Giters

yan-hao-tian / ConTNet

This repo contains the code of "ConTNet: Why not use convolution and transformer at the same time?"

Home Page:https://arxiv.org/abs/2104.13497

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Reproduce ConTNet-Tiny*

akuxcw opened this issue · comments

commented

Hi, thank you for sharing this awesome work! I'm trying to reproduce the result of ConTNet-Tiny*(74.9) with this code. But my result is very low (60.85). I used the following command:

CUDA_VISIBLE_DEVICES=0,1,2,3 python3 -m torch.distributed.launch --nproc_per_node=4 --master_port 29501 main.py --arch ConT-Ti --batch_size 256 --save_path contnet-tiny --save_best True

Is there any suggestion to correctly reproduce the results?

commented

That's weird. In general, the top-1 acc. of CONTNET-TI on ImageNet val can reach about %60 at very early epoch. Thanks for your attention and I will check it.