UniqAI/gaussian-splatting
1
0
Fork 0
mirror of https://github.com/graphdeco-inria/gaussian-splatting synced 2024-11-21 15:57:45 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Nice fixed output

Browse Source
This commit is contained in:
bkerbl 2023-07-05 11:56:17 +02:00
parent 43e42bd20f
commit 45a9877ac4
2 changed files with 40 additions and 37 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
SIBR_viewers_windows

@ -1 +1 @@
Subproject commit f9b5d03bc86c8fabd8d7a26fabff91129618b4ce
Subproject commit 71ced0023fd0c0aaaa83bb1ab32bce1d4ed630c7

75
metrics.py
View File

@ -30,51 +30,54 @@ def evaluate(model_paths):
per_view_dict_polytopeonly = {}
for scene_dir in model_paths:
print("Scene:", scene_dir)
full_dict[scene_dir] = {}
per_view_dict[scene_dir] = {}
full_dict_polytopeonly[scene_dir] = {}
per_view_dict_polytopeonly[scene_dir] = {}
try:
print("\nScene:", scene_dir)
full_dict[scene_dir] = {}
per_view_dict[scene_dir] = {}
full_dict_polytopeonly[scene_dir] = {}
per_view_dict_polytopeonly[scene_dir] = {}
test_dir = Path(scene_dir) / "test"
test_dir = Path(scene_dir) / "test"
for method in os.listdir(test_dir):
print("Method:", method)
for method in os.listdir(test_dir):
print("Method:", method)
full_dict[scene_dir][method] = {}
per_view_dict[scene_dir][method] = {}
full_dict_polytopeonly[scene_dir][method] = {}
per_view_dict_polytopeonly[scene_dir][method] = {}
full_dict[scene_dir][method] = {}
per_view_dict[scene_dir][method] = {}
full_dict_polytopeonly[scene_dir][method] = {}
per_view_dict_polytopeonly[scene_dir][method] = {}
method_dir = test_dir / method
gt_dir = method_dir/ "gt"
renders_dir = method_dir / "renders"
renders, gts, image_names = readImages(renders_dir, gt_dir)
method_dir = test_dir / method
gt_dir = method_dir/ "gt"
renders_dir = method_dir / "renders"
renders, gts, image_names = readImages(renders_dir, gt_dir)
ssims = []
psnrs = []
lpipss = []
ssims = []
psnrs = []
lpipss = []
for idx in tqdm(range(len(renders)), desc="Metric evaluation progress"):
ssims.append(ssim(renders[idx], gts[idx]))
psnrs.append(psnr(renders[idx], gts[idx]))
lpipss.append(lpips(renders[idx], gts[idx], net_type='vgg'))
for idx in tqdm(range(len(renders)), desc="Metric evaluation progress"):
ssims.append(ssim(renders[idx], gts[idx]))
psnrs.append(psnr(renders[idx], gts[idx]))
lpipss.append(lpips(renders[idx], gts[idx], net_type='vgg'))
print("SSIM: {}".format(torch.tensor(ssims).mean()))
print("PSNR: {}".format(torch.tensor(psnrs).mean()))
print("LPIPS: {}".format(torch.tensor(lpipss).mean()))
print(" SSIM : {:>12.7f}".format(torch.tensor(ssims).mean(), ".5"))
print(" PSNR : {:>12.7f}".format(torch.tensor(psnrs).mean(), ".5"))
print(" LPIPS: {:>12.7f}".format(torch.tensor(lpipss).mean(), ".5"), "\n")
full_dict[scene_dir][method].update({"SSIM": torch.tensor(ssims).mean().item(),
"PSNR": torch.tensor(psnrs).mean().item(),
"LPIPS": torch.tensor(lpipss).mean().item()})
per_view_dict[scene_dir][method].update({"SSIM": {name: ssim for ssim, name in zip(torch.tensor(ssims).tolist(), image_names)},
"PSNR": {name: psnr for psnr, name in zip(torch.tensor(psnrs).tolist(), image_names)},
"LPIPS": {name: lp for lp, name in zip(torch.tensor(lpipss).tolist(), image_names)}})
full_dict[scene_dir][method].update({"SSIM": torch.tensor(ssims).mean().item(),
"PSNR": torch.tensor(psnrs).mean().item(),
"LPIPS": torch.tensor(lpipss).mean().item()})
per_view_dict[scene_dir][method].update({"SSIM": {name: ssim for ssim, name in zip(torch.tensor(ssims).tolist(), image_names)},
"PSNR": {name: psnr for psnr, name in zip(torch.tensor(psnrs).tolist(), image_names)},
"LPIPS": {name: lp for lp, name in zip(torch.tensor(lpipss).tolist(), image_names)}})
with open(scene_dir + "/results.json", 'w') as fp:
json.dump(full_dict[scene_dir], fp, indent=True)
with open(scene_dir + "/per_view.json", 'w') as fp:
json.dump(per_view_dict[scene_dir], fp, indent=True)
with open(scene_dir + "/results.json", 'w') as fp:
json.dump(full_dict[scene_dir], fp, indent=True)
with open(scene_dir + "/per_view.json", 'w') as fp:
json.dump(per_view_dict[scene_dir], fp, indent=True)
except:
print("Unable to compute metrics for model", scene_dir)
if __name__ == "__main__":
device = torch.device("cuda:0")