UnsupDIS-pytorch icon indicating copy to clipboard operation
UnsupDIS-pytorch copied to clipboard

A pytorch implementation of UnsupervisedDeepImageStitching

Results 13 UnsupDIS-pytorch issues
Sort by recently updated
recently updated
newest added

在对齐网络网络训练时,出现中断 CUDA runtime error: an illegal memory access was encountered (700) in apply_lu_factor_batched_magma at /opt/conda/conda-bld/pytorch_1656352463056/work/aten/src/ATen/native/cuda/linalg/BatchLinearAlgebra.cpp:1961 Images loss1 loss2 loss3 total PSNR SSIM terminate called after throwing an instance of 'c10::CUDAError'...

Hi there! Thanks for the great work! Trying to run on UDIS testing data to generate coarse aligned results, but failing with the following error, what I'm doing wrong? ```python...

请问您的这个方法,可以实现多张图像全景拼接吗,还是只能实现两张图像的拼接?

[Step 6 (Reconstruction): Generating the finally stitched results] python3 inference_fuse.py --weights weights/fuse/udis/weights/best.pt --source data/udis.yaml --task test --half --img-size 640 --reg-mode crop After the sixth step is completed. Why does the...

有在windows中训练的嘛,请教一下怎么链接数据集?或者怎么改一下可以跑起来代码

您好,我想问一下为什么torch版本测试的PSNR和SSIM会比原tensorflow版本的高这么多呢?

Did you change the order of training and testing for UDIS-D(order of target image and warping image)? I found that the order of both coarse stitching and overlapping PSNR and...

您好,在运行python3 train.py --data data/aquaponics.yaml --hyp data/hyp.align.finetune.yaml --cfg models/align_origin.yaml --weights weights/align/warpedcoco/weights/coco_align_yolo.pt --img-size 128 --epochs 30 --adam --mode align 时出现以下问题,把models换成align_yolo.yaml 可以正常运行

I try to train this model.But every time in the testing phase of epoch2/149 report errors。 Epoch gpu_mem loss1 loss2 loss3 total img_size 2/149 20.4G 0.1235 0.1084 0.1039 2.514 128:...