Add ssim and update typechecks (#66)

* Add ssim and update typechecks

* update requirements

* Fix type error
This commit is contained in:
Matthew Tancik authored and GitHub committed 2022-05-10 11:52:32 -07:00
1 parent 6340f975db
commit 29ba6d8abc
4 files changed
+72 -5

No files matched your search

+6
View File
@@ -21,4 +21,10 @@
],
"python.testing.unittestEnabled": false,
"python.testing.pytestEnabled": true,
"python.linting.ignorePatterns": [
"**/site-packages/**/*.py",
".vscode/*.py",
"external/**/*.py",
],
"python.analysis.typeCheckingMode": "basic",
}
+1
View File
@@ -10,6 +10,7 @@ mediapy
plotly==5.7.0
pylint==2.13.4
pytest
pytorch-msssim>=0.2.1
tensorboard==2.8.0
torch==1.11.0
torchtyping
+13 -3
View File
@@ -9,12 +9,12 @@ import torch
from torch import nn
from torch.nn import Parameter
from mattport.nerf import metrics
from mattport.nerf.field_modules.encoding import NeRFEncoding
from mattport.nerf.field_modules.field_heads import DensityFieldHead, FieldHeadNames, RGBFieldHead
from mattport.nerf.field_modules.mlp import MLP
from mattport.nerf.graph.base import Graph
from mattport.nerf.loss import MSELoss
from mattport.nerf.metrics import get_psnr
from mattport.nerf.renderers import AccumulationRenderer, DepthRenderer, RGBRenderer
from mattport.nerf.sampler import PDFSampler, UniformSampler
from mattport.structures import colors
@@ -221,15 +221,25 @@ class NeRFGraph(Graph):
combined_image = torch.cat([depth_coarse, depth_fine], dim=1)
writer.write_event({"name": f"image_idx_{image_idx}", "x": combined_image, "step": step, "group": "val_depth"})
coarse_psnr = get_psnr(image, rgb_coarse)
coarse_psnr = metrics.get_psnr(image, rgb_coarse)
writer.write_event(
{"name": f"image_idx_{image_idx}", "scalar": float(coarse_psnr), "step": step, "group": "val"}
)
fine_psnr = get_psnr(image, rgb_fine)
coarse_ssim = metrics.get_ssim(image, rgb_coarse)
writer.write_event(
{"name": f"image_idx_{image_idx}", "scalar": float(coarse_ssim), "step": step, "group": "ssim"}
)
fine_psnr = metrics.get_psnr(image, rgb_fine)
stats_tracker.update_stats(
{"name": stats_tracker.Stats.CURR_TEST_PSNR, "value": float(fine_psnr), "step": step}
)
writer.write_event(
{"name": f"image_idx_{image_idx}-fine_psnr", "scalar": float(fine_psnr), "step": step, "group": "val"}
)
fine_ssim = metrics.get_ssim(image, rgb_fine)
writer.write_event(
{"name": f"image_idx_{image_idx}-fine_ssim", "scalar": float(fine_ssim), "step": step, "group": "ssim"}
)
+52 -2
View File
@@ -3,11 +3,61 @@ Collection of metrics.
"""
import torch
from pytorch_msssim import ssim, ms_ssim
from torchtyping import TensorType
def get_psnr(image_gt, image_pred):
def get_psnr(image_gt: TensorType, image_pred: TensorType) -> TensorType:
"""
Returns the psnr for an image. TODO: add masking
Returns the PSNR (peak signal-to-noise ratio) for an image. TODO: add masking
Args:
image_gt (TensorType): Ground truth image
image_pred (TensorType): Predicted image
Returns:
float: PSNR
"""
mean = torch.mean((image_gt - image_pred) ** 2)
return -10 * torch.log10(mean)
def get_ssim(image_gt: TensorType, image_pred: TensorType) -> TensorType:
"""
Returns the SSIM (structural similarty) for an image.
Args:
image_gt (TensorType): Ground truth image
image_pred (TensorType): Predicted image
Returns:
float: SSIM
"""
assert image_gt.shape[-1] in [1, 3]
assert image_pred.shape[-1] in [1, 3]
assert image_gt.shape == image_pred.shape
if image_gt.dim() == 3:
image_gt = image_gt[None, ...]
if image_pred.dim() == 3:
image_pred = image_pred[None, ...]
return ssim(image_gt, image_pred, data_range=1.0)
def get_ms_ssim(image_gt: TensorType, image_pred: TensorType) -> TensorType:
"""
Returns the MS_SSIM (multi-scale structural similarty) for an image.
Args:
image_gt (TensorType): Ground truth image
image_pred (TensorType): Predicted image
Returns:
float: MS-SSIM
"""
assert image_gt.shape[-1] in [1, 3]
assert image_pred.shape[-1] in [1, 3]
assert image_gt.shape == image_pred.shape
if image_gt.dim() == 3:
image_gt = image_gt[None, ...]
if image_pred.dim() == 3:
image_pred = image_pred[None, ...]
return ms_ssim(image_gt, image_pred, data_range=1.0)