search

swz30 / MIRNet

[ECCV 2020] Learning Enriched Features for Real Image Restoration and Enhancement. SOTA results for image denoising, super-resolution, and image enhancement.
Other
667 stars 96 forks source link

A lightweight, fast and extended version of MIRNet is accepted in TPAMI #53

Closed Devil-Ideal closed 1 year ago

Devil-Ideal commented 1 year ago

hi! I'm very interested in your work, especially the lightweight version published in TPAMI. I would like to know the type of GPU used, and the total GPU memory time required for MIRNETv2 training. I noticed that batchsize is 64 in MIRNETv2 but only 16 in MIRNET. MIRNETv2 uses a larger batchsize and patch, which means more GPU memory is required.

adityac8 commented 1 year ago

You can have a look at the Table. MIRNetv2 uses less parameters and flops as MIRNet. We trained our models on 8 Tesla V100s. If you have a different GPU, you can adjust the batch size to run on your machine.

image
Devil-Ideal commented 1 year ago

You can have a look at the Table. MIRNetv2 uses less parameters and flops as MIRNet. We trained our models on 8 Tesla V100s. If you have a different GPU, you can adjust the batch size to run on your machine. image

thank you for your reply