search

wanmeihuali / taichi_3d_gaussian_splatting

An unofficial implementation of paper 3D Gaussian Splatting for Real-Time Radiance Field Rendering by taichi lang.
Apache License 2.0
638 stars 58 forks source link

switch to seperate parameters #148

Open wanmeihuali opened 9 months ago

github-actions[bot] commented 9 months ago

Running experiment on sagemaker with git sha 46c6961e5855e43b98113a24af8a705ac78d0800

github-actions[bot] commented 9 months ago

Training job pose-pp-46c6961-231017-193459-tat-truck-baseline created

github-actions[bot] commented 9 months ago

Running experiment on sagemaker with git sha 46c6961e5855e43b98113a24af8a705ac78d0800

github-actions[bot] commented 9 months ago

Training job pose-pp-46c6961-231017-193546-tat-train-baseline created

github-actions[bot] commented 9 months ago

Training job pose-pp-46c6961-231017-193459-tat-truck-baseline failed

github-actions[bot] commented 9 months ago

Training job pose-pp-46c6961-231017-193459-tat-truck-baseline final metrics:

Latest Metrics

train:iteration train:l1loss train:loss train:num_valid_points train:psnr train:ssim train:ssimloss val:loss val:psnr val:ssim
4090.0 0.07808087766170502 0.13137362897396088 265832.0 17.90740394592285 0.6427943706512451 0.3445446491241455 0.20602254569530487 14.621099472045898 0.5179296731948853

Max Metrics

train:psnr train:ssim val:psnr val:ssim
17.90740394592285 0.6427943706512451 14.621099472045898 0.5179296731948853
github-actions[bot] commented 9 months ago

Training job pose-pp-46c6961-231017-193546-tat-train-baseline failed

github-actions[bot] commented 9 months ago

Training job pose-pp-46c6961-231017-193546-tat-train-baseline final metrics:

Latest Metrics

train:iteration train:l1loss train:loss train:num_valid_points train:psnr train:ssim train:ssimloss val:loss val:psnr val:ssim
4090.0 0.12454218417406082 0.20430371165275574 305263.0 16.388172149658203 0.49622035026550293 0.5233498215675354 0.2328539937734604 13.977322578430176 0.4893655776977539

Max Metrics

train:psnr train:ssim val:psnr val:ssim
16.388172149658203 0.49622035026550293 13.977322578430176 0.4893655776977539