YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
language:
- en
tags:
- image-classification
- bangla-food
- bangladeshi-food
- food-recognition
- efficientnetv2
library_name: transformers
base_model: timm/tf_efficientnetv2_s.in21k_ft_in1k
metrics:
- accuracy
- f1
---
# Bangla Food Recognizer - EfficientNetV2-S
Fine-tuned from EfficientNetV2-S `timm/tf_efficientnetv2_s.in21k_ft_in1k` for Bangladeshi food image recognition.
## Training Sources
- `tanziro/bangladeshi-food-1041`
- DeshiFoodBD, Mendeley Data DOI `10.17632/tczzndbprx.1`
- FoodBD polygon-annotated meal images, Mendeley Data DOI `10.17632/xh3ghf3jbg.2`
- BD-Food33, Mendeley Data DOI `10.17632/8wt48bjmx3.1`
## Evaluation
```json
{
"validation": { "validation_loss": 2.2158524990081787, "validation_accuracy": 0.6118909991742362, "validation_macro_f1": 0.2587394309318114, "validation_weighted_f1": 0.5640698507031976, "validation_top3_accuracy": 0.7448389760528489 }, "test": { "test_loss": 2.483065605163574, "test_accuracy": 0.5770750988142292, "test_macro_f1": 0.2316382332791406, "test_weighted_f1": 0.5353572882969004, "test_top3_accuracy": 0.7114624505928854 } } ```
## Intended Use
Exploratory Bangladeshi food recognition from images. This is not a nutrition, medical, allergy, or food-safety system. Check original dataset licences and terms before commercial use.
- Downloads last month
- 3
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support