LJY
LJY
我把所有的权重部署到了本地但是，不管怎么改都无法绕过下载模型这个操作。 /home/mouxing/anaconda3/envs/Grounded-Segment-Anything/bin/python /home/mouxing/PYTHON/Kop/Grounded-Segment-Anything/grounding_dino_demo.py HF_DATASETS_OFFLINE=1 TRANSFORMERS_OFFLINE=1 \ /home/mouxing/anaconda3/envs/Grounded-Segment-Anything/lib/python3.9/site-packages/torch/functional.py:504: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:3526.) return _VF.meshgrid(tensors, **kwargs) #...
ImportError: cannot import name 'PositionalEncodingPermute3D' from 'positional_encodings' 这个positional_encodings库怎么下载，通过python setup.py develop命令编译出来为空
datasets: train: name: Vimeo90K type: Vimeo90KDataset dataroot_gt: /cluster/work/cvl/videosr/vimeo90k/vimeo90k_train_GT_all.lmdb dataroot_lq: /cluster/work/cvl/videosr/vimeo90k/vimeo90k_train_LR7frames.lmdb dataroot_flow: ~ meta_info_file: basicsr/data/meta_info/meta_info_Vimeo90K_train_GT.txt val: name: Vimeo90K-Test type: VideoTestVimeo90KDataset dataroot_gt: ./vimeo_septuplet/sequences dataroot_lq: ./vimeo_septuplet_matlabLRx4/sequences meta_info_file: basicsr/data/meta_info/meta_info_Vimeo90K_test_GT.txt 配置文件中这些meta_info_file 的含义是什么
你好大佬，我按照你发的https://github.com/Digital2Slave/ncnn-android-yolov8-seg/wiki/Convert-yolov8%E2%80%90seg-to-ncnn-model-step-by-step 转换了一个模型，就是部署上去闪退，找不到原因。