add whl for kaolin

app.py

@@ -10,11 +10,12 @@ import subprocess
 
 if os.getenv('SYSTEM') == 'spaces':
     subprocess.run('pip install pyembree'.split())
-    subprocess.run('pip install git+https://github.com/YuliangXiu/rembg.git@hf'.split())
+    subprocess.run(
+        'pip install git+https://github.com/YuliangXiu/rembg.git@hf'.split())
     subprocess.run(
         'pip install torch==1.11.0+cu113 torchvision==0.12.0+cu113 -f https://download.pytorch.org/whl/cu113/torch_stable.html'.split())
     subprocess.run(
-        'pip wheel git+https://github.com/YuliangXiu/kaolin.git -w /home/user/app && pip install /home/user/app/kaolin-0.11.0-cp38-cp38-linux_x86_64.whl', shell=True)
+        'pip install https://download.is.tue.mpg.de/icon/HF/kaolin-0.11.0-cp38-cp38-linux_x86_64.whl'.split())
     subprocess.run('pip install --no-index --no-cache-dir pytorch3d -f https://dl.fbaipublicfiles.com/pytorch3d/packaging/wheels/py38_cu113_pyt1110/download.html'.split())
     subprocess.run(
         'pip install git+https://github.com/Project-Splinter/human_det.git'.split())
@@ -94,7 +95,8 @@ def generate_image(seed, psi):
 
 random.seed(2022)
 model_types = ['icon-filter', 'pifu', 'pamir']
-examples = [[item, random.choice(model_types)] for item in glob.glob('examples/*.png')]
+examples = [[item, random.choice(model_types)]
+            for item in glob.glob('examples/*.png')]
 
 with gr.Blocks() as demo:
     gr.Markdown(description)
@@ -139,11 +141,9 @@ with gr.Blocks() as demo:
                 clear_color=[0.0, 0.0, 0.0, 0.0],  label="Refined Recon")
             out_final_download = gr.File(
                 label="Download refined clothed human mesh")
-            out_kaolin_download = gr.File(
-                label="Kaolin")
 
     out_lst = [out_smpl, out_smpl_download, out_smpl_npy_download, out_recon, out_recon_download,
-               out_final, out_final_download, out_vid, out_vid_download, overlap_inp, out_kaolin_download]
+               out_final, out_final_download, out_vid, out_vid_download, overlap_inp]
 
     btn_submit.click(fn=generate_model, inputs=[
                      inp, radio_choice], outputs=out_lst)

apps/infer.py

@@ -14,7 +14,8 @@
 #
 # Contact: ps-license@tuebingen.mpg.de
 
-import os, gc
+import os
+import gc
 
 import logging
 from lib.common.config import cfg
@@ -46,7 +47,7 @@ logging.getLogger("trimesh").setLevel(logging.ERROR)
 
 
 def generate_model(in_path, model_type):
-    
+
     torch.cuda.empty_cache()
 
     config_dict = {'loop_smpl': 100,
@@ -59,7 +60,7 @@ def generate_model(in_path, model_type):
     # cfg read and merge
     cfg.merge_from_file(config_dict['config'])
     cfg.merge_from_file("./lib/pymaf/configs/pymaf_config.yaml")
-    
+
     os.makedirs(config_dict['out_dir'], exist_ok=True)
 
     cfg_show_list = [
@@ -262,7 +263,6 @@ def generate_model(in_path, model_type):
         os.makedirs(os.path.join(config_dict['out_dir'],
                     cfg.name, "obj"), exist_ok=True)
 
-
         norm_pred = (
             ((in_tensor["normal_F"][0].permute(1, 2, 0) + 1.0) * 255.0 / 2.0)
             .detach()
@@ -334,7 +334,8 @@ def generate_model(in_path, model_type):
         recon_obj = trimesh.Trimesh(
             verts_pr, faces_pr, process=False, maintains_order=True
         )
-        recon_obj.visual.vertex_colors = (recon_obj.vertex_normals+1.0)*255.0*0.5
+        recon_obj.visual.vertex_colors = (
+            recon_obj.vertex_normals+1.0)*255.0*0.5
         recon_obj.export(
             os.path.join(config_dict['out_dir'], cfg.name,
                          f"obj/{data['name']}_recon.obj")
@@ -343,7 +344,7 @@ def generate_model(in_path, model_type):
             os.path.join(config_dict['out_dir'], cfg.name,
                          f"obj/{data['name']}_recon.glb")
         )
-        
+
         # Isotropic Explicit Remeshing for better geometry topology
         verts_refine, faces_refine = remesh(os.path.join(config_dict['out_dir'], cfg.name,
                                                          f"obj/{data['name']}_recon.obj"), 0.5, device)
@@ -411,23 +412,21 @@ def generate_model(in_path, model_type):
                 optimizer_cloth.step()
                 scheduler_cloth.step(cloth_loss)
 
-
             final = trimesh.Trimesh(
                 mesh_pr.verts_packed().detach().squeeze(0).cpu(),
                 mesh_pr.faces_packed().detach().squeeze(0).cpu(),
                 process=False, maintains_order=True
             )
-            
-            
+
             # without front texture
-            final_colors = (mesh_pr.verts_normals_padded().squeeze(0).detach().cpu() + 1.0) * 0.5 * 255.0
+            final_colors = (mesh_pr.verts_normals_padded().squeeze(
+                0).detach().cpu() + 1.0) * 0.5 * 255.0
             final.visual.vertex_colors = final_colors
             final.export(
                 f"{config_dict['out_dir']}/{cfg.name}/obj/{data['name']}_refine.obj")
             final.export(
                 f"{config_dict['out_dir']}/{cfg.name}/obj/{data['name']}_refine.glb")
 
-
         # always export visualized video regardless of the cloth refinment
         if final is not None:
             verts_lst = [verts_pr, final.vertices]
@@ -444,7 +443,7 @@ def generate_model(in_path, model_type):
             os.path.join(config_dict['out_dir'], cfg.name,
                          f"vid/{data['name']}_cloth.mp4"),
         )
-    
+
     smpl_obj_path = f"{config_dict['out_dir']}/{cfg.name}/obj/{data['name']}_smpl.obj"
     smpl_glb_path = f"{config_dict['out_dir']}/{cfg.name}/obj/{data['name']}_smpl.glb"
     smpl_npy_path = f"{config_dict['out_dir']}/{cfg.name}/obj/{data['name']}_smpl.npy"
@@ -452,21 +451,21 @@ def generate_model(in_path, model_type):
     recon_glb_path = f"{config_dict['out_dir']}/{cfg.name}/obj/{data['name']}_recon.glb"
     refine_obj_path = f"{config_dict['out_dir']}/{cfg.name}/obj/{data['name']}_refine.obj"
     refine_glb_path = f"{config_dict['out_dir']}/{cfg.name}/obj/{data['name']}_refine.glb"
-    
-    video_path = os.path.join(config_dict['out_dir'], cfg.name, f"vid/{data['name']}_cloth.mp4")
-    overlap_path = os.path.join(config_dict['out_dir'], cfg.name, f"png/{data['name']}_overlap.png")
-    
+
+    video_path = os.path.join(
+        config_dict['out_dir'], cfg.name, f"vid/{data['name']}_cloth.mp4")
+    overlap_path = os.path.join(
+        config_dict['out_dir'], cfg.name, f"png/{data['name']}_overlap.png")
+
     # clean all the variables
     for element in dir():
         if 'path' not in element:
             del locals()[element]
     gc.collect()
     torch.cuda.empty_cache()
-    
-    kaolin_path = "/home/user/app/kaolin-0.11.0-cp38-cp38-linux_x86_64.whl"
-    
-    return [smpl_glb_path, smpl_obj_path, 
-            smpl_npy_path, 
-            recon_glb_path, recon_obj_path, 
-            refine_glb_path, refine_obj_path, 
-            video_path, video_path, overlap_path, kaolin_path]
+
+    return [smpl_glb_path, smpl_obj_path,
+            smpl_npy_path,
+            recon_glb_path, recon_obj_path,
+            refine_glb_path, refine_obj_path,
+            video_path, video_path, overlap_path]