suyali
suyali
@vcvycy ，@alphaYao 由于模型结构相较https://github.com/vcvycy/TensorflowFreezeModel/blob/master/freeze_mtcnn.py 调整了很多，所以想问一下：现在可了解如何将3个model的.ckpt固化到同一个.pb文件中，
@kli017 你尝试在tensorflow detection demo上调用成功了吗？
@vcvycy , hello,如何用3个.pb文件固化成一个.pb呢？
> 我自己写了一个工程来读取图像，进行预处理后进行识别，利用提供的detection_output.cc处理最后一层，但是识别不到任何东西？ > > ``` > { > // config runtime > #ifdef USEGPU > //mace::SetOpenMPThreadPolicy(-1,static_cast(1)); > mace::DeviceType device_type = mace::GPU;//CPU = 0, GPU = 2, HEXAGON = 3 >...
You should reduce learning_rate
Yes, you can use opencv to load video!I made it!
@smilecode-github Have you solved this problem?
@minus31 I stil have no idea about the setting of labels, can you give me an example?
the same question