zpge
zpge
> Hi @zpge > > I have prepared a script that allows you train your own data using this repo's training strategy. It works on my machine with Pytorch-1.4.0 and...
Have you solved this problem?
> _No description provided._ Thanks. It's very nice of you. But I don't think it's a good idea to include the nms into the frozen model. Because it the inference...
OK. Thanks very much.
> Hey everyone, > I took the following steps: > > 1. Change the `utils/nms_utils.py` lines 53-55 to: > > ``` > boxes = tf.concat(boxes_list, axis=0, name='output/box_output') > score =...
After frozen to pb file, the model still takes over 5 Gb on GPU. Is it normal?
> 我现在生成的模型是 200多m，而且效果也没变差。 很优秀，非常感谢。想问一下，模型变小了是不是意味着占用GPU显存也变小了。原来YunYang版本的模型freeze之后，也要占用5G多，感觉有点怪。
> > > 我现在生成的模型是 200多m，而且效果也没变差。 > > > > > > 很优秀，非常感谢。想问一下，模型变小了是不是意味着占用GPU显存也变小了。原来YunYang版本的模型freeze之后，也要占用5G多，感觉有点怪。 > > 我的这里预测的话，显存占用很小，基本没用到多少啊，中文的会慢一些。 tensorflow默认占用全部显存，可能是我这边的原因吧