kl402401
kl402401
> 你好 > > 复制net_g_50000.pth到weights目录,然后 > > * 省事的办法是替换掉原来的模型 > > * 更好的办法修改inference_realesrgan.py 中的相关代码,加入训练的新模型。 > > > 比如 你的微调模型是从 _RealESRGAN_x4plus_ 微调而来 > > **原代码** > > ``` > if args.model_name...
复制下载链接到迅雷等下载工具就可以下载
这是来自QQ邮箱的假期自动回复邮件。 您好,我最近正在休假中,无法亲自回复您的邮件。我将在假期结束后,尽快给您回复。
buy the way,I have two gpu cards
solve: CUDA_VISIBLE_DEVICES=0,1 \ python -m torch.distributed.launch --nproc_per_node=2 --master_port=4321 realesrgan/train.py -opt options/finetune_realesrgan_x4plus_pairdata.yml --launcher pytorch --auto_resume change CUDA_VISIBLE_DEVICES=0,1 \ torchrun --nproc_per_node=2 --master_port=4321 realesrgan/train.py -opt options/finetune_realesrgan_x4plus_pairdata.yml --launcher pytorch --auto_resume torchrun replace python -m...
Traceback (most recent call last): File "/mnt/data/Real-ESRGAN/realesrgan/train.py", line 11, in train_pipeline(root_path) File "/data/envs/geo_real_esrgan/lib/python3.11/site-packages/basicsr/train.py", line 124, in train_pipeline model = build_model(opt) ^^^^^^^^^^^^^^^^ File "/data/envs/geo_real_esrgan/lib/python3.11/site-packages/basicsr/models/__init__.py", line 26, in build_model model = MODEL_REGISTRY.get(opt['model_type'])(opt)...
请问该项目支持模型的增量学习吗?
> 你好,请问你进行模型微调的时候数据集是使用的readme里所写的那些还是用自己构造的数据呀,有什么数据集数量上的要求吗,我使用自己的数据进行微调的时候有一个报错: raise ValueError(f'Scale mismatches. GT ({h_gt}, {w_gt}) is not {scale}x ', ValueError: ('Scale mismatches. GT (256, 256) is not 4x ', 'multiplication of LQ (256, 256).') 你是用来训练影像瓦片吗?我也遇到这个问题,请问您知道什么原因了吗?
> > Note that in the config file ( finetune_realesrgan_x4plus_pairdata.yml) that is present under the options folder, the scale is set as 4 by default. In your case, the dimensions...
> After we upgraded to the latest from 0.6, we found that $env:GDAL_VERSION **must** be set or the gdal-sys build script will just quit (Windows) > After we upgraded to...