl_extra_loss_skirt_2" > nohup/ablation/abl_extra_loss_skirt_2.out 2>&1 &
|
||||
nohup python cvae.py --name="lhunor_abl_curv" > nohup/ablation/abl_curv.out 2>&1 &
|
||||
nohup python cvae.py --name="lhunor_abl_curv_skirt" > nohup/ablation/abl_curv_skirt.out 2>&1 &
|
||||
nohup python cvae.py --name="lhunor_abl_abs" > nohup/ablation/abl_abs.out 2>&1 &
|
||||
nohup python cvae.py --name="lhunor_abl_abs_skirt" > nohup/ablation/abl_abs_skirt.out 2>&1 &
|
||||
nohup python cvae.py --name="lhunor_abl_skin" > nohup/ablation/abl_skin.out 2>&1 &
|
||||
nohup python cvae.py --name="lhunor_abl_skin_norm" > nohup/ablation/abl_skin_norm.out 2>&1 &
|
||||
nohup python cvae.py --name="lhunor_abl_skin_skirt" > nohup/ablation/abl_skin_skirt.out 2>&1 &
|
||||
nohup python cvae.py --name="lhunor_abl_all" > nohup/ablation/abl_all.out 2>&1 &
|
||||
nohup python cvae.py --name="lhunor_abl_all_skirt" > nohup/ablation/abl_all_skirt.out 2>&1 &
|
||||
nohup python cvae.py --name="lhunor_abl_orient" > nohup/ablation/abl_orient.out 2>&1 &
|
||||
nohup python cvae.py --name="lhunor_abl_orient_skirt" > nohup/ablation/abl_orient_skirt.out 2>&1 &
|
||||
nohup python cvae.py --name="lhunor_abl_one_hot_skirt" > nohup/ablation/abl_one_hot_skirt.out 2>&1 &
|
||||
nohup python cvae.py --name="lhunor_abl_norm" > nohup/ablation/abl_norm.out 2>&1 &
|
||||
nohup python cvae.py --name="lhunor_abl_10p" > nohup/ablation/abl_10p.out 2>&1 &
|
||||
nohup python cvae.py --name="lhunor_abl_25p" > nohup/ablation/abl_25p.out 2>&1 &
|
||||
nohup python cvae.py --name="lhunor_abl_10p_skin" > nohup/ablation/abl_10p_skin.out 2>&1 &
|
||||
nohup python cvae.py --name="lhunor_abl_25p_skin" > nohup/ablation/abl_25p_skin.out 2>&1 &
|
||||
nohup python cvae.py --name="lhunor_abl_50p_skin" > nohup/ablation/abl_50p_skin.out 2>&1 &
|
||||
|
||||
nohup python cvae.py --name="lhunor_abl_skin_var" > nohup/ablation/abl_skin_var.out 2>&1 &
|
||||
nohup python cvae.py --name="lhunor_abl_skin_var_2" > nohup/ablation/abl_skin_var_2.out 2>&1 &
|
||||
nohup python cvae.py --name="lhunor_abl_skin_var_3" > nohup/ablation/abl_skin_var_3.out 2>&1 &
|
||||
nohup python cvae.py --name="lhunor_abl_skin_var_4" > nohup/ablation/abl_skin_var_4.out 2>&1 &
|
||||
|
||||
nohup python cvae_curv.py --name="lhunor_cvae_curv" > nohup/ablation/cvae_curv.out 2>&1 &
|
||||
nohup python cvae_curv.py --name="lhunor_cvae_curv_2" > nohup/ablation/cvae_curv_2.out 2>&1 &
|
||||
|
||||
|
||||
abl_2_pyr_32_64_128
|
||||
abl_2_pyr_64_cape_f_03223_SS
|
||||
abl_2_pyr_32_64_128_256_512
|
||||
|
||||
nohup python cvae.py --name="lhunor_cape_f_03223_SL_2" > nohup/ablation/cape_f_03223_SL_2.out 2>&1 &
|
||||
nohup python cvae.py --name="lhunor_cape_f_03223_SS_2" > nohup/ablation/cape_f_03223_SS_2.out 2>&1 &
|
||||
nohup python cvae.py --name="lhunor_abl_all_post" > nohup/post/abl_all_post.out 2>&1 &
|
||||
|
||||
nohup python cvae_pyramid.py --name="lhunor_abl_2_pyr_32" > nohup/ablation_2/abl_2_pyr_32.out 2>&1 &
|
||||
nohup python cvae_pyramid.py --name="lhunor_abl_2_pyr_32_skin" > nohup/ablation_2/abl_2_pyr_32_skin.out 2>&1 &
|
||||
nohup python cvae_pyramid.py --name="lhunor_abl_2_pyr_32_skin_2" > nohup/ablation_2/abl_2_pyr_32_skin_2.out 2>&1 &
|
||||
nohup python cvae_pyramid.py --name="lhunor_abl_2_pyr_32_skin_norm" > nohup/ablation_2/abl_2_pyr_32_skin_norm.out 2>&1 &
|
||||
nohup python cvae_pyramid.py --name="lhunor_abl_2_pyr_32_64" > nohup/ablation_2/abl_2_pyr_32_64.out 2>&1 &
|
||||
nohup python cvae_pyramid.py --name="lhunor_abl_2_pyr_32_64_2" > nohup/ablation_2/abl_2_pyr_32_64_2.out 2>&1 &
|
||||
nohup python cvae_pyramid.py --name="lhunor_abl_2_pyr_32_64_128" > nohup/ablation_2/abl_2_pyr_32_64_128.out 2>&1 &
|
||||
nohup python cvae_pyramid.py --name="lhunor_abl_2_pyr_32_64_128_256" > nohup/ablation_2/abl_2_pyr_32_64_128_256.out 2>&1 &
|
||||
nohup python cvae_pyramid.py --name="lhunor_abl_2_pyr_32_64_128_256_512" > nohup/ablation_2/abl_2_pyr_32_64_128_256_512.out 2>&1 &
|
||||
nohup python cvae_pyramid.py --name="lhunor_abl_2_pyr_32_64_128_256_512_norm" > nohup/ablation_2/abl_2_pyr_32_64_128_256_512_norm.out 2>&1 &
|
||||
|
||||
nohup python cvae_pyramid.py --name="lhunor_abl_2_pyr_32_skirt" > nohup/ablation_2/abl_2_pyr_32_skirt.out 2>&1 &
|
||||
nohup python cvae_pyramid.py --name="lhunor_abl_2_pyr_32_skirt_extra_loss" > nohup/ablation_2/abl_2_pyr_32_skirt_extra_loss.out 2>&1 &
|
||||
nohup python cvae_pyramid.py --name="lhunor_abl_2_pyr_32_64_skirt" > nohup/ablation_2/abl_2_pyr_32_64_skirt.out 2>&1 &
|
||||
nohup python cvae_pyramid.py --name="lhunor_abl_2_pyr_32_64_128_skirt" > nohup/ablation_2/abl_2_pyr_32_64_128_skirt.out 2>&1 &
|
||||
nohup python cvae_pyramid.py --name="lhunor_abl_2_pyr_32_64_128_256_skirt" > nohup/ablation_2/abl_2_pyr_32_64_128_256_skirt.out 2>&1 &
|
||||
nohup python cvae_pyramid.py --name="lhunor_abl_2_pyr_32_64_128_256_512_skirt" > nohup/ablation_2/abl_2_pyr_32_64_128_256_512_skirt.out 2>&1 &
|
||||
|
||||
nohup python cvae_pyramid.py --name="lhunor_abl_2_pyr_64_cape_f" > nohup/ablation_2/abl_2_pyr_64_cape_f.out 2>&1 &
|
||||
nohup python cvae_pyramid.py --name="lhunor_abl_2_pyr_64_128_cape_f" > nohup/ablation_2/abl_2_pyr_64_128_cape_f.out 2>&1 &
|
||||
nohup python cvae_pyramid.py --name="lhunor_abl_2_pyr_64_128_256_cape_f" > nohup/ablation_2/abl_2_pyr_64_128_256_cape_f.out 2>&1 &
|
||||
nohup python cvae_pyramid.py --name="lhunor_abl_2_pyr_64_128_256_512_cape_f" > nohup/ablation_2/abl_2_pyr_64_128_256_512_cape_f.out 2>&1 &
|
||||
nohup python cvae_pyramid.py --name="lhunor_abl_2_pyr_64_cape_m" > nohup/ablation_2/abl_2_pyr_64_cape_m.out 2>&1 &
|
||||
nohup python cvae_pyramid.py --name="lhunor_abl_2_pyr_64_128_cape_m" > nohup/ablation_2/abl_2_pyr_64_128_cape_m.out 2>&1 &
|
||||
nohup python cvae_pyramid.py --name="lhunor_abl_2_pyr_64_128_256_cape_m" > nohup/ablation_2/abl_2_pyr_64_128_256_cape_m.out 2>&1 &
|
||||
nohup python cvae_pyramid.py --name="lhunor_abl_2_pyr_64_128_256_512_cape_m" > nohup/ablation_2/abl_2_pyr_64_128_256_512_cape_m.out 2>&1 &
|
||||
|
||||
nohup python cvae_pyramid.py --name="lhunor_abl_2_pyr_64_128_256_cape_m_00032_SL" > nohup/ablation_2/abl_2_pyr_64_128_256_cape_m_00032_SL.out 2>&1 &
|
||||
|
||||
abl_2_all_skirt
|
||||
abl_2_pyr_64_cape_m_00032_SL
|
||||
|
||||
python convert_to_uv.py -f '/home/workspace/data/dataset/validation' -s 0 -e 150 -n "lhunor"
|
||||
python convert_to_uv.py -f '/home/workspace/data/dataset/skirt_test' -s 0 -e 1 -n "lhunor"
|
||||
|
||||
cp configs/config_abl_all.py configs/config_abl_abs.py
|
||||
|
||||
|
||||
python merge_data.py -fi '/home/workspace/data/dataset/test' -fo '/home/workspace/data/dataset/test_ready' -s 0 -e 1500
|
||||
python merge_data.py -fi '/home/workspace/data/dataset/valid_skirt' -fo '/home/workspace/local-data/valid_skirt' -s 0 -e 1500
|
||||
|
||||
nohup python upscale_test.py > nohup/u.out 2>&1 &
|
||||
nohup python unpose_one_hot.py > nohup/unpose_one_hot_train_skirt.out 2>&1 &
|
||||
nohup python preprocessing.py > nohup/unshape_one_hot_test_skirt.out 2>&1 &
|
||||
nohup python dataset.py > nohup/avg_skirt.out 2>&1 &
|
||||
nohup python evaluate_ae_support.py > nohup/evaluate_ae_support.out 2>&1 &
|
||||
nohup python evaluate_cape.py --name evaluate_abl_pyr_64_128_256_512_cape_f > nohup/evaluate_abl_pyr_64_128_256_512_cape_f.out 2>&1 &
|
||||
nohup python evaluate_ae_pyramid.py --name evaluate_ae_abl_pyr_32_64_110k > nohup/evaluate_ae_abl_pyr_32_64_110k.out 2>&1 &
|
||||
nohup python evaluate_ae_pyramid.py --name evaluate_ae_abl_pyr_32_64_2_50k > nohup/evaluate_ae_abl_pyr_32_64_2_50k.out 2>&1 &
|
||||
nohup python evaluate_ae_pyramid.py --name evaluate_ae_abl_pyr_32_skirt > nohup/evaluate_ae_abl_pyr_32_skirt.out 2>&1 &
|
||||
nohup python evaluate_ae.py --name abl_norm_skirt_70k > nohup/evaluate/abl_norm_skirt_70k.out 2>&1 &
|
||||
nohup python calculate_error.py --name error_abl_2_pyr_32_64_128_skirt > nohup/error_ae_abl_skin_skirt_70k.out 2>&1 &
|
||||
|
||||
nohup python evaluate_ae_pyramid.py --name abl_2_pyr_32_64_100k > nohup/evaluate/abl_2_pyr_32_64_100k.out 2>&1 &
|
||||
nohup python evaluate_ae_pyramid.py --name abl_2_pyr_32_64_128_80k > nohup/evaluate/abl_2_pyr_32_64_128_80k.out 2>&1 &
|
||||
nohup python evaluate_ae_pyramid.py --name abl_2_pyr_32_64_128_256_512_skirt_50k > nohup/evaluate/abl_2_pyr_32_64_128_256_512_skirt_50k.out 2>&1 &
|
||||
|
||||
nohup python calculate_error.py --name abl_2_pyr_32_64_128_256_512_50k > nohup/error/abl_2_pyr_32_64_128_256_512_50k.out 2>&1 &
|
||||
|
||||
nohup 7z x CAPE_dataset.zip.001 > nohup/unzip.out 2>&1 &
|
||||
|
||||
nohup python main.py --config configs/CAPE-affineconv_nz18_pose24_clotype8_male.yaml --name CAPE-affineconv_nz18_pose24_clotype8_male --gender male --mode demo > cape_male.out 2>&1 &
|
||||
nohup python3 main.py --config configs/CAPE-affineconv_nz18_pose24_clotype8_female.yaml --name CAPE-affineconv_nz18_pose24_clotype8_female --gender female --mode demo > cape_female.out 2>&1 &
|
||||
|
||||
nohup python curvature_labels.py > nohup/dijkstra_skirt.out 2>&1 &
|
||||
nohup python downscale.py > nohup/downscale_2_test_skirt.out 2>&1 &
|
||||
nohup python downscale_cape.py > nohup/downscale_cape_train_m.out 2>&1 &
|
||||
nohup python merge_data.py -fi /home/workspace/data/dataset/train -fo /home/workspace/local-data/train -s 0 -e 1500 > nohup/merge_data_valid_skirt.out 2>&1 &
|
||||
nohup python merge_data.py -fi /home/workspace/data/dataset/test_skirt -fo /home/workspace/data/dataset/test_skirt_ready -s 0 -e 1500 > nohup/merge_data_test_skirt_ready.out 2>&1 &
|
||||
|
||||
nohup python unpose_skirt.py -f /home/workspace/data/dataset/train_skirt -s 0 -e 100 -n lhunor_unpose_skirt_0_100 > nohup/unpose_skirt_0_100.out 2>&1 &
|
||||
nohup python unpose_skirt.py -f /home/workspace/data/dataset/train_skirt -s 100 -e 200 -n lhunor_unpose_skirt_100_200 > nohup/unpose_skirt_100_200.out 2>&1 &
|
||||
nohup python unpose_skirt.py -f /home/workspace/data/dataset/train_skirt -s 200 -e 300 -n lhunor_unpose_skirt_200_300 > nohup/unpose_skirt_200_300.out 2>&1 &
|
||||
nohup python unpose_skirt.py -f /home/workspace/data/dataset/train_skirt -s 300 -e 400 -n lhunor_unpose_skirt_300_400 > nohup/unpose_skirt_300_400.out 2>&1 &
|
||||
nohup python unpose_skirt.py -f /home/workspace/data/dataset/train_skirt -s 400 -e 500 -n lhunor_unpose_skirt_400_500 > nohup/unpose_skirt_400_500.out 2>&1 &
|
||||
nohup python unpose_skirt.py -f /home/workspace/data/dataset/train_skirt -s 500 -e 600 -n lhunor_unpose_skirt_500_600 > nohup/unpose_skirt_500_600.out 2>&1 &
|
||||
nohup python unpose_skirt.py -f /home/workspace/data/dataset/train_skirt -s 600 -e 700 -n lhunor_unpose_skirt_600_700 > nohup/unpose_skirt_600_700.out 2>&1 &
|
||||
nohup python unpose_skirt.py -f /home/workspace/data/dataset/train_skirt -s 700 -e 800 -n lhunor_unpose_skirt_700_800 > nohup/unpose_skirt_700_800.out 2>&1 &
|
||||
nohup python unpose_skirt.py -f /home/workspace/data/dataset/test_skirt -s 0 -e 100 -n lhunor_unpose_test_skirt_0_100 > nohup/unpose_test_skirt_0_100_2.out 2>&1 &
|
||||
nohup python unpose_skirt.py -f /home/workspace/data/dataset/test_skirt -s 100 -e 200 -n lhunor_unpose_test_skirt_100_200 > nohup/unpose_test_skirt_100_200_2.out 2>&1 &
|
||||
nohup python unpose_skirt.py -f /home/workspace/data/dataset/cloth3d_skirt -s 0 -e 100 -n lhunor_unpose_extra_skirt_0_100 > nohup/unpose_extra_skirt_0_100.out 2>&1 &
|
||||
nohup python unpose_skirt.py -f /home/workspace/data/dataset/cloth3d_skirt -s 100 -e 200 -n lhunor_unpose_extra_skirt_100_200 > nohup/unpose_extra_skirt_100_200.out 2>&1 &
|
||||
nohup python unpose_skirt.py -f /home/workspace/data/dataset/cloth3d_skirt -s 200 -e 300 -n lhunor_unpose_extra_skirt_200_300 > nohup/unpose_extra_skirt_200_300_2.out 2>&1 &
|
||||
nohup python unpose_skirt.py -f /home/workspace/data/dataset/cloth3d_skirt -s 300 -e 400 -n lhunor_unpose_extra_skirt_300_400 > nohup/unpose_extra_skirt_300_400.out 2>&1 &
|
||||
nohup python unpose_skirt.py -f /home/workspace/data/dataset/test -s 0 -e 100 -n lhunor_unpose_test_0_100 > nohup/unpose_test_0_100.out 2>&1 &
|
||||
nohup python unpose_skirt.py -f /home/workspace/data/dataset/test -s 100 -e 200 -n lhunor_unpose_test_100_200 > nohup/unpose_test_100_200.out 2>&1 &
|
||||
nohup python unpose_skirt.py -f /home/workspace/data/dataset/test -s 200 -e 300 -n lhunor_unpose_test_200_300 > nohup/unpose_test_200_300.out 2>&1 &
|
||||
nohup python unpose_skirt.py -f /home/workspace/data/dataset/test -s 300 -e 400 -n lhunor_unpose_test_300_400 > nohup/unpose_test_300_400.out 2>&1 &
|
||||
nohup python unpose_skirt.py -f /home/workspace/data/dataset/test -s 00 -e 00 -n lhunor_unpose_test_00_00 > nohup/unpose_test_00_00.out 2>&1 &
|
||||
|
||||
|
||||
calculate avg garment for skirt
|
||||
need dijkstra/dijsktra skirt
|
||||
bodies have to be converted in non-skirt mode
|
||||
need to pretrain encoders again...
|
||||
not enough sapce to preprocess data
|
||||
|
||||
add one more layer and train, repeat
|
||||
|
||||
curvature binning
|
||||
do it according to trainingn set distribution for validation, or it's own for validation
|
||||
merge curvatures for validation from data-net to local
|
||||
avg garment for big datasets
|
||||
check ranges of curvatur ranges
|
||||
|
||||
collision in pecentage
|
||||
bend loss?
|
||||
evaluation pipeline
|
||||
look tailernot dataset
|
||||
blender for visualization
|
||||
|
||||
|
||||
gpu needed estimation
|
||||
let's say if we want to finish in on eweek
|
||||
|
||||
we use the same skinning weights for skirts. okay?
|
||||
|
||||
|
||||
redo curvatures for skirt train.valid
|
||||
train_skirt: array([1.83511008e-06, 1.84299448e-03, 3.38148023e-03, 5.67459036e-03, 1.02263279e-02, 2.21962575e-02, 3.24614763e-01])
|
||||
array([1.83511008e-06, 1.82755420e-03, 3.35242413e-03, 5.61911613e-03, 1.01151643e-02, 2.20824350e-02, 3.25994939e-01])
|
||||
valid_skirt: array([4.51388405e-06, 1.90253550e-03, 3.44673195e-03, 5.73266158e-03, 1.02412868e-02, 2.22220197e-02, 3.12285781e-01])
|
||||
array([4.51388405e-06, 1.88061886e-03, 3.40514188e-03, 5.64374123e-03, 1.00161384e-02, 2.18187869e-02, 3.17445695e-01])
|
||||
test_skirt: array([7.21150764e-06, 1.77989923e-03, 3.26598203e-03, 5.47702867e-03, 9.79944225e-03, 2.07518619e-02, 3.23069602e-01])
|
||||
|
||||
how to include curvature in evaluation?
|
||||
use gt, predict with vae?
|
||||
|
||||
|
||||
docker run -d --rm -p 61208-61209:61208-61209 -e GLANCES_OPT="-w" -v /var/run/docker.sock:/var/run/docker.sock:ro --pid host nicolargo/glances:alpine-dev
|
||||
|
||||
|
||||
+3
-3
@@ -1,6 +1,6 @@
|
||||
import os
|
||||
import sys
|
||||
from configs.config_abl_all_post import config
|
||||
from configs.config_abl_pyr_32 import config
|
||||
|
||||
os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
|
||||
# import tensorflow as tf
|
||||
@@ -59,13 +59,13 @@ if __name__ == '__main__':
|
||||
folder = config['test_dir']
|
||||
|
||||
checkpoint_name = config['name']
|
||||
iteration = ''
|
||||
iteration = '200000'
|
||||
|
||||
F = np.load("custom_utils/smpl_faces" + skirt_modifier + ".npy").astype(np.int32)
|
||||
garment_type_table = np.load('custom_data/garment_type_table_test.npy', allow_pickle=True).item()
|
||||
|
||||
|
||||
output_folder = '/home/workspace/data/results/post/' + checkpoint_name + '-' + iteration
|
||||
output_folder = '/home/workspace/data/results/' + checkpoint_name + '-' + iteration
|
||||
|
||||
|
||||
faces_folder = '/home/workspace/data/results/support/faces' + ('_skirt' if config['is_skirt'] else '')
|
||||
|
||||
@@ -1,8 +1,9 @@
|
||||
config = dict()
|
||||
|
||||
config['gpu'] = '0'
|
||||
config['name'] = 'pyr_abl_32'
|
||||
config['name'] = 'pyr_abl_32_64_e2e_r3_fine_2'
|
||||
config['notes'] = ''
|
||||
config['tags'] = ['review_3']
|
||||
|
||||
# DON'T FORGET TO RESET SSIM LOSS USAGE
|
||||
# DON'T FORGET TO CHECK MODEL LOADING
|
||||
@@ -21,9 +22,12 @@ config['use_offsets'] = False
|
||||
|
||||
|
||||
config['pyramid'] = dict()
|
||||
config['pyramid']['resolutions'] = [32]
|
||||
config['pyramid']['resolutions'] = [32, 64]
|
||||
config['pyramid']['pretrained_pyramid'] = ''
|
||||
config['pyramid']['final_upscale_enhancer'] = 'checkpoints/32_512_4'
|
||||
config['pyramid']['final_upscale_enhancer'] = 'checkpoints/64_512_2'
|
||||
|
||||
config['pretrained_model'] = 'checkpoints/pyr_abl_32_64_e2e_r3_fine'
|
||||
config['pretrained_model_iteration'] = ''
|
||||
|
||||
config['train_dir'] = '/home/workspace/local-data/train'
|
||||
config['valid_dir'] = '/home/workspace/local-data/valid'
|
||||
@@ -40,7 +44,7 @@ config['smpl_res'] = 14475
|
||||
if config['is_cape']:
|
||||
config['smpl_res'] = 3638
|
||||
|
||||
config['lr'] = 0.0001
|
||||
config['lr'] = 0.00001
|
||||
config['starting_balancing_coeff'] = 0.0001
|
||||
config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
|
||||
config['avg_garment_path'] = ''
|
||||
@@ -64,7 +68,7 @@ config['pyramid']['latent_dim'] = config['latent_dim']
|
||||
config['pyramid']['add_noise'] = True
|
||||
config['pyramid']['noise_amount'] = 0.025
|
||||
|
||||
config['pyramid']['loss_weights'] = [1,1,1,1,1]
|
||||
config['pyramid']['loss_weights'] = [2,1,1,1,1]
|
||||
|
||||
for res in config['pyramid']['resolutions']:
|
||||
if res != 512:
|
||||
@@ -149,7 +153,7 @@ for res in config['pyramid']['resolutions']:
|
||||
level['decoder_depths'] = [9, 9]
|
||||
level['decoder_dims'] = [256, 256]
|
||||
level['avg_garment_path'] = ''
|
||||
level['upscale_enhancer'] = ''#'checkpoints/up_3_d32_64_2'
|
||||
level['upscale_enhancer'] = 'checkpoints/32_512_4'#'checkpoints/up_3_d32_64_2'
|
||||
level['upscale_enhancer_freeze'] = True
|
||||
config['pyramid']['levels'].append(level)
|
||||
else:
|
||||
|
||||
@@ -1,8 +1,8 @@
|
||||
config = dict()
|
||||
|
||||
config['gpu'] = '3'
|
||||
config['name'] = 'pyr_abl_32_skirt_2'
|
||||
config['notes'] = 'continued from pyr_abl_32_skirt-180k'
|
||||
config['name'] = 'pyr_abl_32_skirt_r1'
|
||||
config['notes'] = ''
|
||||
|
||||
# DON'T FORGET TO RESET SSIM LOSS USAGE
|
||||
# DON'T FORGET TO CHECK MODEL LOADING
|
||||
@@ -24,7 +24,10 @@ config['pyramid']['resolutions'] = [32]
|
||||
config['pyramid']['pretrained_pyramid'] = ''
|
||||
config['pyramid']['final_upscale_enhancer'] = 'checkpoints/32_512_skirt'
|
||||
|
||||
config['train_dir'] = '/home/workspace/local-data/train_skirt'
|
||||
config['pretrained_model'] = ''
|
||||
config['pretrained_model_iteration'] = ''
|
||||
|
||||
config['train_dir'] = '/home/workspace/data/dataset/local-cache/train_skirt'
|
||||
config['valid_dir'] = '/home/workspace/local-data/valid_skirt'
|
||||
config['test_dir'] = '/home/workspace/data/dataset/test_skirt_ready_2'
|
||||
config['batch_size'] = 4
|
||||
@@ -35,7 +38,7 @@ config['pyramid']['static_model'] = 'checkpoints/static_1_skirt'
|
||||
config['pyramid']['body_model'] = 'checkpoints/body_1_skirt_2_2'
|
||||
config['pyramid']['curvature_model'] = 'checkpoints/curv_1_skirt'
|
||||
|
||||
config['dataset_in_memory'] = False
|
||||
config['dataset_in_memory'] = True
|
||||
config['resolution'] = None
|
||||
config['latent_dim'] = 128
|
||||
|
||||
@@ -65,6 +68,7 @@ config['signature_static'] = { 'uv_static': (512, 256, 3),
|
||||
config['pyramid']['is_label'] = False
|
||||
config['pyramid']['latent_dim'] = config['latent_dim']
|
||||
config['pyramid']['add_noise'] = True
|
||||
config['pyramid']['noise_amount'] = 0.001
|
||||
|
||||
config['pyramid']['loss_weights'] = [1,1,1,1,1]
|
||||
|
||||
|
||||
@@ -45,7 +45,7 @@ class UV2Mesh(tf.keras.Model):
|
||||
if uv.shape[1] == 3:
|
||||
uv = tf.transpose(uv, [0,2,3,1])
|
||||
if uv.shape[1] != 512:
|
||||
uv = tf.image.resize(uv, (512, 256), tf.image.ResizeMethod.LANCZOS5)
|
||||
uv = tf.image.resize(uv, (512, 256), tf.image.ResizeMethod.BILINEAR)
|
||||
|
||||
batch_size = uv.shape[0]
|
||||
|
||||
|
||||
+50
-38
@@ -1,6 +1,6 @@
|
||||
import os
|
||||
import sys
|
||||
from configs.post.config_abl_pyr_64_128_5 import config
|
||||
from configs.config_abl_pyr_32 import config
|
||||
|
||||
os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
|
||||
import tensorflow as tf
|
||||
@@ -41,7 +41,7 @@ from losses import collision_loss as collision_penalty
|
||||
from custom_utils.custom_utils import batch_to_dict, load_model
|
||||
from dataset import DatasetFactory, StaticDataset
|
||||
from custom_utils.smpl import SMPL
|
||||
from models.pyramid_model_optimized import PyramidNew as Pyramid
|
||||
from models.pyramid_model_optimized import Pyramid
|
||||
from postprocessing import fix_collision
|
||||
|
||||
|
||||
@@ -59,9 +59,11 @@ def init_wandb():
|
||||
artifact.add_file('models/cond_encoder.py')
|
||||
artifact.add_file('dataset.py')
|
||||
artifact.add_file('convnext/models/convnext_tf.py')
|
||||
config_file_names = [key for key in sys.modules.keys() if key.startswith('configs.post.')]
|
||||
config_file_names = [key for key in sys.modules.keys() if key.startswith('configs')]
|
||||
for config_file_name in config_file_names:
|
||||
artifact.add_file('/'.join(config_file_name.split('.')) + '.py')
|
||||
file_name = '/'.join(config_file_name.split('.')) + '.py'
|
||||
if os.path.exists(file_name):
|
||||
artifact.add_file(file_name)
|
||||
run.log_artifact(artifact)
|
||||
|
||||
uv2mesh = UV2Mesh(res=256, is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape'])
|
||||
@@ -215,19 +217,23 @@ def train_step(batch):
|
||||
with tf.GradientTape() as tape:
|
||||
out_levels = model([levels_input, conds], training=True)
|
||||
|
||||
if config['use_skinning']:
|
||||
mesh_orig, uv_orig = batch['mesh_unposed'], batch['uv_unposed']
|
||||
else:
|
||||
mesh_orig, uv_orig = batch['mesh_posed'], batch['uv_posed']
|
||||
|
||||
output = dict()
|
||||
reconstr_loss_total = 0
|
||||
kl_total = 0
|
||||
|
||||
#for i, res in enumerate(config['pyramid']['resolutions']):
|
||||
i = -1
|
||||
res = config['pyramid']['resolutions'][-1]
|
||||
res_modifier = '_' + str(res) if res != 512 else ''
|
||||
for i, res in enumerate(config['pyramid']['resolutions']):
|
||||
# i = -1
|
||||
# res = config['pyramid']['resolutions'][-1]
|
||||
if res != 512:
|
||||
if i == len(config['pyramid']['resolutions']) - 1:
|
||||
res_modifier = ''
|
||||
else:
|
||||
res_modifier = '_' + str(res)
|
||||
else:
|
||||
res_modifier = ''
|
||||
|
||||
pred, mean, logvar = out_levels[i]
|
||||
|
||||
mesh_pred = uv2mesh(pred)
|
||||
@@ -247,7 +253,7 @@ def train_step(batch):
|
||||
e_loss = tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask']))
|
||||
c_loss, c_ratio = collision_penalty(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask'])
|
||||
c_loss, c_ratio = tf.reduce_mean(c_loss), tf.reduce_mean(c_ratio)
|
||||
l2_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(((uv_orig - pred) ** 2), axis=-1), axis=[1, 2]))
|
||||
l2_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(((batch['uv_unposed' + res_modifier] - pred) ** 2), axis=-1), axis=[1, 2]))
|
||||
# ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(pred + 5, batch['uv_unposed'] + 5, max_val=10, power_factors=(0.5, 0.2, 0.1, 0.1, 0.1)))
|
||||
# ms_ssim = tf.reduce_mean(tf.image.ssim(pred + 1, batch['uv_unposed'] + 1, max_val=3))
|
||||
l2_mesh_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (batch['mesh_posed'] - mesh_pred_posed) ** 2, axis=-1), axis=-1))
|
||||
@@ -261,8 +267,8 @@ def train_step(batch):
|
||||
else:
|
||||
reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss)
|
||||
|
||||
if config['use_norm_loss'] and step > 2000:
|
||||
reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff']
|
||||
# if config['use_norm_loss'] and step > 2000:
|
||||
# reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff']
|
||||
|
||||
kl_total += kl
|
||||
|
||||
@@ -288,20 +294,23 @@ def valid_step(batch):
|
||||
levels_input, conds = group_inputs_for_levels(batch, config)
|
||||
out_levels = model([levels_input, conds], training=False)
|
||||
|
||||
|
||||
if config['use_skinning']:
|
||||
mesh_orig, uv_orig = batch['mesh_unposed'], batch['uv_unposed']
|
||||
else:
|
||||
mesh_orig, uv_orig = batch['mesh_posed'], batch['uv_posed']
|
||||
|
||||
output = dict()
|
||||
reconstr_loss_total = 0
|
||||
kl_total = 0
|
||||
|
||||
#for i, res in enumerate(config['pyramid']['resolutions']):
|
||||
i = -1
|
||||
res = config['pyramid']['resolutions'][-1]
|
||||
res_modifier = '_' + str(res) if res != 512 else ''
|
||||
for i, res in enumerate(config['pyramid']['resolutions']):
|
||||
# i = -1
|
||||
# res = config['pyramid']['resolutions'][-1]
|
||||
if res != 512:
|
||||
if i == len(config['pyramid']['resolutions']) - 1:
|
||||
res_modifier = ''
|
||||
else:
|
||||
res_modifier = '_' + str(res)
|
||||
else:
|
||||
res_modifier = ''
|
||||
|
||||
pred, mean, logvar = out_levels[i]
|
||||
|
||||
mesh_pred = uv2mesh(pred)
|
||||
@@ -320,7 +329,7 @@ def valid_step(batch):
|
||||
e_loss = tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask']))
|
||||
c_loss, c_ratio = collision_penalty(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask'])
|
||||
c_loss, c_ratio = tf.reduce_mean(c_loss), tf.reduce_mean(c_ratio)
|
||||
l2_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(((uv_orig - pred) ** 2), axis=-1), axis=[1, 2]))
|
||||
l2_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(((batch['uv_unposed' + res_modifier] - pred) ** 2), axis=-1), axis=[1, 2]))
|
||||
# ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(pred + 5, batch['uv_unposed'] + 5, max_val=10, power_factors=(0.5, 0.2, 0.1, 0.1, 0.1)))
|
||||
# ms_ssim = tf.reduce_mean(tf.image.ssim(pred + 1, batch['uv_unposed'] + 1, max_val=3))
|
||||
l2_mesh_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (batch['mesh_posed'] - mesh_pred_posed) ** 2, axis=-1), axis=-1))
|
||||
@@ -334,8 +343,8 @@ def valid_step(batch):
|
||||
else:
|
||||
reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss)
|
||||
|
||||
if config['use_norm_loss'] and step > 2000:
|
||||
reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff']
|
||||
# if config['use_norm_loss'] and step > 2000:
|
||||
# reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff']
|
||||
|
||||
kl_total += kl
|
||||
|
||||
@@ -790,7 +799,7 @@ if __name__ == '__main__':
|
||||
# generate_results()
|
||||
|
||||
ckpt = tf.train.Checkpoint(model=model)
|
||||
manager = tf.train.CheckpointManager(ckpt, 'checkpoints/post/' + config['name'], max_to_keep=20)
|
||||
manager = tf.train.CheckpointManager(ckpt, 'checkpoints/' + config['name'], max_to_keep=20)
|
||||
|
||||
# load_model(model, 'checkpoints/pyr_abl_32_skirt', iteration='180000')
|
||||
|
||||
@@ -798,30 +807,33 @@ if __name__ == '__main__':
|
||||
# assert len(config['pyramid']['resolutions']) == 1
|
||||
load_model(model, config['pretrained_model'], iteration=config['pretrained_model_iteration'])
|
||||
|
||||
if len(config['pyramid']['resolutions']) == 1:
|
||||
model.static_enc.trainable = False
|
||||
model.body_enc.trainable = False
|
||||
model.curv_enc.trainable = False
|
||||
else:
|
||||
load_model(model, config['pyramid']['pretrained_pyramid'], iteration=(config['pyramid']['pretrained_pyramid_iteration'] if 'pretrained_pyramid_iteration' in config.keys() else ''))
|
||||
model.static_enc.trainable = False
|
||||
model.body_enc.trainable = False
|
||||
model.curv_enc.trainable = False
|
||||
|
||||
# model.trainable = False
|
||||
# model.cond_encoder_2.trainable = True
|
||||
# if len(config['pyramid']['resolutions']) == 1:
|
||||
# else:
|
||||
# load_model(model, config['pyramid']['pretrained_pyramid'], iteration=(config['pyramid']['pretrained_pyramid_iteration'] if 'pretrained_pyramid_iteration' in config.keys() else ''))
|
||||
# model.static_enc.trainable = False
|
||||
# model.body_enc.trainable = False
|
||||
# model.curv_enc.trainable = False
|
||||
# model.cond_encoder.trainable = False
|
||||
|
||||
# load_model(model.levels[0].upscale_enhancer, config['pyramid']['levels'][0]['upscale_enhancer'])
|
||||
# model.levels[0].upscale_enhancer.trainable = False
|
||||
|
||||
|
||||
for i in range(len(model.levels)):
|
||||
for i in range(len(model.levels)-1):
|
||||
load_model(model.levels[i].upscale_enhancer, config['pyramid']['levels'][i]['upscale_enhancer'])
|
||||
model.levels[i].upscale_enhancer.trainable = False
|
||||
# if config['pyramid']['resolutions'][-1] != 512:
|
||||
# load_model(model.upscale_enhancer, config['pyramid']['final_upscale_enhancer'])
|
||||
# model.upscale_enhancer.trainable = False
|
||||
if config['pyramid']['resolutions'][-1] != 512:
|
||||
load_model(model.upscale_enhancer, config['pyramid']['final_upscale_enhancer'])
|
||||
model.upscale_enhancer.trainable = False
|
||||
|
||||
for i in range(len(model.levels)-1):
|
||||
model.levels[i].trainable = False
|
||||
# for i in range(len(model.levels)-1):
|
||||
# model.levels[i].trainable = False
|
||||
|
||||
# load_model(model.cond_encoder, config['pyramid']['pretrained_pyramid'])
|
||||
# load_model(model.levels[0], config['pyramid']['pretrained_pyramid'])
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
import os
|
||||
import sys
|
||||
from configs.config_abl_2_pyr_32_64_128_256_512 import config
|
||||
from configs.config_abl_pyr_32 import config
|
||||
|
||||
os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
|
||||
import tensorflow as tf
|
||||
@@ -97,7 +97,7 @@ if __name__ == '__main__':
|
||||
ids = [id.split('_')[0] for id in ids]
|
||||
ids = set(ids)
|
||||
|
||||
iteration = '50000'
|
||||
iteration = '200000'
|
||||
|
||||
load_model(model, 'checkpoints/' + checkpoint_name, iteration=iteration)
|
||||
# load_model(model, 'checkpoints/' + 'abl_all_120k')
|
||||
|
||||
@@ -43,7 +43,7 @@ class CVAE(tf.keras.Model):
|
||||
self.cond_encoder = tf.keras.Sequential([tf.keras.layers.Dense(512, activation='relu'),
|
||||
tf.keras.layers.Dense(256, activation='relu'),
|
||||
tf.keras.layers.Dense(128, activation='relu'),
|
||||
tf.keras.layers.Lambda(lambda x: x / 1000),
|
||||
# tf.keras.layers.Lambda(lambda x: x / 1000),
|
||||
tf.keras.layers.Dense(config['latent_dim'], activation='tanh')])
|
||||
|
||||
self.encoder = VariationalEncoder(config['cvae']['latent_dim'], config['cvae']['encoder_depths'], config['cvae']['encoder_dims'], kernel_size=config['cvae']['kernel_size'])
|
||||
|
||||
@@ -92,7 +92,7 @@ class PyramidLevel(tf.keras.Model):
|
||||
|
||||
# x = x * uv_mask_high[:,:,:,tf.newaxis]
|
||||
|
||||
return x, mean, logvar
|
||||
return x, z, mean, logvar
|
||||
|
||||
|
||||
|
||||
|
||||
@@ -78,6 +78,11 @@ class Pyramid(tf.keras.Model):
|
||||
load_model(self.upscale_enhancer, config['pyramid']['final_upscale_enhancer'])
|
||||
self.upscale_enhancer.trainable = False
|
||||
|
||||
self.cond_encoder_2 = tf.keras.Sequential([tf.keras.layers.Dense(512, activation='relu'),
|
||||
tf.keras.layers.Dense(256, activation='relu'),
|
||||
tf.keras.layers.Dense(128, activation='relu'),
|
||||
tf.keras.layers.Dense(config['pyramid']['latent_dim'], activation='tanh'),])
|
||||
|
||||
def enhance(self, low, mask, training):
|
||||
x = self.upscale_enhancer([low, mask], training=training)
|
||||
return x
|
||||
@@ -90,44 +95,54 @@ class Pyramid(tf.keras.Model):
|
||||
z_cond = tf.concat([z_static, z_body, z_curv], axis=-1)
|
||||
z_cond = self.cond_encoder(z_cond, training=training)
|
||||
|
||||
return z_cond, z_static, z_body, z_curv
|
||||
|
||||
def encode_conds_2(self, z, z_static, z_body, z_curv, training):
|
||||
z_cond = tf.concat([z, z_static, z_body, z_curv], axis=-1)
|
||||
z_cond = self.cond_encoder_2(z_cond, training=training)
|
||||
|
||||
return z_cond
|
||||
|
||||
def call(self, inputs, training):
|
||||
levels_input, conds = inputs
|
||||
uv_static, uv_body, uv_curv = conds[0], conds[1], conds[2]
|
||||
|
||||
z_cond = self.encode_conds(uv_static, uv_body, uv_curv, training)
|
||||
z_cond, z_static, z_body, z_curv = self.encode_conds(uv_static, uv_body, uv_curv, training)
|
||||
|
||||
if self.add_noise == True and training == True:
|
||||
z_cond = z_cond + (tf.random.uniform(z_cond.shape, maxval=self.noise_amount * 2) - self.noise_amount)
|
||||
|
||||
out_levels = []
|
||||
pred, mean, logvar = self.levels[0](levels_input[0], z_cond, training=training)
|
||||
pred, z, mean, logvar = self.levels[0](levels_input[0], z_cond, training=training)
|
||||
if self.use_offsets:
|
||||
pred = pred + levels_input[0][2] # uv_body_posed_32
|
||||
if 1 != len(self.levels):
|
||||
pred = self.levels[0].enhance(pred, levels_input[0][-2], training=training) # levels_input[i][-2]=uv_mask_res
|
||||
pred = tf.image.resize(pred, (self.levels[1].size, self.levels[1].size//2), tf.image.ResizeMethod.LANCZOS5)
|
||||
out_levels.append([pred, mean, logvar])
|
||||
pred = tf.image.resize(pred, (self.levels[1].size, self.levels[1].size//2), tf.image.ResizeMethod.BILINEAR)
|
||||
pred = pred * levels_input[1][-2][:,:,:,tf.newaxis]
|
||||
else:
|
||||
pred = self.enhance(pred, levels_input[0][-2], training=training)
|
||||
pred = tf.image.resize(pred, (512, 256), tf.image.ResizeMethod.LANCZOS5)
|
||||
pred = tf.image.resize(pred, (512, 256), tf.image.ResizeMethod.BILINEAR)
|
||||
pred = pred * levels_input[-1][-1][:,:,:,tf.newaxis] # full res uv mask
|
||||
out_levels.append([pred, mean, logvar])
|
||||
|
||||
for i in range(1, len(self.levels)):
|
||||
pred_level, mean, logvar = self.levels[i](levels_input[i], z_cond, training=training)
|
||||
input = levels_input[i]
|
||||
input[0] = pred # use previous level output as input for next level
|
||||
z_cond_2 = self.encode_conds_2(z, z_static, z_body, z_curv, training=training)
|
||||
|
||||
pred_level, z, mean, logvar = self.levels[i](input, z_cond_2, training=training)
|
||||
pred = pred + pred_level
|
||||
if i != len(self.levels) - 1:
|
||||
pred = self.levels[i].enhance(pred, levels_input[i][-2], training=training)
|
||||
out_levels.append([pred, mean, logvar])
|
||||
pred = tf.image.resize(pred, (self.levels[i+1].size, self.levels[i+1].size//2), tf.image.ResizeMethod.LANCZOS5)
|
||||
pred = tf.image.resize(pred, (self.levels[i+1].size, self.levels[i+1].size//2), tf.image.ResizeMethod.BILINEAR)
|
||||
pred = pred * levels_input[i+1][-2][:,:,:,tf.newaxis]
|
||||
else:
|
||||
if self.upscale_enhancer is not None:
|
||||
pred = self.enhance(pred, levels_input[-1][-2], training=training)
|
||||
pred = tf.image.resize(pred, (512, 256), tf.image.ResizeMethod.LANCZOS5)
|
||||
pred = tf.image.resize(pred, (512, 256), tf.image.ResizeMethod.BILINEAR)
|
||||
pred = pred * levels_input[-1][-1][:,:,:,tf.newaxis] # full res uv mask
|
||||
out_levels.append([pred, mean, logvar])
|
||||
|
||||
|
||||
Reference in New Issue
Block a user