-
```
What steps will reproduce the problem?
In [3]: ipaddr.IPv4Network("10.254.188.64/26").supernet()
Out[3]: IPv4Network('10.254.188.64/25')
In [4]: ipaddr.IPv4Network("10.254.188.64/26").supernet()…
-
Thanks for the great work again!
I've successfully run `WS-GM/exp_scripts/rsws-ws-201.sh`, and now I obtained four checkpoints of supernets, e.g., `supernets_0/1/2/3.pt`.
I want to reproduce the…
-
```
What steps will reproduce the problem?
In [3]: ipaddr.IPv4Network("10.254.188.64/26").supernet()
Out[3]: IPv4Network('10.254.188.64/25')
In [4]: ipaddr.IPv4Network("10.254.188.64/26").supernet()…
-
The latest builds of mm on both the `jl777` and `dev` branch crash when I issue commands over the socket.
If I just remove the non zero `queueid` to make the requests normal HTTP requests it works …
-
Thanks for sharing the awesome work!
I have one question about quantization function and bit inheritance.
In the paper, you choose LSQ as the quantization function which has a learnable scale parem…
zl-hw updated
4 years ago
-
I am using run.bat with %\* to pass args. But do not see any args coming in.
-
Hi,
Thanks for your great work! I have some questions about the two-stage training. I'd appreciate it if you could share more details.
1. In `Stage 2 - Once-for-All Training`, which model is us…
-
https://github.com/megvii-model/SinglePathOneShot/blob/36eed6cf083497ffa9cfe7b8da25bb0b6ba5a452/src/Supernet/train.py#L213
It seems that author want the candidates' flops distribute uniformly among…
-
# Connecting Validator to remote Bootnode.
## Description
I'd like to know if there is a guide for connecting adding remote validators to the validator set of an existing Supernet.
I have a local S…
-
tl;dr support supernets with varying block sizes (`intermediate_size` and `n_heads` can be lists)
**Is your feature request related to a problem? Please describe.**
When converting HW-GPT-Bench su…