test frontend

app.py

@@ -1,7 +1,124 @@
+import os
+import sys
+import os.path as osp
+from pathlib import Path
+import cv2
 import gradio as gr
+import torch
+import math
+import spaces
 
-def greet(name):
-    return "Hello " + name + "!!"
+try:
+    import mmpose
+except:
+    os.system('pip install /home/user/app/main/transformer_utils')
 
-iface = gr.Interface(fn=greet, inputs="text", outputs="text")
-iface.launch()
+os.system('cp -rf /home/user/app/assets/conversions.py /home/user/.pyenv/versions/3.9.18/lib/python3.9/site-packages/torchgeometry/core/conversions.py')
+DEFAULT_MODEL='smpler_x_h32'
+OUT_FOLDER = '/home/user/app/demo_out'
+os.makedirs(OUT_FOLDER, exist_ok=True)
+# num_gpus = 1 if torch.cuda.is_available() else -1
+# print("!!!", torch.cuda.is_available())      
+# print(torch.cuda.device_count())   
+# print(torch.version.cuda)  
+# index = torch.cuda.current_device()
+# print(index)  
+# print(torch.cuda.get_device_name(index))
+# from main.inference import Inferer
+# inferer = Inferer(DEFAULT_MODEL, num_gpus, OUT_FOLDER)
+
+@spaces.GPU(enable_queue=True)
+def infer(image_input, in_threshold=0.5, num_people="Single person", render_mesh=False):
+    # num_gpus = 1 if torch.cuda.is_available() else -1
+    # print("!!!", torch.cuda.is_available())      
+    # print(torch.cuda.device_count())   
+    # print(torch.version.cuda)  
+    # index = torch.cuda.current_device()
+    # print(index)  
+    # print(torch.cuda.get_device_name(index))
+    # from main.inference import Inferer
+    # inferer = Inferer(DEFAULT_MODEL, num_gpus, OUT_FOLDER)
+    # os.system(f'rm -rf {OUT_FOLDER}/*')
+    # multi_person = False if (num_people == "Single person") else True
+    # cap = cv2.VideoCapture(video_input)
+    # fps = math.ceil(cap.get(5))
+    # width = int(cap.get(3))
+    # height = int(cap.get(4))
+    # fourcc = cv2.VideoWriter_fourcc(*'mp4v')
+    # video_path = osp.join(OUT_FOLDER, f'out.m4v')
+    # final_video_path = osp.join(OUT_FOLDER, f'out.mp4')
+    # video_output = cv2.VideoWriter(video_path, fourcc, fps, (width, height))
+    # success = 1
+    # frame = 0
+    # while success:
+    #     success, original_img = cap.read()
+    #     if not success:
+    #         break
+    #     frame += 1
+    #     img, mesh_paths, smplx_paths = inferer.infer(original_img, in_threshold, frame, multi_person, not(render_mesh))
+    #     video_output.write(img)
+    #     yield img, None, None, None
+    # cap.release()
+    # video_output.release()
+    # cv2.destroyAllWindows()
+    # os.system(f'ffmpeg -i {video_path} -c copy {final_video_path}')
+
+    # #Compress mesh and smplx files
+    # save_path_mesh = os.path.join(OUT_FOLDER, 'mesh')
+    # save_mesh_file = os.path.join(OUT_FOLDER, 'mesh.zip')
+    # os.makedirs(save_path_mesh, exist_ok= True)
+    # save_path_smplx = os.path.join(OUT_FOLDER, 'smplx')
+    # save_smplx_file = os.path.join(OUT_FOLDER, 'smplx.zip')
+    # os.makedirs(save_path_smplx, exist_ok= True)
+    # os.system(f'zip -r {save_mesh_file} {save_path_mesh}')
+    # os.system(f'zip -r {save_smplx_file} {save_path_smplx}')
+    # yield img, video_path, save_mesh_file, save_smplx_file
+    return image_input, "success"
+
+TITLE = '''<h1 align="center">PostoMETRO: Pose Token Enhanced Mesh Transformer for Robust 3D Human Mesh Recovery</h1>'''
+DESCRIPTION = '''
+<b>Official Gradio demo</b> for <b>PostoMETRO: Pose Token Enhanced Mesh Transformer for Robust 3D Human Mesh Recovery</b>.<br>
+<p>
+Note: You can drop a image at the panel (or select one of the examples) 
+to obtain the 3D parametric reconstructions of the detected humans.
+</p>
+'''
+
+with gr.Blocks(title="PostoMETRO", css=".gradio-container") as demo:
+
+    gr.Markdown(TITLE)
+    gr.Markdown(DESCRIPTION)
+
+    with gr.Row():
+        with gr.Column():
+            image_input = gr.Image(label="Input image", elem_classes="Image")
+            threshold = gr.Slider(0, 1.0, value=0.5, label='BBox detection threshold')
+            num_people = gr.Radio(
+                choices=["Single person", "Multiple people"],
+                value="Single person",
+                label="Number of people",
+                info="Choose how many people are there in the video. Choose 'single person' for faster inference.",
+                interactive=True,
+                scale=1,)
+            mesh_as_vertices = gr.Checkbox(
+                label="Render as mesh", 
+                info="By default, the estimated SMPL-X parameters are rendered as vertices for faster visualization. Check this option if you want to visualize meshes instead.",
+                interactive=True,
+                scale=1,)
+            send_button = gr.Button("Infer")
+        with gr.Column():
+            processed_frames = gr.Image(label="Last processed frame")
+            debug_textbox = gr.Textbox(label="Debug information")
+
+    # example_images = gr.Examples([])
+    send_button.click(fn=infer, inputs=[image_input, threshold, num_people, mesh_as_vertices], outputs=[processed_frames, debug_textbox])
+    # with gr.Row():
+    example_images = gr.Examples([
+        ['/home/user/app/assets/01.jpg'], 
+        ['/home/user/app/assets/02.jpg'], 
+        ['/home/user/app/assets/03.jpg'], 
+        ], 
+        inputs=[image_input, 0.5])
+
+#demo.queue()
+demo.queue().launch(debug=True)