init project

app.py

@@ -519,21 +519,21 @@ def get_reconstructed_scene(outdir, filelist, schedule, niter, min_conf_thr,
 
     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):
     
-#     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('cuda') 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):
@@ -560,7 +560,7 @@ 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
@@ -646,8 +646,8 @@ 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)