reduced-3dgs 1.10.7__cp310-cp310-win_amd64.whl → 1.10.12__cp310-cp310-win_amd64.whl

reduced_3dgs/train.py

@@ -14,8 +14,12 @@ from reduced_3dgs.quantization import AbstractQuantizer
 from reduced_3dgs.prepare import modes, prepare_gaussians, prepare_trainer
 
 
-def prepare_training(sh_degree: int, source: str, device: str, mode: str, trainable_camera: bool = False, load_ply: str = None, load_camera: str = None, load_depth=False, with_scale_reg=False, quantize: bool = False, load_quantized: str = None, configs={}):
-    dataset = prepare_dataset(source=source, device=device, trainable_camera=trainable_camera, load_camera=load_camera, load_depth=load_depth)
+def prepare_training(
+        sh_degree: int, source: str, device: str, mode: str,
+        trainable_camera: bool = False, load_ply: str = None, load_camera: str = None,
+        load_mask=True, load_depth=True,
+        with_scale_reg=False, quantize: bool = False, load_quantized: str = None, configs={}):
+    dataset = prepare_dataset(source=source, device=device, trainable_camera=trainable_camera, load_camera=load_camera, load_mask=load_mask, load_depth=load_depth)
     gaussians = prepare_gaussians(sh_degree=sh_degree, source=source, device=device, trainable_camera=trainable_camera, load_ply=load_ply)
     trainer, quantizer = prepare_trainer(gaussians=gaussians, dataset=dataset, mode=mode, with_scale_reg=with_scale_reg, quantize=quantize, load_quantized=load_quantized, configs=configs)
     return dataset, gaussians, trainer, quantizer
@@ -23,26 +27,39 @@ def prepare_training(sh_degree: int, source: str, device: str, mode: str, traina
 
 def training(dataset: CameraDataset, gaussians: GaussianModel, trainer: AbstractTrainer, quantizer: AbstractQuantizer, destination: str, iteration: int, save_iterations: List[int], device: str, empty_cache_every_step=False):
     shutil.rmtree(os.path.join(destination, "point_cloud"), ignore_errors=True)  # remove the previous point cloud
-    pbar = tqdm(range(1, iteration+1))
+    pbar = tqdm(range(1, iteration+1), dynamic_ncols=True, desc="Training")
     epoch = list(range(len(dataset)))
     epoch_psnr = torch.empty(3, 0, device=device)
+    epoch_maskpsnr = torch.empty(3, 0, device=device)
     ema_loss_for_log = 0.0
     avg_psnr_for_log = 0.0
+    avg_maskpsnr_for_log = 0.0
     for step in pbar:
         epoch_idx = step % len(dataset)
         if epoch_idx == 0:
             avg_psnr_for_log = epoch_psnr.mean().item()
+            avg_maskpsnr_for_log = epoch_maskpsnr.mean().item()
             epoch_psnr = torch.empty(3, 0, device=device)
+            epoch_maskpsnr = torch.empty(3, 0, device=device)
             random.shuffle(epoch)
         idx = epoch[epoch_idx]
         loss, out = trainer.step(dataset[idx])
         if empty_cache_every_step:
             torch.cuda.empty_cache()
         with torch.no_grad():
+            ground_truth_image = dataset[idx].ground_truth_image
+            rendered_image = out["render"]
+            epoch_psnr = torch.concat([epoch_psnr, psnr(rendered_image, ground_truth_image)], dim=1)
+            if dataset[idx].ground_truth_image_mask is not None:
+                ground_truth_maskimage = ground_truth_image * dataset[idx].ground_truth_image_mask
+                rendered_maskimage = rendered_image * dataset[idx].ground_truth_image_mask
+                epoch_maskpsnr = torch.concat([epoch_maskpsnr, psnr(rendered_maskimage, ground_truth_maskimage)], dim=1)
             ema_loss_for_log = 0.4 * loss.item() + 0.6 * ema_loss_for_log
-            epoch_psnr = torch.concat([epoch_psnr, psnr(out["render"], dataset[idx].ground_truth_image)], dim=1)
             if step % 10 == 0:
-                pbar.set_postfix({'epoch': step // len(dataset), 'loss': ema_loss_for_log, 'psnr': avg_psnr_for_log, 'n': gaussians._xyz.shape[0]})
+                postfix = {'epoch': step // len(dataset), 'loss': ema_loss_for_log, 'psnr': avg_psnr_for_log, 'n': gaussians._xyz.shape[0]}
+                if avg_maskpsnr_for_log > 0:
+                    postfix['psnr (mask)'] = avg_maskpsnr_for_log
+                pbar.set_postfix(postfix)
         if step in save_iterations:
             save_path = os.path.join(destination, "point_cloud", "iteration_" + str(step))
             os.makedirs(save_path, exist_ok=True)
@@ -68,6 +85,7 @@ if __name__ == "__main__":
     parser.add_argument("-l", "--load_ply", default=None, type=str)
     parser.add_argument("--load_camera", default=None, type=str)
     parser.add_argument("--quantize", action='store_true')
+    parser.add_argument("--no_image_mask", action="store_true")
     parser.add_argument("--no_depth_data", action='store_true')
     parser.add_argument("--with_scale_reg", action="store_true")
     parser.add_argument("--load_quantized", default=None, type=str)
@@ -83,7 +101,9 @@ if __name__ == "__main__":
     configs = {o.split("=", 1)[0]: eval(o.split("=", 1)[1]) for o in args.option}
     dataset, gaussians, trainer, quantizer = prepare_training(
         sh_degree=args.sh_degree, source=args.source, device=args.device, mode=args.mode, trainable_camera="camera" in args.mode,
-        load_ply=args.load_ply, load_camera=args.load_camera, load_depth=not args.no_depth_data, with_scale_reg=args.with_scale_reg,
+        load_ply=args.load_ply, load_camera=args.load_camera,
+        load_mask=not args.no_image_mask, load_depth=not args.no_depth_data,
+        with_scale_reg=args.with_scale_reg,
         quantize=args.quantize, load_quantized=args.load_quantized, configs=configs)
     dataset.save_cameras(os.path.join(args.destination, "cameras.json"))
     torch.cuda.empty_cache()

{reduced_3dgs-1.10.7.dist-info → reduced_3dgs-1.10.12.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: reduced_3dgs
-Version: 1.10.7
+Version: 1.10.12
 Summary: Refactored code for the paper "Reducing the Memory Footprint of 3D Gaussian Splatting"
 Home-page: https://github.com/yindaheng98/reduced-3dgs
 Author: yindaheng98
@@ -35,6 +35,7 @@ This repository contains the **refactored Python code for [Reduced-3DGS](https:/
 
 * [Pytorch](https://pytorch.org/) (v2.4 or higher recommended)
 * [CUDA Toolkit](https://developer.nvidia.com/cuda-12-4-0-download-archive) (12.4 recommended, should match with PyTorch version)
+* (Optional) [cuML](https://github.com/rapidsai/cuml) for faster vector quantization
 
 (Optional) If you have trouble with [`gaussian-splatting`](https://github.com/yindaheng98/gaussian-splatting), try to install it from source:
 ```sh

{reduced_3dgs-1.10.7.dist-info → reduced_3dgs-1.10.12.dist-info}/RECORD

@@ -2,13 +2,13 @@ reduced_3dgs/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 reduced_3dgs/combinations.py,sha256=dRrtTIQLggUP22Olp0DVSlD0C8YDgnrpTlrCcGZyWM0,9441
 reduced_3dgs/prepare.py,sha256=MFUUckRHKfgcva4ZOBxfPFyE95N-OlCQLplpmEPuzOk,4440
 reduced_3dgs/quantize.py,sha256=BVqBb2tQgiP3hap5-OByD8VELtJJGfEeFzaVFyzCJZU,2572
-reduced_3dgs/train.py,sha256=yRQPQv-hTOBQN-tqGHYs2aIZ0AbWq158CXpthYN2cfw,5666
-reduced_3dgs/diff_gaussian_rasterization/_C.cp310-win_amd64.pyd,sha256=umncdQpRjdTtR0dzSn1EW-ZG_gkEweJvFOi23QxGOWM,1610752
+reduced_3dgs/train.py,sha256=P9GCoEVl_VGldKuA3ycj1nea5rTc3xqu_f02a8oe-Lc,6734
+reduced_3dgs/diff_gaussian_rasterization/_C.cp310-win_amd64.pyd,sha256=T3bwC1BQvTG47Ha-VCGjtTOPU81HYv7TCsa0lYAqVF4,1610752
 reduced_3dgs/diff_gaussian_rasterization/__init__.py,sha256=oV6JjTc-50MscX4XHeIWSgLr3l8Y25knBIs-0gRbJr4,7932
 reduced_3dgs/importance/__init__.py,sha256=neJsbY5cLikEGBQGdR4MjwCQ5VWVikT1357DwL0EtWU,289
 reduced_3dgs/importance/combinations.py,sha256=F9IYDZ6iquZw5Djn2An88dlp2MUGieAyuZyVaDZdSts,2962
 reduced_3dgs/importance/trainer.py,sha256=Sj4ORvoYtFT7z3hifzFZDfhFyqumHraXyk3vMVtk0AU,12661
-reduced_3dgs/importance/diff_gaussian_rasterization/_C.cp310-win_amd64.pyd,sha256=o6a3wL0bQzhmpj3qIk3g_6T80xPthL1bO9kJlcuiATs,1302016
+reduced_3dgs/importance/diff_gaussian_rasterization/_C.cp310-win_amd64.pyd,sha256=TLEsXJXzHr3fYCzE-P17gGkpoQ_X80LsvqCeT9vzchQ,1302016
 reduced_3dgs/importance/diff_gaussian_rasterization/__init__.py,sha256=Tix8auyXBb_QFQtXrV3sLE9kdnl5zgHH0BbqcFzDp84,12850
 reduced_3dgs/pruning/__init__.py,sha256=E_YxJ9cDV_B6EJbYUBEcuRYMIht_C72rI1VJUXFCLpM,201
 reduced_3dgs/pruning/combinations.py,sha256=xO39d08DEsDnKI5np_1xQ4H29O486Q_cThLfWhlH810,2385
@@ -21,9 +21,9 @@ reduced_3dgs/quantization/wrapper.py,sha256=cyXqfJgo9b3fS7DYXxOk5LmQudvrEhweOebF
 reduced_3dgs/shculling/__init__.py,sha256=nP2BejDCUdCmJNRbg0hfhHREO6jyZXwIcRiw6ttVgqo,149
 reduced_3dgs/shculling/gaussian_model.py,sha256=f8QWaL09vaV9Tcf6Dngjg_Fmk1wTQPAjWhuhI_N02Y8,2877
 reduced_3dgs/shculling/trainer.py,sha256=9hwR77djhZpyf-URhwKHjnLbe0ZAOS-DIw58RzkcHXQ,6369
-reduced_3dgs/simple_knn/_C.cp310-win_amd64.pyd,sha256=6DC6PsctGeSGC1i_ruHtFyDnWilQ9smDsz2ZhROCJeE,1248768
-reduced_3dgs-1.10.7.dist-info/licenses/LICENSE.md,sha256=LQ4_LAqlncGkg_mQy5ykMAFtQDSPB0eKmIEtBut0yjw,4916
-reduced_3dgs-1.10.7.dist-info/METADATA,sha256=XffxXiROEKO9jeTVmfiZcWBAHK0cgSS9B6ZKvY5wT5k,12317
-reduced_3dgs-1.10.7.dist-info/WHEEL,sha256=KUuBC6lxAbHCKilKua8R9W_TM71_-9Sg5uEP3uDWcoU,101
-reduced_3dgs-1.10.7.dist-info/top_level.txt,sha256=PpU5aT3-baSCdqCtTaZknoB32H93UeKCkYDkRCCZMEI,13
-reduced_3dgs-1.10.7.dist-info/RECORD,,
+reduced_3dgs/simple_knn/_C.cp310-win_amd64.pyd,sha256=elGT2b5IdsO5qGhW0XBj_5qdUyJBNveMgEM6yVdoHiY,1248768
+reduced_3dgs-1.10.12.dist-info/licenses/LICENSE.md,sha256=LQ4_LAqlncGkg_mQy5ykMAFtQDSPB0eKmIEtBut0yjw,4916
+reduced_3dgs-1.10.12.dist-info/METADATA,sha256=7cQgH63LmWATezhRqXDPA6ytT_Ld9mYXKppGqvR8QTw,12404
+reduced_3dgs-1.10.12.dist-info/WHEEL,sha256=KUuBC6lxAbHCKilKua8R9W_TM71_-9Sg5uEP3uDWcoU,101
+reduced_3dgs-1.10.12.dist-info/top_level.txt,sha256=PpU5aT3-baSCdqCtTaZknoB32H93UeKCkYDkRCCZMEI,13
+reduced_3dgs-1.10.12.dist-info/RECORD,,