angleboy

Nowadays，google translation helps you to some extent. In China，people use some translation software to understand better some English repositories. If you have some problems, others are willing to help you....

@maxteleg I try your method, but the problem still exists. Traceback (most recent call last): File "", line 1, in File "d:\ProgramData\Anaconda3\envs\caffe27\lib\site-packages\caffe\__init__.py", line 1, in from .pycaffe import Net, SGDSolver,...

I use CUDA 10.0, VS 2015, PYTHON 2.7. In addtion, Python 3.5 is the same as that. Do you have a better resolution. Please inform me.

pip install --user --upgrade protobuf==3.1.0.post1 For above problem，I solved it by "https://github.com/BVLC/caffe/issues/5357". I hope these will be helpful for you.

网上说应该将输出图像转成整数，bug是没了，但是结果显示的不对。

> > INFO: Prediction is too large for python process-process communication. Saving to file... It's stuck here while you train the prediction part of the model > > And now...

> Hi, I did not include them in the project since they were big files. You can generate them by running the train pipeline. Thank you for your reply and...

By the way, if it is possible, [google drive](https://drive.google.com/) can solve the problem of large files very well. Thanks, again.

> Hello, we will look into this problem later, it may due to our unstable server issues, you can try huggingface gradio online demo first with this link: https://huggingface.co/spaces/Mountchicken/Grounding-DINO-1.5 >...