dragon10

same issue，how to fix？

> ../build/examples/squeezenet ../images/256-ncnn.png -bash: ../build/examples/squeezenet: No such file or directory ；麻烦问下这是表示没编译成功吗

> copy squeezenet_v1.1.param and squeezenet_v1.1.bin from ncnn/examples to your current working directory 

> copy squeezenet_v1.1.param and squeezenet_v1.1.bin from ncnn/examples to your current working directory cd ../benchmark ../build/benchmark/benchncnn 10 $(nproc) 0 0 这个能正常运行，就是上面的squeezenet运行不了

> 编译安装；案例使用小白表示看不大懂文档，文档写的东一块西一块；简单案例都复现不出来，打击信心 小白感受还是比较难上手

> 请问是哪个文档？https://tengine.readthedocs.io/zh_CN/latest/source_compile/compile_linux.html 还要使用案例https://github.com/OAID/Tengine/tree/tengine-lite/examples；感觉不是很直观简单方便

> After fine tuning the model on my dataset (containing 272 images) for 5 epoch and learning rate 5e-5, after training model just give same Image as result for every...

what is the clip.model.convert_weights meaning? and can you Provide a complete training code if possible

> @lonngxiang For more information, read #57, clip.model.convert_weights basically convert the CLIP model weight into float16. This will help accelerate and reduce memory usage during training. > The definition of...

there is a error when run this train code： TypeError: default_collate: batch must contain tensors, numpy arrays, numbers, dicts or lists; found