-
## Why
Machine Learning 輪講は最新の技術や論文を追うことで、エンジニアが「技術で解決できること」のレベルをあげていくことを目的にした会です。
prev. #8
## What
話したいことがある人はここにコメントしましょう！
面白いものを見つけた時点でとりあえず話すという宣言だけでもしましょう！
-
deep learning on graph
pytorch has very nice tools for gcns, including:
DGL: https://github.com/dmlc/dgl
PyTorch Geometric : https://github.com/rusty1s/pytorch_geometric
…
-
When I tried to run resnet34 model test with the nightly version that is installed with pip in cuda 11.6 with A100 gpu.
~~UPDATE: As mentioned in Notes below, it seems that the problem caused by `…
-
**researcher**
- [Rie Johnson](http://riejohnson.com/)
- [CONTEXT v4: Neural network code for text categorization in C++ on GPU](http://riejohnson.com/cnn_download.html)
**papers**
- Pang,…
-
你好，看了你的代码受益匪浅，对于Bert的变种我有一个问题想问一下，就是Bert_CNN、Bert_RNN、Bert_RCNN以及Bert_DPCNN模型都是出自于某一篇论文吗？如果是的话可否将论文名称或者论文链接分享一下？谢谢。
ghost updated
2 years ago
-
one interesting application of this representation might be that it might be explainable in a useful form.
If we train a model on the image, we can then use one of the established interpretability…
-
Issue to track classification task
-
Dynamicly quantized AlBert model shows poor performance
When I quantized fine-tuned albert-base-v2 model, checkpoint size reduced from 43MB to almost 22MB, but F1 score drops to 0.05 whereas on non q…
-
Excuse me, how do you extract the ResNeXt-101 motion features?
-