reduced-3dgs 1.10.1__tar.gz → 1.10.2__tar.gz

{reduced_3dgs-1.10.1 → reduced_3dgs-1.10.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: reduced_3dgs
-Version: 1.10.1
+Version: 1.10.2
 Summary: Refactored code for the paper "Reducing the Memory Footprint of 3D Gaussian Splatting"
 Home-page: https://github.com/yindaheng98/reduced-3dgs
 Author: yindaheng98

reduced_3dgs-1.10.2/reduced_3dgs/prepare.py

@@ -0,0 +1,105 @@
+from gaussian_splatting import GaussianModel
+from gaussian_splatting.dataset import CameraDataset
+from gaussian_splatting.dataset.colmap import colmap_init
+from gaussian_splatting.trainer import AbstractTrainer
+from gaussian_splatting.trainer.extensions import ScaleRegularizeTrainerWrapper
+from reduced_3dgs.quantization import VectorQuantizeTrainerWrapper
+from reduced_3dgs.shculling import VariableSHGaussianModel, SHCullingTrainer
+from reduced_3dgs.pruning import PruningTrainer
+from reduced_3dgs.combinations import PrunerInDensifyTrainer, SHCullingDensificationTrainer, SHCullingPruningTrainer, SHCullingPrunerInDensifyTrainer
+from reduced_3dgs.combinations import CameraTrainableVariableSHGaussianModel, CameraSHCullingTrainer, CameraPruningTrainer
+from reduced_3dgs.combinations import CameraPrunerInDensifyTrainer, CameraSHCullingDensifyTrainer, CameraSHCullingPruningTrainer, CameraSHCullingPruningDensifyTrainer
+
+
+def prepare_gaussians(sh_degree: int, source: str, device: str, trainable_camera: bool = False, load_ply: str = None) -> GaussianModel:
+    if trainable_camera:
+        gaussians = CameraTrainableVariableSHGaussianModel(sh_degree).to(device)
+        gaussians.load_ply(load_ply) if load_ply else colmap_init(gaussians, source)
+    else:
+        gaussians = VariableSHGaussianModel(sh_degree).to(device)
+        gaussians.load_ply(load_ply) if load_ply else colmap_init(gaussians, source)
+    return gaussians
+
+
+modes = {
+    "shculling": SHCullingTrainer,
+    "pruning": PruningTrainer,
+    "densify-pruning": PrunerInDensifyTrainer,
+    "densify-shculling": SHCullingDensificationTrainer,
+    "prune-shculling": SHCullingPruningTrainer,
+    "densify-prune-shculling": SHCullingPrunerInDensifyTrainer,
+    "camera-shculling": CameraSHCullingTrainer,
+    "camera-pruning": CameraPruningTrainer,
+    "camera-densify-pruning": CameraPrunerInDensifyTrainer,
+    "camera-densify-shculling": CameraSHCullingDensifyTrainer,
+    "camera-prune-shculling": CameraSHCullingPruningTrainer,
+    "camera-densify-prune-shculling": CameraSHCullingPruningDensifyTrainer,
+}
+
+
+def prepare_quantizer(
+        gaussians: GaussianModel,
+        scene_extent: float,
+        dataset: CameraDataset,
+        base_constructor,
+        load_quantized: str = None,
+
+        num_clusters=256,
+        num_clusters_rotation_re=None,
+        num_clusters_rotation_im=None,
+        num_clusters_opacity=None,
+        num_clusters_scaling=None,
+        num_clusters_features_dc=None,
+        num_clusters_features_rest=[],
+
+        quantize_from_iter=5000,
+        quantize_until_iter=30000,
+        quantize_interval=1000,
+        **configs):
+    trainer = VectorQuantizeTrainerWrapper(
+        base_constructor(
+            gaussians,
+            scene_extent=scene_extent,
+            dataset=dataset,
+            **configs
+        ),
+
+        num_clusters=num_clusters,
+        num_clusters_rotation_re=num_clusters_rotation_re,
+        num_clusters_rotation_im=num_clusters_rotation_im,
+        num_clusters_opacity=num_clusters_opacity,
+        num_clusters_scaling=num_clusters_scaling,
+        num_clusters_features_dc=num_clusters_features_dc,
+        num_clusters_features_rest=num_clusters_features_rest,
+
+        quantize_from_iter=quantize_from_iter,
+        quantize_until_iter=quantize_until_iter,
+        quantize_interval=quantize_interval,
+    )
+    if load_quantized:
+        trainer.quantizer.load_quantized(load_quantized)
+    return trainer, trainer.quantizer
+
+
+def prepare_trainer(gaussians: GaussianModel, dataset: CameraDataset, mode: str, with_scale_reg=False, quantize: bool = False, load_quantized: str = None, configs={}) -> AbstractTrainer:
+    constructor = modes[mode]
+    if with_scale_reg:
+        constructor = lambda *args, **kwargs: ScaleRegularizeTrainerWrapper(modes[mode], *args, **kwargs)
+    if quantize:
+        trainer, quantizer = prepare_quantizer(
+            gaussians,
+            scene_extent=dataset.scene_extent(),
+            dataset=dataset,
+            base_constructor=modes[mode],
+            load_quantized=load_quantized,
+            **configs
+        )
+    else:
+        trainer = constructor(
+            gaussians,
+            scene_extent=dataset.scene_extent(),
+            dataset=dataset,
+            **configs
+        )
+        quantizer = None
+    return trainer, quantizer

reduced_3dgs-1.10.2/reduced_3dgs/train.py

@@ -0,0 +1,93 @@
+import os
+import random
+import shutil
+from typing import List
+import torch
+from tqdm import tqdm
+from gaussian_splatting import GaussianModel
+from gaussian_splatting.dataset import CameraDataset
+from gaussian_splatting.utils import psnr
+from gaussian_splatting.trainer import AbstractTrainer
+from gaussian_splatting.prepare import prepare_dataset
+from gaussian_splatting.train import save_cfg_args
+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)
+    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
+
+
+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))
+    epoch = list(range(len(dataset)))
+    epoch_psnr = torch.empty(3, 0, device=device)
+    ema_loss_for_log = 0.0
+    avg_psnr_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()
+            epoch_psnr = 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():
+            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]})
+        if step in save_iterations:
+            save_path = os.path.join(destination, "point_cloud", "iteration_" + str(step))
+            os.makedirs(save_path, exist_ok=True)
+            gaussians.save_ply(os.path.join(save_path, "point_cloud.ply"))
+            dataset.save_cameras(os.path.join(destination, "cameras.json"))
+            if quantizer:
+                quantizer.save_quantized(gaussians, os.path.join(save_path, "point_cloud_quantized.ply"))
+    save_path = os.path.join(destination, "point_cloud", "iteration_" + str(iteration))
+    os.makedirs(save_path, exist_ok=True)
+    gaussians.save_ply(os.path.join(save_path, "point_cloud.ply"))
+    dataset.save_cameras(os.path.join(destination, "cameras.json"))
+    if quantizer:
+        quantizer.save_quantized(gaussians, os.path.join(save_path, "point_cloud_quantized.ply"))
+
+
+if __name__ == "__main__":
+    from argparse import ArgumentParser
+    parser = ArgumentParser()
+    parser.add_argument("--sh_degree", default=3, type=int)
+    parser.add_argument("-s", "--source", required=True, type=str)
+    parser.add_argument("-d", "--destination", required=True, type=str)
+    parser.add_argument("-i", "--iteration", default=30000, type=int)
+    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_depth_data", action='store_true')
+    parser.add_argument("--with_scale_reg", action="store_true")
+    parser.add_argument("--load_quantized", default=None, type=str)
+    parser.add_argument("--mode", choices=list(modes), default="densify-prune-shculling")
+    parser.add_argument("--save_iterations", nargs="+", type=int, default=[7000, 30000])
+    parser.add_argument("--device", default="cuda", type=str)
+    parser.add_argument("--empty_cache_every_step", action='store_true')
+    parser.add_argument("-o", "--option", default=[], action='append', type=str)
+    args = parser.parse_args()
+    save_cfg_args(args.destination, args.sh_degree, args.source)
+    torch.autograd.set_detect_anomaly(False)
+
+    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,
+        quantize=args.quantize, load_quantized=args.load_quantized, configs=configs)
+    dataset.save_cameras(os.path.join(args.destination, "cameras.json"))
+    torch.cuda.empty_cache()
+    training(
+        dataset=dataset, gaussians=gaussians, trainer=trainer, quantizer=quantizer,
+        destination=args.destination, iteration=args.iteration, save_iterations=args.save_iterations,
+        device=args.device)

{reduced_3dgs-1.10.1 → reduced_3dgs-1.10.2}/reduced_3dgs.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: reduced_3dgs
-Version: 1.10.1
+Version: 1.10.2
 Summary: Refactored code for the paper "Reducing the Memory Footprint of 3D Gaussian Splatting"
 Home-page: https://github.com/yindaheng98/reduced-3dgs
 Author: yindaheng98

{reduced_3dgs-1.10.1 → reduced_3dgs-1.10.2}/reduced_3dgs.egg-info/SOURCES.txt

@@ -3,6 +3,7 @@ README.md
 setup.py
 reduced_3dgs/__init__.py
 reduced_3dgs/combinations.py
+reduced_3dgs/prepare.py
 reduced_3dgs/quantize.py
 reduced_3dgs/train.py
 reduced_3dgs.egg-info/PKG-INFO

{reduced_3dgs-1.10.1 → reduced_3dgs-1.10.2}/setup.py

@@ -60,7 +60,7 @@ if os.name == 'nt':
 
 setup(
     name="reduced_3dgs",
-    version='1.10.1',
+    version='1.10.2',
     author='yindaheng98',
     author_email='yindaheng98@gmail.com',
     url='https://github.com/yindaheng98/reduced-3dgs',

reduced_3dgs-1.10.1/reduced_3dgs/train.py

@@ -1,200 +0,0 @@
-import os
-import random
-import shutil
-from typing import List, Tuple
-import torch
-from tqdm import tqdm
-from gaussian_splatting import GaussianModel
-from gaussian_splatting.dataset import CameraDataset
-from gaussian_splatting.utils import psnr
-from gaussian_splatting.dataset.colmap import colmap_init
-from gaussian_splatting.trainer import AbstractTrainer
-from gaussian_splatting.trainer.extensions import ScaleRegularizeTrainerWrapper
-from gaussian_splatting.train import prepare_dataset, save_cfg_args
-from reduced_3dgs.quantization import AbstractQuantizer, VectorQuantizeTrainerWrapper
-from reduced_3dgs.shculling import VariableSHGaussianModel, SHCullingTrainer
-from reduced_3dgs.pruning import PruningTrainer
-from reduced_3dgs.combinations import PrunerInDensifyTrainer, SHCullingDensificationTrainer, SHCullingPruningTrainer, SHCullingPrunerInDensifyTrainer
-from reduced_3dgs.combinations import CameraTrainableVariableSHGaussianModel, CameraSHCullingTrainer, CameraPruningTrainer
-from reduced_3dgs.combinations import CameraPrunerInDensifyTrainer, CameraSHCullingDensifyTrainer, CameraSHCullingPruningTrainer, CameraSHCullingPruningDensifyTrainer
-
-
-basemodes = {
-    "shculling": SHCullingTrainer,
-    "pruning": PruningTrainer,
-    "densify-pruning": PrunerInDensifyTrainer,
-    "densify-shculling": SHCullingDensificationTrainer,
-    "prune-shculling": SHCullingPruningTrainer,
-    "densify-prune-shculling": SHCullingPrunerInDensifyTrainer,
-}
-cameramodes = {
-    "camera-shculling": CameraSHCullingTrainer,
-    "camera-pruning": CameraPruningTrainer,
-    "camera-densify-pruning": CameraPrunerInDensifyTrainer,
-    "camera-densify-shculling": CameraSHCullingDensifyTrainer,
-    "camera-prune-shculling": CameraSHCullingPruningTrainer,
-    "camera-densify-prune-shculling": CameraSHCullingPruningDensifyTrainer,
-}
-
-
-def prepare_quantizer(
-        gaussians: GaussianModel,
-        scene_extent: float,
-        dataset: CameraDataset,
-        base_constructor,
-        load_quantized: str = None,
-
-        num_clusters=256,
-        num_clusters_rotation_re=None,
-        num_clusters_rotation_im=None,
-        num_clusters_opacity=None,
-        num_clusters_scaling=None,
-        num_clusters_features_dc=None,
-        num_clusters_features_rest=[],
-
-        quantize_from_iter=5000,
-        quantize_until_iter=30000,
-        quantize_interval=1000,
-        **configs):
-    trainer = VectorQuantizeTrainerWrapper(
-        base_constructor(
-            gaussians,
-            scene_extent=scene_extent,
-            dataset=dataset,
-            **configs
-        ),
-
-        num_clusters=num_clusters,
-        num_clusters_rotation_re=num_clusters_rotation_re,
-        num_clusters_rotation_im=num_clusters_rotation_im,
-        num_clusters_opacity=num_clusters_opacity,
-        num_clusters_scaling=num_clusters_scaling,
-        num_clusters_features_dc=num_clusters_features_dc,
-        num_clusters_features_rest=num_clusters_features_rest,
-
-        quantize_from_iter=quantize_from_iter,
-        quantize_until_iter=quantize_until_iter,
-        quantize_interval=quantize_interval,
-    )
-    if load_quantized:
-        trainer.quantizer.load_quantized(load_quantized)
-    return trainer, trainer.quantizer
-
-
-def prepare_gaussians(sh_degree: int, source: str, device: str, trainable_camera: bool = False, load_ply: str = None) -> Tuple[CameraDataset, GaussianModel, AbstractTrainer]:
-    if trainable_camera:
-        gaussians = CameraTrainableVariableSHGaussianModel(sh_degree).to(device)
-        gaussians.load_ply(load_ply) if load_ply else colmap_init(gaussians, source)
-    else:
-        gaussians = VariableSHGaussianModel(sh_degree).to(device)
-        gaussians.load_ply(load_ply) if load_ply else colmap_init(gaussians, source)
-    return gaussians
-
-
-def prepare_trainer(gaussians: GaussianModel, dataset: CameraDataset, mode: str, with_scale_reg=False, quantize: bool = False, load_quantized: str = None, configs={}) -> AbstractTrainer:
-    if mode in basemodes:
-        modes = basemodes
-    elif mode in cameramodes:
-        modes = cameramodes
-    else:
-        raise ValueError(f"Unknown mode: {mode}")
-    constructor = modes[mode]
-    if with_scale_reg:
-        constructor = lambda *args, **kwargs: ScaleRegularizeTrainerWrapper(modes[mode], *args, **kwargs)
-    if quantize:
-        trainer, quantizer = prepare_quantizer(
-            gaussians,
-            scene_extent=dataset.scene_extent(),
-            dataset=dataset,
-            base_constructor=modes[mode],
-            load_quantized=load_quantized,
-            **configs
-        )
-    else:
-        trainer = constructor(
-            gaussians,
-            scene_extent=dataset.scene_extent(),
-            dataset=dataset,
-            **configs
-        )
-        quantizer = None
-    return trainer, quantizer
-
-
-def prepare_training(sh_degree: int, source: str, device: str, mode: str, load_ply: str = None, load_camera: str = None, load_depth=False, with_scale_reg=False, quantize: bool = False, load_quantized: str = None, configs={}) -> Tuple[CameraDataset, GaussianModel, AbstractTrainer]:
-    dataset = prepare_dataset(source=source, device=device, trainable_camera=mode in cameramodes, load_camera=load_camera, load_depth=load_depth)
-    gaussians = prepare_gaussians(sh_degree=sh_degree, source=source, device=device, trainable_camera=mode in cameramodes, 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
-
-
-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))
-    epoch = list(range(len(dataset)))
-    epoch_psnr = torch.empty(3, 0, device=device)
-    ema_loss_for_log = 0.0
-    avg_psnr_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()
-            epoch_psnr = 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():
-            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]})
-        if step in save_iterations:
-            save_path = os.path.join(destination, "point_cloud", "iteration_" + str(step))
-            os.makedirs(save_path, exist_ok=True)
-            gaussians.save_ply(os.path.join(save_path, "point_cloud.ply"))
-            dataset.save_cameras(os.path.join(destination, "cameras.json"))
-            if quantizer:
-                quantizer.save_quantized(gaussians, os.path.join(save_path, "point_cloud_quantized.ply"))
-    save_path = os.path.join(destination, "point_cloud", "iteration_" + str(iteration))
-    os.makedirs(save_path, exist_ok=True)
-    gaussians.save_ply(os.path.join(save_path, "point_cloud.ply"))
-    dataset.save_cameras(os.path.join(destination, "cameras.json"))
-    if quantizer:
-        quantizer.save_quantized(gaussians, os.path.join(save_path, "point_cloud_quantized.ply"))
-
-
-if __name__ == "__main__":
-    from argparse import ArgumentParser, Namespace
-    parser = ArgumentParser()
-    parser.add_argument("--sh_degree", default=3, type=int)
-    parser.add_argument("-s", "--source", required=True, type=str)
-    parser.add_argument("-d", "--destination", required=True, type=str)
-    parser.add_argument("-i", "--iteration", default=30000, type=int)
-    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_depth_data", action='store_true')
-    parser.add_argument("--with_scale_reg", action="store_true")
-    parser.add_argument("--load_quantized", default=None, type=str)
-    parser.add_argument("--mode", choices=list(basemodes.keys()) + list(cameramodes.keys()), default="densify-prune-shculling")
-    parser.add_argument("--save_iterations", nargs="+", type=int, default=[7000, 30000])
-    parser.add_argument("--device", default="cuda", type=str)
-    parser.add_argument("--empty_cache_every_step", action='store_true')
-    parser.add_argument("-o", "--option", default=[], action='append', type=str)
-    args = parser.parse_args()
-    save_cfg_args(args.destination, args.sh_degree, args.source)
-    torch.autograd.set_detect_anomaly(False)
-
-    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,
-        load_ply=args.load_ply, load_camera=args.load_camera, 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()
-    training(
-        dataset=dataset, gaussians=gaussians, trainer=trainer, quantizer=quantizer,
-        destination=args.destination, iteration=args.iteration, save_iterations=args.save_iterations,
-        device=args.device)