WEN Hao

It might be caused by data overflow, in which case `np.max(sig) - np.min(sig)` produces something with a very large absolute value. However, your data range (`-400 to 200`) does not...

`ATI-CNN` is essentially a convolutional recurrent neural network (CRNN) with a VGG-like CNN backbone, It can be initiated for example ```python from copy import deepcopy from torch_ecg.model_configs import ECG_CRNN_CONFIG from...

普通的convolution就是跨channel (lead)的，就把不同channel的信息融合到了一起 (除了所谓的depth-wise convolution, 把`groups`的数目设置成和`in_channels`一样。) 另外，ATI-CNN的最后的Attention应该和`AttentivePooling`是类似的。

> 你好作者，关于您工具库的使用，请问我是否可以加您个联系方式，方便交流呢。我在使用的过程中发现了一些问题，如数据库无法加载等 [email protected], 欢迎提BUG！

Thank you. The codes are up-to-date. Implementations of several nets are still pending. I will do it when I have enough time. Should be before the end of 2021.

It seems that one should not modify `rx_record` and `rx_signal`. This would result in `FileNotFoundError` when calling `rdrecord` since the `ge_median_beats_wfdb` folder does not exist. The `PTB-XL+` database should be...

See the [example](https://github.com/wenh06/hatch-debug/actions/runs/10543509653/job/29211527465)  The example [`setup.py`](https://github.com/wenh06/hatch-debug/blob/main/setup.py) is as follows: ```python """ """ from pathlib import Path import setuptools cwd = Path(__file__).absolute().parent long_description = (cwd / "README.md").read_text(encoding="utf-8") setuptools.setup( name="sample", version="0.1.0",...

@ofek

For `pretrained weights` (models), currently, one can call the `from_remote` to download and load weights from somewhere on the internet. There are trained models (stored in Google Drive, Dropbox, my...

Thank you for your suggestion. The benchmark folder contains full pipelines training from scratch. Currently, there's no list of trained models and scripts/notebooks for using them. I will do this...