Hi, thanks for the excellent work!
I’m encountering an issue where the scene does not render as expected. After running the project, no visual output appears
this my terminal output:
yt@yts:/media/yt/data4t/lingbot-map$ python demo.py --model_path ./lingbot-map-long.pt --image_folder example/courthouse --mask_sky Loading 286 images... Loading images: 100%|████████████████████████| 286/286 [00:00<00:00, 933.20it/s] Preprocessed images to 518x294 using canonical crop mode Building model... pretrained_path: Failed to load pretrained weights: [Errno 2] No such file or directory: '' Loading checkpoint: ./lingbot-map-long.pt Checkpoint loaded. Total load time: 12.5s Casting aggregator to torch.bfloat16 (heads kept in fp32) Input: 286 frames, shape (286, 3, 294, 518) Mode: streaming GPU mem after load: alloc=3.34 GB, reserved=3.38 GB Running streaming inference (dtype=torch.bfloat16)... Streaming inference: 100%|███████████████████████████████████████████████████████████████████████| 286/286 [00:47<00:00, 5.81it/s] Inference done in 49.9s GPU peak during inference: 13.74 GB (reserved peak 14.40 GB) Moving results to CPU... ╭────── viser (listening *:8080) ───────╮ │ ╷ │ │ HTTP │ http://localhost:8080 │ │ Websocket │ ws://localhost:8080 │ │ ╵ │ ╰───────────────────────────────────────╯ Generating sky masks from image array... 100%|████████████████████████████████████████████████████████████████████████████████████████████| 286/286 [01:33<00:00, 3.07it/s] Sky segmentation applied successfully 3D viewer at http://localhost:8080 (viser) Connection opened (0, 1 total), 3784 persistent messages
Hi, thanks for the excellent work!
I’m encountering an issue where the scene does not render as expected. After running the project, no visual output appears
this my terminal output:
yt@yts:/media/yt/data4t/lingbot-map$ python demo.py --model_path ./lingbot-map-long.pt --image_folder example/courthouse --mask_sky Loading 286 images... Loading images: 100%|████████████████████████| 286/286 [00:00<00:00, 933.20it/s] Preprocessed images to 518x294 using canonical crop mode Building model... pretrained_path: Failed to load pretrained weights: [Errno 2] No such file or directory: '' Loading checkpoint: ./lingbot-map-long.pt Checkpoint loaded. Total load time: 12.5s Casting aggregator to torch.bfloat16 (heads kept in fp32) Input: 286 frames, shape (286, 3, 294, 518) Mode: streaming GPU mem after load: alloc=3.34 GB, reserved=3.38 GB Running streaming inference (dtype=torch.bfloat16)... Streaming inference: 100%|███████████████████████████████████████████████████████████████████████| 286/286 [00:47<00:00, 5.81it/s] Inference done in 49.9s GPU peak during inference: 13.74 GB (reserved peak 14.40 GB) Moving results to CPU... ╭────── viser (listening *:8080) ───────╮ │ ╷ │ │ HTTP │ http://localhost:8080 │ │ Websocket │ ws://localhost:8080 │ │ ╵ │ ╰───────────────────────────────────────╯ Generating sky masks from image array... 100%|████████████████████████████████████████████████████████████████████████████████████████████| 286/286 [01:33<00:00, 3.07it/s] Sky segmentation applied successfully 3D viewer at http://localhost:8080 (viser) Connection opened (0, 1 total), 3784 persistent messages