Compare commits
10
Commits
7470ca9fb6
...
new_model
| Author | SHA1 | Date | |
|---|---|---|---|
 luni
|
0912b9f390 | ||
|
luni
|
ac27319860 | ||
|
luni
|
2100d364f9 | ||
|
luni
|
be78b02bad | ||
|
luni
|
ebbc52d0fd | ||
|
luni
|
33eff16c8c | ||
|
luni
|
61a609c8f7 | ||
|
luni
|
8fbd075f92 | ||
|
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
|
||||
+217
@@ -0,0 +1,217 @@
|
||||
nohup python cvae.py --name="lhunor_weights_test_6" > nohup/iccv/weights_test_6.out 2>&1 &
|
||||
nohup python evaluate_ae.py --name iccv_weights_test_6 > nohup/iccv/evaluate_iccv_weights_test_6.out 2>&1 &
|
||||
nohup python calculate_error.py --name iccv_weights_test_6 > nohup/iccv/error_iccv_weights_test_6.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
|
||||
|
||||
|
||||
@@ -0,0 +1,188 @@
|
||||
import os
|
||||
import sys
|
||||
from configs.config_abl_all_post import config as config_a
|
||||
|
||||
os.environ["CUDA_VISIBLE_DEVICES"] = '5'
|
||||
import tensorflow as tf
|
||||
|
||||
gpus = tf.config.experimental.list_physical_devices('GPU')
|
||||
if gpus:
|
||||
try:
|
||||
# Currently, memory growth needs to be the same across GPUs
|
||||
for gpu in gpus:
|
||||
tf.config.experimental.set_memory_growth(gpu, True)
|
||||
logical_gpus = tf.config.experimental.list_logical_devices('GPU')
|
||||
print(len(gpus), "Physical GPUs,", len(logical_gpus), "Logical GPUs")
|
||||
except RuntimeError as e:
|
||||
# Memory growth must be set before GPUs have been initialized
|
||||
print(e)
|
||||
|
||||
import glob
|
||||
import time
|
||||
import argparse
|
||||
import wandb
|
||||
import tqdm
|
||||
import random
|
||||
import numpy as np
|
||||
import plotly.graph_objects as go
|
||||
import plotly.express as ex
|
||||
from PIL import Image
|
||||
from postprocessing import fix_collision
|
||||
|
||||
if config_a['is_skirt']:
|
||||
from losses import edge_loss_skirt as edge_loss
|
||||
else:
|
||||
from losses import edge_loss
|
||||
|
||||
|
||||
|
||||
from losses import collision_ratio, kl_loss #, concept_loss
|
||||
# from losses import collision_penalty as collision_penalty
|
||||
from losses import collision_loss as collision_penalty
|
||||
from custom_utils.custom_utils import batch_to_dict, load_model, plot_3d, UV2Mesh, get_summary_html, maskFacesBatch, _maskFaces, plot_3d_collision
|
||||
from dataset import DatasetFactory, StaticDataset
|
||||
from custom_utils.smpl import SMPL
|
||||
from models.cvae_model import CVAE
|
||||
from custom_utils.supersmpl_io import writeOBJ
|
||||
from plotly.subplots import make_subplots
|
||||
|
||||
|
||||
# uv2mesh = UV2Mesh(res=256, is_skirt=config_a['is_skirt'], is_adaptive=False)
|
||||
|
||||
|
||||
|
||||
def plot(mesh_gt, pred_a, pred_b, body, mask):
|
||||
fig = make_subplots(rows=1, cols=3, start_cell="top-left", specs = [ [{ 'type': 'scene' } for _ in range(3)] ])
|
||||
|
||||
_, faces_garment = _maskFaces(np.zeros((14475, 3), np.float32), F, mask)
|
||||
faces = np.concatenate((F, faces_garment + 14475), axis=0)
|
||||
mesh_gt = np.concatenate((body, mesh_gt[mask, :]), axis=0)
|
||||
pred_a = np.concatenate((body, pred_a), axis=0)
|
||||
pred_b = np.concatenate((body, pred_b), axis=0)
|
||||
colors = np.concatenate((np.ones_like(body, dtype=np.int32)*100, np.ones_like(mesh_gt, dtype=np.int32)*230), axis=0)
|
||||
# colors = np.ones_like(mesh_gt, dtype=np.int32)*230
|
||||
|
||||
fig.add_trace(go.Mesh3d(
|
||||
x=mesh_gt[:,0],
|
||||
y=mesh_gt[:,2],
|
||||
z=mesh_gt[:,1],
|
||||
i = faces[:,0],
|
||||
j = faces[:,1],
|
||||
k = faces[:,2],
|
||||
text="Ground Truth",
|
||||
vertexcolor=colors,
|
||||
),
|
||||
row=1, col=1)
|
||||
|
||||
fig.add_trace(go.Mesh3d(
|
||||
x=pred_a[:,0],
|
||||
y=pred_a[:,2],
|
||||
z=pred_a[:,1],
|
||||
i = faces[:,0],
|
||||
j = faces[:,1],
|
||||
k = faces[:,2],
|
||||
text="Pred A",
|
||||
vertexcolor=colors,
|
||||
),
|
||||
row=1, col=2)
|
||||
|
||||
fig.add_trace(go.Mesh3d(
|
||||
x=pred_b[:,0],
|
||||
y=pred_b[:,2],
|
||||
z=pred_b[:,1],
|
||||
i = faces[:,0],
|
||||
j = faces[:,1],
|
||||
k = faces[:,2],
|
||||
text="Pred B",
|
||||
vertexcolor=colors,
|
||||
),
|
||||
row=1, col=3)
|
||||
|
||||
|
||||
|
||||
fig.update_layout(scene_aspectmode='manual', scene_aspectratio=dict(x=1, y=1, z=1),
|
||||
scene2_aspectmode='manual', scene2_aspectratio=dict(x=1, y=1, z=1),
|
||||
scene3_aspectmode='manual', scene3_aspectratio=dict(x=1, y=1, z=1),
|
||||
)
|
||||
helper = dict(xaxis = dict(nticks=4, range=[-1,1],),
|
||||
yaxis = dict(nticks=4, range=[-1,1],),
|
||||
zaxis = dict(nticks=4, range=[-1,1],),)
|
||||
fig.update_layout(scene = helper,
|
||||
scene2 = helper,
|
||||
scene3 = helper,
|
||||
)
|
||||
|
||||
return fig
|
||||
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
run = wandb.init(project='plots', name=config_a['name'], notes=config_a['notes'], dir='/wandb')
|
||||
|
||||
parser = argparse.ArgumentParser(description='')
|
||||
parser.add_argument('--name', type=str)
|
||||
args = vars(parser.parse_args())
|
||||
|
||||
skirt_modifier = '_skirt' if config_a['is_skirt'] else ''
|
||||
|
||||
folder = config_a['test_dir']
|
||||
# smpl = SMPL(use_one_hot=False)
|
||||
|
||||
F = np.load("custom_utils/smpl_faces" + skirt_modifier + ".npy").astype(np.int32)
|
||||
|
||||
iteration = ''
|
||||
|
||||
# load_model(model, 'checkpoints/' + 'abl_all_120k')
|
||||
|
||||
|
||||
factory = DatasetFactory()
|
||||
dataset_a = factory.get_dataset(folder=config_a['test_dir'],
|
||||
batch_size=config_a['batch_size'],
|
||||
signature=config_a['signature_dynamic'],
|
||||
resolutions=[config_a['resolution']],
|
||||
in_memory=False,
|
||||
do_repeat=False,
|
||||
use_one_hot=config_a['use_one_hot'],
|
||||
use_no_orient=config_a['remove_global_orientation'],
|
||||
shuffle=False,
|
||||
testing=True,
|
||||
# frames_file='frames_abl.txt',
|
||||
)
|
||||
static_dataset_a = StaticDataset(folder=config_a['test_dir'],
|
||||
signature=config_a['signature_static'],
|
||||
resolutions=[config_a['resolution']],
|
||||
in_memory=True)
|
||||
|
||||
iterator_a = iter(dataset_a)
|
||||
|
||||
|
||||
faces_folder = '/home/workspace/data/results/support/faces' + ('_skirt' if config_a['is_skirt'] else '')
|
||||
ids = os.listdir(faces_folder)
|
||||
ids = [id.split('.')[0] for id in ids]
|
||||
faces = {id : np.load(faces_folder + '/' + id + '.npy') for id in ids }
|
||||
|
||||
results_folder = '/home/workspace/data/results/post'
|
||||
|
||||
count = 0
|
||||
while True:
|
||||
batch = iterator_a.get_next()
|
||||
|
||||
batch = static_dataset_a.expand_batch(batch_to_dict(batch, config_a['signature_dynamic']))
|
||||
|
||||
mask = batch['mesh_mask'].numpy().astype(bool)
|
||||
gt = batch['mesh_posed'].numpy()
|
||||
body = batch['mesh_body_posed'].numpy()
|
||||
|
||||
for i in range(mask.shape[0]):
|
||||
id, frame_nr = batch['id'][i].numpy().decode("utf-8"), batch['frame_nr'][i].numpy().decode("utf-8")
|
||||
pred_a = np.load(results_folder + '/al_all_post-/' + id + '_' + frame_nr + '.npy')
|
||||
pred_b = np.load(results_folder + '/iccv_weights_test_6-/' + id + '_' + frame_nr + '.npy')
|
||||
# pred_c = np.load(results_folder + '/iccv_weights_test_6-/' + id + '_' + frame_nr + '.npy')
|
||||
|
||||
fig = plot(gt[i], pred_a, pred_b, body[i], mask[i])
|
||||
|
||||
wandb.log({f'{id}_{frame_nr}': fig}, step = count)
|
||||
count += 1
|
||||
|
||||
print(count)
|
||||
|
||||
@@ -7,7 +7,7 @@ config = dict()
|
||||
# DON'T FORGET TO LOAD FINAL UPSCALER UNLESS HAVE LEVEL 512
|
||||
# DON'T FORGET TO CHECK AVG GARMENT USED
|
||||
|
||||
config['use_skinning'] = True # and deshaping
|
||||
config['use_skinning'] = False # and deshaping
|
||||
config['remove_global_orientation'] = True
|
||||
config['use_curvature'] = True
|
||||
config['use_extra_losses'] = True # edge, collision, 3d mesh
|
||||
@@ -19,9 +19,9 @@ config['only_curvatures'] = False
|
||||
ablation_count = [config['use_skinning'], config['remove_global_orientation'], config['use_curvature'], config['use_extra_losses'], config['use_offsets']].count(False)
|
||||
assert ablation_count == 1 or ablation_count == 0
|
||||
|
||||
config['gpu'] = '1'
|
||||
config['name'] = 'al_all_post'
|
||||
config['notes'] = ''
|
||||
config['gpu'] = '5'
|
||||
config['name'] = 'iccv_weights_test_8'
|
||||
config['notes'] = 'smaller weight loss coeff, 1e-6, convolutional weight learning, changed convnext reverse'
|
||||
|
||||
config['avg_garment_path'] = 'custom_data/train_no_shape_avg_uv.npy' #custom_data/train_no_shape_avg_uv.npy # train_no_shape_avg_uv train_no_shape_one_hot_avg_uv
|
||||
if config['use_skinning']:
|
||||
@@ -86,14 +86,15 @@ config['use_one_hot'] = False
|
||||
config['cvae'] = dict()
|
||||
config['cvae']['is_label'] = False
|
||||
config['cvae']['add_noise'] = True
|
||||
config['cvae']['noise_amount'] = 0.001
|
||||
config['cvae']['noise_amount'] = 0.00001
|
||||
|
||||
config['cvae']['kernel_size'] = 7
|
||||
config['cvae']['encoder_depths'] = [3, 3, 3, 9, 3]
|
||||
config['cvae']['encoder_dims'] = [32, 64, 128, 256, 64]
|
||||
config['cvae']['decoder_depths'] = config['cvae']['encoder_depths']
|
||||
config['cvae']['decoder_dims'] = config['cvae']['encoder_dims']
|
||||
|
||||
config['cvae']['decoder_depths'] = [3, 9, 3, 3, 3, 3]
|
||||
config['cvae']['decoder_dims'] = [3, 32, 128, 128, 256, 512]
|
||||
config['cvae']['decoder_weights_depths'] = [3, 9, 3, 3, 3]
|
||||
config['cvae']['decoder_weights_dims'] = [24, 32, 64, 128, 256]
|
||||
|
||||
config['cond_ae_static'] = dict()
|
||||
config['cond_ae_static']['is_label'] = False
|
||||
|
||||
@@ -2,7 +2,7 @@ from unittest import skip
|
||||
import numpy as np
|
||||
import tensorflow as tf
|
||||
from tensorflow.keras.layers import (Conv2D, Conv2DTranspose, Dense, DepthwiseConv2D,
|
||||
GlobalAveragePooling2D, Layer,
|
||||
GlobalAveragePooling2D, Layer, Activation, Lambda,
|
||||
LayerNormalization, Flatten, Reshape, UpSampling2D)
|
||||
|
||||
def drop_path(inputs, drop_prob, is_training):
|
||||
@@ -222,29 +222,31 @@ class ConvNeXtReverse(tf.keras.Model):
|
||||
|
||||
def __init__(self,
|
||||
depths=[3, 3, 9, 3], dims=[96, 192, 384, 768], kernel_size=7,
|
||||
drop_path_rate=0., layer_scale_init_value=1e-6, head_init_scale=1.,
|
||||
drop_path_rate=0., layer_scale_init_value=1e-6, head_init_scale=1., learn_weights=False,
|
||||
):
|
||||
super().__init__()
|
||||
self.upsample_layers = [] # stem and 3 intermediate downsampling conv layers
|
||||
self.upsample_layers = []
|
||||
|
||||
stem = tf.keras.Sequential([
|
||||
Conv2DTranspose(dims[0], kernel_size=4, strides=4, padding='same'),
|
||||
# UpSampling2D((4, 4), interpolation='nearest'),
|
||||
# Conv2D(dims[0], kernel_size=4, strides=1, padding='same'),
|
||||
# Dense(dims[0]),
|
||||
LayerNormalization(epsilon=1e-6)]
|
||||
)
|
||||
LayerNormalization(epsilon=1e-6),
|
||||
Conv2DTranspose(dims[0], kernel_size=2, strides=2, padding='same'),
|
||||
])
|
||||
self.upsample_layers.append(stem)
|
||||
for i in range(len(depths) - 1):
|
||||
|
||||
for i in range(len(depths) - 2):
|
||||
downsample_layer = tf.keras.Sequential([
|
||||
LayerNormalization(epsilon=1e-6),
|
||||
Conv2DTranspose(dims[i+1], kernel_size=2, strides=2, padding='same')
|
||||
# UpSampling2D((2,2), interpolation='nearest'),
|
||||
# Conv2D(dims[i+1], kernel_size=2, strides=1, padding='same'),
|
||||
# Dense(dims[i+1]),
|
||||
Conv2DTranspose(dims[i+1], kernel_size=2, strides=2, padding='same'),
|
||||
])
|
||||
self.upsample_layers.append(downsample_layer)
|
||||
|
||||
self.stages = [] # 4 feature resolution stages, each consisting of multiple residual blocks
|
||||
downsample_layer = tf.keras.Sequential([
|
||||
Conv2DTranspose(dims[i+2], kernel_size=2, strides=2, padding='same'),
|
||||
LayerNormalization(epsilon=1e-6),
|
||||
])
|
||||
self.upsample_layers.append(downsample_layer)
|
||||
|
||||
self.stages = []
|
||||
dp_rates = [x for x in np.linspace(0, drop_path_rate, sum(depths))]
|
||||
cur = 0
|
||||
for i in range(len(depths)):
|
||||
@@ -255,12 +257,19 @@ class ConvNeXtReverse(tf.keras.Model):
|
||||
self.stages.append(stage)
|
||||
cur += depths[i]
|
||||
|
||||
self.last = Dense(3, activation='tanh')
|
||||
if not learn_weights:
|
||||
self.last = Dense(3, activation='tanh')
|
||||
# self.last = Activation('tanh')
|
||||
else:
|
||||
self.last = Activation('softmax')
|
||||
# self.last = Dense(24, activation='softmax')
|
||||
|
||||
|
||||
def call(self, x, training):
|
||||
for i in reversed(range(len(self.upsample_layers))):
|
||||
x = self.upsample_layers[i](x, training=training)
|
||||
x = self.stages[i](x, training=training)
|
||||
|
||||
x = self.last(x, training=training)
|
||||
return x
|
||||
|
||||
|
||||
@@ -2,6 +2,7 @@ import json
|
||||
import numpy as np
|
||||
import tensorflow as tf
|
||||
import scipy as sp
|
||||
import cmapy as cm
|
||||
import plotly.graph_objects as go
|
||||
from plotly.subplots import make_subplots
|
||||
|
||||
@@ -216,6 +217,35 @@ def plot_3d(mesh_gt, mesh_pred_unposed, faces, collision, collision_faces, colli
|
||||
return fig
|
||||
|
||||
|
||||
def plot_weights(weights, body, faces):
|
||||
fig = go.Figure()
|
||||
colors = np.array([cm.color('jet', 1 - w) for w in weights.numpy()])
|
||||
|
||||
# if flip_xy:
|
||||
# mesh_gt = flip_axis(mesh_gt)
|
||||
# mesh_pred_unposed = flip_axis(mesh_pred_unposed)
|
||||
# collision = flip_axis(collision, ind=14475)
|
||||
|
||||
fig.add_trace(go.Mesh3d(
|
||||
x=body[:,0],
|
||||
y=body[:,2],
|
||||
z=body[:,1],
|
||||
i = faces[:,0],
|
||||
j = faces[:,1],
|
||||
k = faces[:,2],
|
||||
vertexcolor=colors
|
||||
))
|
||||
|
||||
|
||||
fig.update_layout(scene_aspectmode='manual', scene_aspectratio=dict(x=1, y=1, z=1),)
|
||||
helper = dict(xaxis = dict(nticks=4, range=[-1,1],),
|
||||
yaxis = dict(nticks=4, range=[-1,1],),
|
||||
zaxis = dict(nticks=4, range=[-1,1],),)
|
||||
fig.update_layout(scene = helper,)
|
||||
|
||||
return fig
|
||||
|
||||
|
||||
def plot_3d_collision(gt, collision_1, collision_2, collision_faces, collision_color, flip_xy=False):
|
||||
fig = make_subplots(rows=1, cols=3, start_cell="top-left", specs = [ [{ 'type': 'scene' } for _ in range(3)] ])
|
||||
|
||||
|
||||
@@ -406,7 +406,8 @@ class SMPL:
|
||||
return T_out, J_out
|
||||
|
||||
|
||||
def run_garment_with_weights(self, R, betas, v_cloth, weights, J=None):
|
||||
def run_garment_with_weights(self, pose, betas, v_cloth, weights, J=None):
|
||||
R = self.run_rodrigues(pose)
|
||||
|
||||
if J is None:
|
||||
J = self.get_joints_template(betas)
|
||||
@@ -430,13 +431,12 @@ class SMPL:
|
||||
J = tf.gather(J, tf.constant([0, 1, 2], tf.int32), axis=1)
|
||||
|
||||
T = tf.tensordot(weights, results, axes=((1), (0)))
|
||||
rest_shape_h = tf.concat((v_cloth, tf.ones((v_cloth.get_shape().as_list()[0], 1), dtype=tf.float32)), axis=1)
|
||||
rest_shape_h = tf.concat((v_cloth, tf.ones((v_cloth.shape[0], 1), dtype=tf.float32)), axis=1)
|
||||
v = tf.matmul(T, tf.reshape(rest_shape_h, (-1, 4, 1)))
|
||||
v = tf.reshape(v, (-1, 4))[:, :3]
|
||||
|
||||
return v, tf.squeeze(J)
|
||||
|
||||
# gender = tf.cast(tf.greater_equal(betas[:, 10] , 0), tf.int32)
|
||||
T_out, J_out = tf.map_fn(single_run, (R, J, v_cloth, weights), (tf.float32, tf.float32))
|
||||
|
||||
J0 = tf.reshape(J_out[:,0,:], (-1, 1, 3))
|
||||
|
||||
@@ -38,7 +38,7 @@ else:
|
||||
from losses import collision_ratio, kl_loss, normal_loss #, concept_loss
|
||||
# from losses import collision_penalty as collision_penalty
|
||||
from losses import collision_loss as collision_penalty
|
||||
from custom_utils.custom_utils import batch_to_dict, load_model, plot_3d, UV2Mesh, get_summary_html, maskFacesBatch, _maskFaces, plot_3d_collision
|
||||
from custom_utils.custom_utils import batch_to_dict, load_model, plot_3d, UV2Mesh, UV2MeshLabel, get_summary_html, maskFacesBatch, _maskFaces, plot_3d_collision, plot_weights
|
||||
from dataset import DatasetFactory, StaticDataset
|
||||
from custom_utils.smpl import SMPL
|
||||
from models.cvae_model import CVAENew as CVAE
|
||||
@@ -62,6 +62,7 @@ def init_wandb():
|
||||
run.log_artifact(artifact)
|
||||
|
||||
uv2mesh = UV2Mesh(res=256, is_skirt=config['is_skirt'], is_adaptive=False, is_smpl_orig=config['is_cape'])
|
||||
uv2mesh_label = UV2MeshLabel(res=256, is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape'])
|
||||
|
||||
|
||||
def kl_loss(mean, logvar):
|
||||
@@ -71,9 +72,15 @@ def kl_loss(mean, logvar):
|
||||
return kl_loss
|
||||
|
||||
|
||||
def blend_weights_reg(pred_w, gender=None):
|
||||
orig = smpl.weights
|
||||
l1 = tf.reduce_mean(tf.abs(pred_w - orig[None, 0, :, :]))
|
||||
return l1
|
||||
|
||||
|
||||
# 3d loss on posed !!!!!!!!!!!!
|
||||
|
||||
# @tf.function
|
||||
@tf.function
|
||||
def train_step(batch):
|
||||
|
||||
with tf.GradientTape() as tape:
|
||||
@@ -82,9 +89,10 @@ def train_step(batch):
|
||||
else:
|
||||
mesh_orig, uv_orig = batch['mesh_posed'], batch['uv_posed']
|
||||
|
||||
pred, mean, logvar = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=True)
|
||||
pred, mean, logvar, weights = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=True)
|
||||
|
||||
mesh_pred = uv2mesh(pred)
|
||||
mesh_weigths = uv2mesh_label(weights)
|
||||
|
||||
if config['use_skinning']:
|
||||
shape = batch['pose_shape'][:, 72:]
|
||||
@@ -94,25 +102,31 @@ def train_step(batch):
|
||||
mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis]
|
||||
mesh_pred_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)
|
||||
else:
|
||||
mesh_pred_posed = mesh_pred
|
||||
shape = batch['pose_shape'][:, 72:]
|
||||
gender = tf.cast(tf.greater_equal(shape[:, 10] , 0.5), tf.int32)
|
||||
shape_offsets = tf.stack([tf.gather(tf.tensordot(shape[i,:10][tf.newaxis, :], smpl.shapedirs[gender[i]], axes=[[1], [2]])[0,:,:], smpl.to_keep, axis=0) for i in range(shape.shape[0])])
|
||||
|
||||
mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis]
|
||||
mesh_pred_posed = smpl.run_garment_with_weights(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped, mesh_weigths)
|
||||
|
||||
# is the output already masked?
|
||||
|
||||
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(((uv_orig - pred) ** 2), axis=-1), axis=[1, 2]))
|
||||
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))
|
||||
n_loss = normal_loss(mesh_pred_posed, batch['mesh_posed'], batch['mesh_mask'], is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape'])
|
||||
# conc_loss = concept_loss(pred, batch['uv_unposed'])
|
||||
kl = kl_loss(mean, logvar)
|
||||
weights_l = blend_weights_reg(mesh_weigths)
|
||||
|
||||
reconstr_loss = l2_loss
|
||||
reconstr_loss = l2_mesh_loss + 1e-6 * weights_l
|
||||
if config['use_extra_losses']:
|
||||
if 'block_collision_loss' in config.keys() and config['block_collision_loss'] == True:
|
||||
reconstr_loss = reconstr_loss + l2_mesh_loss + (e_loss) * config['reg_loss_coeff']
|
||||
reconstr_loss = reconstr_loss + (e_loss) * config['reg_loss_coeff']
|
||||
else:
|
||||
reconstr_loss = reconstr_loss + l2_mesh_loss + (e_loss + c_loss) * config['reg_loss_coeff']
|
||||
reconstr_loss = reconstr_loss + (e_loss + c_loss) * config['reg_loss_coeff']
|
||||
if config['use_norm_loss'] and step > 2000:
|
||||
reconstr_loss = reconstr_loss + n_loss * config['reg_loss_coeff']
|
||||
|
||||
@@ -122,14 +136,14 @@ def train_step(batch):
|
||||
logvar = tf.reduce_mean(logvar)
|
||||
|
||||
# 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)))
|
||||
metric = tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_orig - mesh_pred) ** 2, axis=-1))) / tf.reduce_sum(batch['mesh_mask'])
|
||||
metric = tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_orig - mesh_pred_posed) ** 2, axis=-1))) / tf.reduce_sum(batch['mesh_mask'])
|
||||
gradients = tape.gradient(loss, model.trainable_variables)
|
||||
optimizer.apply_gradients(zip(gradients, model.trainable_variables))
|
||||
return { 'train/loss': loss, 'train/edge_loss': e_loss, 'train/collision_loss': c_loss, 'train/euclid_error': metric,
|
||||
'train/reconstr_loss': reconstr_loss, 'train/collision_ratio': c_ratio,
|
||||
'train/mean': mean, 'train/logvar': logvar, 'train/kl_loss': kl, 'train/var': np.e ** logvar,
|
||||
'train/l2_loss': l2_loss, 'train/l2_mesh_loss': l2_mesh_loss, 'train/normal_loss': n_loss,
|
||||
# 'train/ms_ssim': ms_ssim,
|
||||
'train/l2_mesh_loss': l2_mesh_loss, 'train/normal_loss': n_loss, 'train/weights_loss': weights_l,
|
||||
# 'train/ms_ssim': ms_ssim, 'train/l2_loss': l2_loss,
|
||||
}
|
||||
|
||||
|
||||
@@ -140,9 +154,10 @@ def valid_step(batch):
|
||||
else:
|
||||
mesh_orig, uv_orig = batch['mesh_posed'], batch['uv_posed']
|
||||
|
||||
pred, mean, logvar = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=False)
|
||||
pred, mean, logvar, weights = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=False)
|
||||
|
||||
mesh_pred = uv2mesh(pred)
|
||||
mesh_weigths = uv2mesh_label(weights)
|
||||
|
||||
if config['use_skinning']:
|
||||
shape = batch['pose_shape'][:, 72:]
|
||||
@@ -152,22 +167,28 @@ def valid_step(batch):
|
||||
mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis]
|
||||
mesh_pred_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)
|
||||
else:
|
||||
mesh_pred_posed = mesh_pred
|
||||
shape = batch['pose_shape'][:, 72:]
|
||||
gender = tf.cast(tf.greater_equal(shape[:, 10] , 0.5), tf.int32)
|
||||
shape_offsets = tf.stack([tf.gather(tf.tensordot(shape[i,:10][tf.newaxis, :], smpl.shapedirs[gender[i]], axes=[[1], [2]])[0,:,:], smpl.to_keep, axis=0) for i in range(shape.shape[0])])
|
||||
|
||||
mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis]
|
||||
mesh_pred_posed = smpl.run_garment_with_weights(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped, mesh_weigths)
|
||||
|
||||
# is the output already masked?
|
||||
|
||||
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(((uv_orig - pred) ** 2), axis=-1), axis=[1, 2]))
|
||||
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))
|
||||
n_loss = normal_loss(mesh_pred_posed, batch['mesh_posed'], batch['mesh_mask'], is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape'])
|
||||
# conc_loss = concept_loss(pred, batch['uv_unposed'])
|
||||
kl = kl_loss(mean, logvar)
|
||||
weights_l = blend_weights_reg(mesh_weigths)
|
||||
|
||||
reconstr_loss = l2_loss
|
||||
reconstr_loss = l2_mesh_loss + 1e-6 * weights_l
|
||||
if config['use_extra_losses']:
|
||||
reconstr_loss = reconstr_loss + l2_mesh_loss + (e_loss + c_loss) * config['reg_loss_coeff']
|
||||
reconstr_loss = reconstr_loss + (e_loss + c_loss) * config['reg_loss_coeff']
|
||||
if config['use_norm_loss']:
|
||||
reconstr_loss = reconstr_loss + n_loss * config['reg_loss_coeff']
|
||||
|
||||
@@ -177,12 +198,12 @@ def valid_step(batch):
|
||||
logvar = tf.reduce_mean(logvar)
|
||||
|
||||
# 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)))
|
||||
metric = tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_orig - mesh_pred) ** 2, axis=-1))) / tf.reduce_sum(batch['mesh_mask'])
|
||||
metric = tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_orig - mesh_pred_posed) ** 2, axis=-1))) / tf.reduce_sum(batch['mesh_mask'])
|
||||
# c_ratio = tf.reduce_mean(collision_ratio(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask']))
|
||||
|
||||
return { 'valid/loss': loss, 'valid/edge_loss': e_loss, 'valid/collision_loss': c_loss, 'valid/euclid_error': metric,
|
||||
'valid/reconstr_loss': reconstr_loss, 'valid/l2_mesh_loss': l2_mesh_loss, 'valid/collision_ratio': c_ratio,
|
||||
'valid/mean': mean, 'valid/logvar': logvar, 'valid/kl_loss': kl, 'valid/var': np.e ** logvar,
|
||||
'valid/mean': mean, 'valid/logvar': logvar, 'valid/kl_loss': kl, 'valid/var': np.e ** logvar, 'valid/weights_loss': weights_l,
|
||||
'valid/normal_loss': n_loss,# 'valid/ms_ssim': ms_ssim,
|
||||
}
|
||||
|
||||
@@ -194,7 +215,7 @@ def test_step(batch):
|
||||
else:
|
||||
mesh_orig, uv_orig = batch['mesh_posed'], batch['uv_posed']
|
||||
|
||||
pred, mean, logvar = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=False)
|
||||
pred, mean, logvar, weights = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=False)
|
||||
|
||||
mesh_pred = uv2mesh(pred)
|
||||
|
||||
@@ -208,7 +229,7 @@ def test_step(batch):
|
||||
mesh_orig_shaped = mesh_orig + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis]
|
||||
mesh_orig_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_orig_shaped)
|
||||
else:
|
||||
mesh_pred_posed = mesh_pred
|
||||
mesh_pred_posed = smpl.run_garment_with_weights(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred, weights)
|
||||
mesh_orig_posed = mesh_orig
|
||||
|
||||
mesh_pred_posed_fixed = fix_collision(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask'])
|
||||
@@ -250,9 +271,10 @@ def plot_everything(batch: dict, type: str):
|
||||
else:
|
||||
mesh_orig, uv_orig = batch['mesh_posed'], batch['uv_posed']
|
||||
|
||||
pred, mean, logvar = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=False)
|
||||
pred, mean, logvar, weights = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=False)
|
||||
|
||||
mesh_pred = uv2mesh(pred).numpy()
|
||||
mesh_weigths = uv2mesh_label(weights)
|
||||
|
||||
orig_img = uv_orig
|
||||
uv_static_img = batch['uv_static']
|
||||
@@ -277,7 +299,12 @@ def plot_everything(batch: dict, type: str):
|
||||
mesh_pred[i, mask[i], :] += shape_offsets.numpy()[i, mask[i], :]
|
||||
mesh_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred).numpy()
|
||||
else:
|
||||
mesh_posed = mesh_pred
|
||||
shape = batch['pose_shape'][:, 72:]
|
||||
gender = tf.cast(tf.greater_equal(shape[:, 10] , 0.5), tf.int32)
|
||||
shape_offsets = tf.stack([tf.gather(tf.tensordot(shape[i,:10][tf.newaxis, :], smpl.shapedirs[gender[i]], axes=[[1], [2]])[0,:,:], smpl.to_keep, axis=0) for i in range(shape.shape[0])])
|
||||
|
||||
mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis]
|
||||
mesh_posed = smpl.run_garment_with_weights(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped, mesh_weigths).numpy()
|
||||
gt = [mesh_orig[i].numpy()[mask[i], :] for i in range(pred.shape[0])]
|
||||
garment_unposed, faces = maskFacesBatch(mesh_pred, F, mask)
|
||||
|
||||
@@ -296,13 +323,16 @@ def plot_everything(batch: dict, type: str):
|
||||
collision_fixed = [np.concatenate((body[i], garment_posed_fixed[i]), axis=0) for i in range(len(garment_posed))]
|
||||
collision_gt = [np.concatenate((body[i], gt_posed[i]), axis=0) for i in range(len(garment_posed))]
|
||||
|
||||
figs = { type + "/garment_" + str(i): plot_3d(gt[i], garment_unposed[i], faces[i], collision[i], collision_faces[i], collision_color[i], flip_xy=(not config['use_skinning'] and config['remove_global_orientation'])) for i in range(4) }
|
||||
figs_coll = { type + "/garment_" + str(i) + '_collision': plot_3d_collision(collision_gt[i], collision[i], collision_fixed[i], collision_faces[i], collision_color[i], flip_xy=(not config['use_skinning'] and config['remove_global_orientation'])) for i in range(4) }
|
||||
# figs = { type + "/garment_" + str(i): plot_3d(gt[i], garment_unposed[i], faces[i], garment_posed[i], faces[i], collision_color[i], flip_xy=(not config['use_skinning'] and config['remove_global_orientation'])) for i in range(4) }
|
||||
figs = { type + "/garment_" + str(i): plot_3d(gt[i], garment_unposed[i], faces[i], collision[i], collision_faces[i], collision_color[i],) for i in range(4) }
|
||||
figs_coll = { type + "/garment_" + str(i) + '_collision': plot_3d_collision(collision_gt[i], collision[i], collision_fixed[i], collision_faces[i], collision_color[i],) for i in range(4) }
|
||||
figs_weights = { type + '/weights_' + str(i): plot_weights(mesh_weigths[0,:,i], body[0], F) for i in range(24) }
|
||||
# figs_weights = { type + '/weights_' + str(i): plot_weights(smpl.weights[0,:,i], body[0], F) for i in range(24) }
|
||||
|
||||
mean_hist = wandb.Histogram(sequence=mean.numpy().mean(axis=0))
|
||||
logvar_hist = wandb.Histogram(sequence=logvar.numpy().mean(axis=0))
|
||||
|
||||
return { **figs, **figs_coll, **{ type + '/images': imgs, type + '/mean_hist': mean_hist, type + '/logvar_hist': logvar_hist } }
|
||||
return { **figs, **figs_coll, **figs_weights, **{ type + '/images': imgs, type + '/mean_hist': mean_hist, type + '/logvar_hist': logvar_hist } }
|
||||
|
||||
|
||||
def sample(folder):
|
||||
@@ -476,7 +506,7 @@ def test():
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
# init_wandb()
|
||||
init_wandb()
|
||||
parser = argparse.ArgumentParser(description='')
|
||||
parser.add_argument('--name', type=str)
|
||||
args = vars(parser.parse_args())
|
||||
|
||||
+34
-2
@@ -2,9 +2,41 @@ FROM tensorflow/tensorflow:2.9.0-gpu
|
||||
|
||||
RUN apt-get update
|
||||
RUN apt-get upgrade -y
|
||||
|
||||
# Add the current user to the image
|
||||
ARG USER_NAME=lhunor
|
||||
ARG USER_ID=11017
|
||||
ARG GROUP_NAME=guest
|
||||
ARG GROUP_ID=11000
|
||||
|
||||
# Update the system and install required packages
|
||||
RUN apt-get update && apt-get upgrade -y && apt-get install -y sudo git
|
||||
|
||||
# Create a new group with the same GID as the host
|
||||
RUN groupadd --gid $GROUP_ID $GROUP_NAME
|
||||
|
||||
# Create a new user with the same UID and GID as the host
|
||||
RUN useradd --uid $USER_ID --gid $GROUP_ID --shell /bin/bash --create-home $USER_NAME
|
||||
|
||||
# don't require password with sudo, for convenience
|
||||
# not the safest thing to do, but hopefully okay inside the container
|
||||
RUN echo '%sudo ALL=(ALL) NOPASSWD:ALL' >> /etc/sudoers
|
||||
|
||||
# Add the new user to the sudo group
|
||||
RUN usermod -aG sudo $USER_NAME
|
||||
|
||||
# Set the default user to the new user
|
||||
USER $USER_NAME
|
||||
|
||||
WORKDIR //home-net
|
||||
|
||||
RUN apt-get install git ffmpeg libsm6 libxext6 libopenexr-dev zip unzip htop nano -y
|
||||
RUN pip install numpy matplotlib opencv-python wandb OpenEXR tensorflow-graphics scipy plotly pandas tensorboardX opencv-python cmapy
|
||||
|
||||
# defining the volumes that will be mounted
|
||||
VOLUME [ "/data-net" ]
|
||||
VOLUME [ "/data-local" ]
|
||||
VOLUME [ "/home-net" ]
|
||||
|
||||
WORKDIR /home/workspace/data
|
||||
# RUN wandb login
|
||||
# Start the container with a bash shell
|
||||
CMD ["/bin/bash"]
|
||||
+11
-3
@@ -39,7 +39,7 @@ else:
|
||||
from losses import collision_ratio, kl_loss #, concept_loss
|
||||
# from losses import collision_penalty as collision_penalty
|
||||
from losses import collision_loss as collision_penalty
|
||||
from custom_utils.custom_utils import batch_to_dict, load_model, plot_3d, UV2Mesh, get_summary_html, maskFacesBatch, _maskFaces, plot_3d_collision
|
||||
from custom_utils.custom_utils import batch_to_dict, load_model, plot_3d, UV2Mesh, UV2MeshLabel, get_summary_html, maskFacesBatch, _maskFaces, plot_3d_collision
|
||||
from dataset import DatasetFactory, StaticDataset
|
||||
from custom_utils.smpl import SMPL
|
||||
from models.cvae_model import CVAENew as CVAE
|
||||
@@ -48,6 +48,7 @@ from custom_utils.supersmpl_io import writeOBJ
|
||||
|
||||
|
||||
uv2mesh = UV2Mesh(res=256, is_skirt=config['is_skirt'], is_adaptive=False, is_smpl_orig=config['is_cape'])
|
||||
uv2mesh_label = UV2MeshLabel(res=256, is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape'])
|
||||
|
||||
@tf.function
|
||||
def step(batch):
|
||||
@@ -56,9 +57,10 @@ def step(batch):
|
||||
else:
|
||||
uv_orig = batch['uv_posed']
|
||||
|
||||
pred, _, _ = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=False)
|
||||
pred, _, _, weights = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=False)
|
||||
|
||||
mesh_pred = uv2mesh(pred)
|
||||
mesh_weigths = uv2mesh_label(weights)
|
||||
|
||||
if config['use_skinning']:
|
||||
shape = batch['pose_shape'][:, 72:]
|
||||
@@ -68,7 +70,13 @@ def step(batch):
|
||||
mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis]
|
||||
mesh_pred_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)
|
||||
else:
|
||||
mesh_pred_posed = mesh_pred
|
||||
shape = batch['pose_shape'][:, 72:]
|
||||
gender = tf.cast(tf.greater_equal(shape[:, 10] , 0.5), tf.int32)
|
||||
shape_offsets = tf.stack([tf.gather(tf.tensordot(shape[i,:10][tf.newaxis, :], smpl.shapedirs[gender[i]], axes=[[1], [2]])[0,:,:], smpl.to_keep, axis=0) for i in range(shape.shape[0])])
|
||||
|
||||
mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis]
|
||||
mesh_pred_posed = smpl.run_garment_with_weights(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped, mesh_weigths)
|
||||
|
||||
|
||||
# mesh_pred_posed_fixed = fix_collision(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask'])
|
||||
|
||||
|
||||
+2
-2
@@ -171,13 +171,13 @@ class AEEncoderNew(tf.keras.Model):
|
||||
|
||||
class DecoderNew(tf.keras.Model):
|
||||
|
||||
def __init__(self, depths, dims, kernel_size=7, is_label=False):
|
||||
def __init__(self, depths, dims, kernel_size=7, is_label=False, learn_weights=False):
|
||||
super(DecoderNew, self).__init__()
|
||||
|
||||
self.is_label = is_label
|
||||
|
||||
if not is_label:
|
||||
self.decoder = ConvNeXtReverse(depths=depths, dims=dims, kernel_size=kernel_size)
|
||||
self.decoder = ConvNeXtReverse(depths=depths, dims=dims, kernel_size=kernel_size, learn_weights=learn_weights)
|
||||
else:
|
||||
self.decoder = ConvNeXtReverseLabels(depths=depths, dims=dims, nr_of_classes=7)
|
||||
|
||||
|
||||
@@ -181,6 +181,7 @@ class CVAENew(tf.keras.Model):
|
||||
|
||||
self.encoder = VariationalEncoderNew(config['cvae']['encoder_depths'], config['cvae']['encoder_dims'], kernel_size=config['cvae']['kernel_size'])
|
||||
self.decoder = DecoderNew(config['cvae']['decoder_depths'], config['cvae']['decoder_dims'], config['cvae']['kernel_size'])
|
||||
self.decoder_weights = DecoderNew(config['cvae']['decoder_weights_depths'], config['cvae']['decoder_weights_dims'], config['cvae']['kernel_size'], learn_weights=True)
|
||||
|
||||
self.reshape = tf.keras.layers.Reshape((8, 4, 64))
|
||||
|
||||
@@ -193,12 +194,12 @@ class CVAENew(tf.keras.Model):
|
||||
self.noise_amount = config['cvae']['noise_amount']
|
||||
self.use_curvature = config['use_curvature']
|
||||
self.only_curvatures = config['only_curvatures'] if 'only_curvatures' in config.keys() and config['only_curvatures'] == True else None
|
||||
self.use_offsets_over_body = not config['use_skinning']
|
||||
self.use_offsets_over_body = False
|
||||
|
||||
if self.use_offsets_over_body:
|
||||
assert self.avg_garment is None, 'When we are not using skinning, we can\'t use avg_garment!'
|
||||
if self.avg_garment is not None:
|
||||
assert not self.use_offsets_over_body, 'When avg_garment is given, we must use skinning!'
|
||||
# if self.avg_garment is not None:
|
||||
# assert not self.use_offsets_over_body, 'When avg_garment is given, we must use skinning!'
|
||||
|
||||
# @tf.function
|
||||
def sample(self, uv_template, uv_body_posed, uv_curv, uv_mask, noise=None, add_noise=False):
|
||||
@@ -214,6 +215,7 @@ class CVAENew(tf.keras.Model):
|
||||
z = tf.concat([eps, z_cond], axis=-1)
|
||||
|
||||
x = self.decoder(z, training=False)
|
||||
weights = self.decoder_weights(z, training=False)
|
||||
|
||||
if self.avg_garment is not None:
|
||||
x = x + self.avg_garment[tf.newaxis,:,:,:]
|
||||
@@ -223,7 +225,7 @@ class CVAENew(tf.keras.Model):
|
||||
|
||||
x = x * uv_mask[:,:,:,tf.newaxis]
|
||||
|
||||
return x
|
||||
return x, weights
|
||||
|
||||
|
||||
def reparameterize(self, mean, logvar, training, fix_noise=False):
|
||||
@@ -272,6 +274,7 @@ class CVAENew(tf.keras.Model):
|
||||
|
||||
z = tf.concat([z, z_cond], axis=-1)
|
||||
x = self.decoder(z, training=training)
|
||||
weights = self.decoder_weights(z, training=training)
|
||||
|
||||
if self.avg_garment is not None:
|
||||
x = x + self.avg_garment[tf.newaxis,:,:,:]
|
||||
@@ -281,5 +284,5 @@ class CVAENew(tf.keras.Model):
|
||||
|
||||
x = x * uv_mask[:,:,:,tf.newaxis]
|
||||
|
||||
return x, mean, logvar
|
||||
return x, mean, logvar, weights
|
||||
|
||||
|
||||
Reference in New Issue
Block a user