RoachZhao

@pieandcakes maybe a week ago, Ctrl+F5 do the same with `Start without debugging`. Don't why doesn't work now.

Yes, update it at 2019-01-09...

Thanks for your reply. Yes, I read that [paper](https://arxiv.org/abs/1502.03044). And seems it didn't show the detail of how to calculate  And in [paper](https://arxiv.org/pdf/1409.0473.pdf) referenced by 《Show, Attention and Tell》says...

Waiting for and thanks!

I think don't need a linear layer.

Found vscode support it, and support this feature will be great!

> Yep, the way DAP is structured, every process has to be its own separate session. On debugpy side, when subprocess is detected and detoured, we send a custom event...

Hi @nowgood, I use your method, and compile success. But I have the undefined symbol error. Also tensorflow 1.6 on Manjaro. this is the error: ``` /usr/lib/python3.6/site-packages/h5py/__init__.py:36: FutureWarning: Conversion of...

@YoungSharp thanks for your help. It does help me. But I got a new error...

`pyg ./tools/demo.py --model VGGnet_fast_rcnn_iter_70000.ckpt` ``` /usr/lib/python3.6/site-packages/h5py/__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`....