fixed types for examples

README.md

@@ -5,7 +5,7 @@ emoji: 🤼
 colorFrom: indigo
 colorTo: yellow
 sdk: gradio
-sdk_version: 3.1.3
+sdk_version: 3.1.4
 app_file: app.py
 pinned: true
 python_version: 3.8.13

app.py

@@ -4,7 +4,7 @@
 import glob
 import gradio as gr
 import os
-import random
+import numpy as np
 
 import subprocess
 
@@ -16,7 +16,8 @@ if os.getenv('SYSTEM') == 'spaces':
         '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 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 https://download.is.tue.mpg.de/icon/HF/pytorch3d-0.7.0-cp38-cp38-linux_x86_64.whl'.split())
     subprocess.run(
         'pip install git+https://github.com/Project-Splinter/human_det.git'.split())
     subprocess.run(
@@ -93,10 +94,12 @@ def generate_image(seed, psi):
     return img
 
 
-random.seed(2022)
 model_types = ['ICON', 'PIFu', 'PaMIR']
-examples = [[item, random.choice(model_types)]
-            for item in glob.glob('examples/*.png')]
+examples_names = glob.glob('examples/*.png')
+examples_types = np.random.choice(
+    model_types, len(examples_names), p=[0.6, 0.2, 0.2])
+
+examples = [list(item) for item in zip(examples_names, examples_types)]
 
 with gr.Blocks() as demo:
     gr.Markdown(description)
@@ -119,11 +122,12 @@ with gr.Blocks() as demo:
 
             gr.Examples(examples=examples,
                         inputs=[inp, radio_choice],
-                        cache_examples=True,
+                        cache_examples=False,
                         fn=generate_model,
                         outputs=out_lst)
 
-            out_vid = gr.Video(label="Image + Normal + SMPL Body + Clothed Human")
+            out_vid = gr.Video(
+                label="Image + Normal + SMPL Body + Clothed Human")
             out_vid_download = gr.File(
                 label="Download Video, welcome share on Twitter with #ICON")
 

apps/infer.py

@@ -458,7 +458,7 @@ def generate_model(in_path, model_type):
             del locals()[element]
     gc.collect()
     torch.cuda.empty_cache()
-
+    
     return [smpl_glb_path, smpl_obj_path,smpl_npy_path,
             refine_glb_path, refine_obj_path,
             video_path, video_path, overlap_path]