Yichung Hsu

seems `qt` is not installed properly. try `conda install qt` or re-create env with `conda create -n new_env python=3 qt pyqt pyside2 -y` edit: correct to `conda create -c conda-forge...

Removing the brackets works well to me, modify from `loss = (tf.reduce_mean(input_tensor=layer.output, keepdims=True))` to `loss = tf.reduce_mean(input_tensor=layer.output, keepdims=True)`

Install the package with `pip install -e .`

I'm curious that is it possible to point out an unknown object have not been learned (like anomaly detection) by text prompt if I fine-tune with custom data.

Hi @deepvelop99, Actually, I'm not the author of the ReConPatch paper and this repo is not the official one, but the paper mentioned they use the same approach with [Patchcore](https://openaccess.thecvf.com/content/CVPR2022/papers/Roth_Towards_Total_Recall_in_Industrial_Anomaly_Detection_CVPR_2022_paper.pdf)...

Sorry, I only implemented the ReConpatch module described in the paper for work's project (which is not using PatchCore) use. Honestly I have no experience of implementing PatchCore in TF.

I got following after click "Update Portfolio" button: ```[2025-05-25][06:46:25][wealthfolio_core::market_data::providers::yahoo_provider][WARN] No historical quotes returned by Yahoo API for symbol 'AVGX' between 2025-05-25 and 2025-05-25. [2025-05-25][06:46:25][wealthfolio_core::market_data::providers::yahoo_provider][WARN] No historical quotes returned by Yahoo...

Hi all, After some investigation, I found this issue is caused by a few of activities of ARKW in 2024/11~2024/12. I create an independent account for testing to import that...