init project

app.py

@@ -467,15 +467,11 @@ def get_reconstructed_scene(outdir, filelist, schedule, niter, min_conf_thr,
     elif scenegraph_type == "oneref":
         scenegraph_type = scenegraph_type + "-" + str(refid)
 
-    print('0')
     pairs = make_pairs(imgs, scene_graph=scenegraph_type, prefilter=None, symmetrize=True)
-    print('a')
     output = inference(pairs, pe3r.mast3r, device, batch_size=1, verbose=not silent)
-    print('b')
     mode = GlobalAlignerMode.PointCloudOptimizer if len(imgs) > 2 else GlobalAlignerMode.PairViewer
     scene_1 = global_aligner(output, cog_seg_maps, rev_cog_seg_maps, cog_feats, device=device, mode=mode, verbose=not silent)
     lr = 0.01
-    print('c')
     # if mode == GlobalAlignerMode.PointCloudOptimizer:
     loss = scene_1.compute_global_alignment(tune_flg=True, init='mst', niter=niter, schedule=schedule, lr=lr)
 
@@ -527,6 +523,8 @@ def get_reconstructed_scene(outdir, filelist, schedule, niter, min_conf_thr,
 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'
+    
     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()}