-
The supernet table on the results page appears to generate confusion for some users, especially with large supernets with a lot of delegations which possibly have issues, but aren't related to the act…
-
I train the supernet with the default setting, and got an accuracy of
`TRAIN Iter 150000: lr = 0.000003, loss = 2.805815, Top-1 err = 0.417285, Top-5 err = 0.202197, data_time = 0.050527, train_ti…
-
It'd be useful if it was possible to iterate over the supernets of a net. This can already be done with something like
```rust
let net = "10.0.0.0/8".parse().unwrap();
let mut tmp_net = net.clone()…
-
Thanks for sharing your code!
I'm trying to test your code, but I got an error like:
```
Traceback (most recent call last):
File "C:\Users\admin\PreNAS\supernet_train.py", line 463, in
m…
-
The link to download the supernet cannot be accessed. Could you please provide me? Thank you very much!
-
I want to download the supernet 'ofa_mbv3_d234_e346_k357_w1.0 ', but this link is Forbidden.
Download the pre-trained (on ImageNet) supernet from [here](https://hanlab.mit.edu/files/OnceForAll/ofa_ne…
-
Hi
```
use ipnetwork::Ipv4Network;
let net: Ipv4Network = "10.1.0.0/16".parse().unwrap();
let net2: Ipv4Network = "10.1.0.0/15".parse().unwrap();
println!("{:?} {} {}", net2, net.is_supernet_of…
-
Hi,
Your approach is very impressive; I was wondering if you're planning to release the weights of the supernets you trained? (I'm specifically interested in the HyTra supernet)
-
Once a subnet (let's say a /24) has been split into smaller subnets (e.g. multiple /28) it doesn't seem to be possible to expand some /28 subnets into a larger subnet still within the parent /24. Or m…
-
I try to reproduce your one-shpt results on nas-bench 201.
By running the code
https://github.com/aoiang/few-shot-NAS/blob/main/Few-Shot_NasBench201/supernet/one-shot/run.sh
and eval
https://gi…