init project

app.py

@@ -521,25 +521,25 @@ def get_reconstructed_scene(outdir, filelist, schedule, niter, min_conf_thr,
     #     imgs.append(rgb(depths[i]))
     #     imgs.append(rgb(confs[i]))
 
-    return scene, outfile#, imgs
+    return scene, outfile #, imgs
 
-@spaces.GPU(duration=180)
-def get_3D_object_from_scene(outdir, text, threshold, scene, min_conf_thr, as_pointcloud, 
-                 mask_sky, clean_depth, transparent_cams, cam_size):
+# @spaces.GPU(duration=180)
+# def get_3D_object_from_scene(outdir, text, threshold, scene, min_conf_thr, as_pointcloud, 
+#                  mask_sky, clean_depth, transparent_cams, cam_size):
     
-    device = 'cuda' if torch.cuda.is_available() else 'cpu'
+#     device = 'cuda' if torch.cuda.is_available() else 'cpu'
     
-    texts = [text]
-    inputs = pe3r.siglip_tokenizer(text=texts, padding="max_length", return_tensors="pt")
-    inputs = {key: value.to(device) for key, value in inputs.items()}
-    with torch.no_grad():
-        text_feats =pe3r.siglip.get_text_features(**inputs)
-        text_feats = text_feats / text_feats.norm(dim=-1, keepdim=True)
-    scene.render_image(text_feats, threshold)
-    scene.ori_imgs = scene.rendered_imgs
-    outfile = get_3D_model_from_scene(outdir, scene, min_conf_thr, as_pointcloud, mask_sky,
-                                      clean_depth, transparent_cams, cam_size)
-    return outfile
+#     texts = [text]
+#     inputs = pe3r.siglip_tokenizer(text=texts, padding="max_length", return_tensors="pt")
+#     inputs = {key: value.to(device) for key, value in inputs.items()}
+#     with torch.no_grad():
+#         text_feats =pe3r.siglip.get_text_features(**inputs)
+#         text_feats = text_feats / text_feats.norm(dim=-1, keepdim=True)
+#     scene.render_image(text_feats, threshold)
+#     scene.ori_imgs = scene.rendered_imgs
+#     outfile = get_3D_model_from_scene(outdir, scene, min_conf_thr, as_pointcloud, mask_sky,
+#                                       clean_depth, transparent_cams, cam_size)
+#     return outfile
 
 
 def set_scenegraph_options(inputfiles, winsize, refid, scenegraph_type):
@@ -566,7 +566,7 @@ def set_scenegraph_options(inputfiles, winsize, refid, scenegraph_type):
 with tempfile.TemporaryDirectory(suffix='pe3r_gradio_demo') as tmpdirname:
     recon_fun = functools.partial(get_reconstructed_scene, tmpdirname)
     # model_from_scene_fun = functools.partial(get_3D_model_from_scene, tmpdirname)
-    get_3D_object_from_scene_fun = functools.partial(get_3D_object_from_scene, tmpdirname)
+    # get_3D_object_from_scene_fun = functools.partial(get_3D_object_from_scene, tmpdirname)
 
     with gradio.Blocks(css=""".gradio-container {margin: 0 !important; min-width: 100%};""", title="PE3R Demo") as demo:
         # scene state is save so that you can change conf_thr, cam_size... without rerunning the inference
@@ -652,8 +652,8 @@ with tempfile.TemporaryDirectory(suffix='pe3r_gradio_demo') as tmpdirname:
             #                         inputs=[scene, min_conf_thr, as_pointcloud, mask_sky,
             #                                 clean_depth, transparent_cams, cam_size],
             #                         outputs=outmodel)
-            find_btn.click(fn=get_3D_object_from_scene_fun,
-                                inputs=[text_input, threshold, scene, min_conf_thr, as_pointcloud, mask_sky,
-                                        clean_depth, transparent_cams, cam_size],
-                            outputs=outmodel)
+            # find_btn.click(fn=get_3D_object_from_scene_fun,
+            #                     inputs=[text_input, threshold, scene, min_conf_thr, as_pointcloud, mask_sky,
+            #                             clean_depth, transparent_cams, cam_size],
+            #                 outputs=outmodel)
     demo.launch(show_error=True, share=None, server_name=None, server_port=None)