-
When I used the pre-trained model 'raphaelsty/neural-cherche-sparse-embed' to evaluate the dataset, specifically, the arguana dataset, with a retrieval k value of 100, the result was very poor
{'map'…
-
Hello, @gmberton!
I've encountered an issue when using the --resume option to load the best_model.pth file. Specifically, while the **"model_state_dict"** and **"recalls"** in the checkpoint file c…
-
### Describe the desired feature
Currently, the `[have_unit]` tag supports a `search_recall_list=` key that supports the following values:
- `yes`: search both recall list and on-screen units
- `no…
-
**Describe the bug**
When accessing a normal video (not a short video) on the YouTube website. The Logseq Copilot icon displays incorrect numbers. This behavior only occurs on the YouTube website, wh…
-
I'm on the community-repository on openSUSE-Leap-15.5
gromox-2.27.4.g5639431-lp155.21.1.x86_64
The feature "Recall this message" of the _Outlook for Windows_ clients of senders should be fully sup…
-
After you build and run a case, one can use the database to reload the reactor state. It appears that if you define a component with a custom material like `material: customMaterialModule:myCustomMate…
-
Food authorities provide a number of way to inform the public about product that have been recalled for health and safety reasons (allergens, bacteria etc.)
Here is an example from the UK food agency:…
-
### What
- [ ] Expose recalled products through the API
- [ ] Design doc
-
Motion detection should be the first thing to process to prevent false negatives from the automated counting later in the pipeline, allowing manual review and potential incorporation into future datas…
-
Good evening. My code snipped for classifying breast cancer image is not generalizing well. How do I improve the model performance to produce "accuracy, precision and recall" of over 98%