-
仮説を立てて、検証する、を細かく繰り返す。方が精神に良い。
# 整数コピー数の列挙
「本当に真のコピー数が一番高いスコアを出すか？」を検証したい
今のコピー数に近いコピー数を発生させる部分を作る
→そのスコアの可視化
# 実数コピー数のEMの分析
「不要なk-merを当てられるか？」を検証したい
## 現状の課題
### 全長リードの時
* min_shrinkの閾値の設…
-
Hello Narsil,
Thank you for compiling this list of papers. I'm interested in GflowNet and this is definitely a great resource.
I have a few questions about GflowNet, and I would appreciate if y…
-
Hi!
Thanks for the great work on GFlowNets. I am going through the code, to understand and reproduce the multi-objective molecule generation experiments (from the Multi-objective GFlowNets paper).
…
-
微博内容精选
-
I'm running Ubuntu 16.04.3 on an AWS P3.2xlarge, with the NVIDIA libcuda1-384 package, version 384.111-0ubuntu0.16.04.1, and pytorch version 0.3.0.post4 and cuda90, installed via conda.
In some cir…
-
Dear Mr. Dinghuai,
Thanks for your great work.
I have a question about estimating MDD.
As in (In Dai et al. (2020)), the MMD result is calculated within a fixed group of 4000 samples, which are…
-
### Contributor License Agreement
- [X] I accept and sign the contributor license agreement ([CLA](../../CONTRIBUTING.md#contributor-license-agreement)) to contribute to GT4SD.
-
hi,
Thank you very much for sharing the source codes.
`edges = jnp.stack((sources, num_variables + targets), axis=1)` Line 48 in `nets/gflownet.py`
I don't understand why targets shoule be add…
-
## Related Reference
- Yang Song. [Sliced Score Matching: A Scalable Approach to Density and Score Estimation](https://yang-song.net/blog/2019/ssm/).
- Yang Song. [Generative Modeling by Estimatin…
-
Hi there,
Thank you very much for sharing the source codes.
For reproducibility, I modified the codes as follows,
https://github.com/GFNOrg/gflownet/blob/831a6989d1abd5c05123ec84654fb08629d9…