Upload folder using huggingface_hub

README.md

@@ -0,0 +1,53 @@
+---
+license: mit
+tags:
+- vision
+- food-recognition
+- ingredients
+- utensils
+- portion-size
+- computer-vision
+- mobile
+- ug-food-dataset
+---
+
+# UG Food Detection Model
+
+This model identifies food ingredients, utensils, and estimates portion sizes from images.
+
+## Model Description
+
+This Vision Transformer (ViT) model is trained on the UG Food Dataset to recognize:
+- Food ingredients: Various food items and ingredients
+- Kitchen utensils: Cooking tools and equipment
+- Portion sizes: Measurement estimates
+
+## Classes
+The model can identify 40 classes.
+
+## Usage
+
+```python
+from transformers import ViTImageProcessor, ViTForImageClassification
+from PIL import Image
+import torch
+
+# Load model and processor
+processor = ViTImageProcessor.from_pretrained("ssevan/ug-food-detector")
+model = ViTForImageClassification.from_pretrained("ssevan/ug-food-detector")
+
+# Process image
+image = Image.open('food_image.jpg')
+inputs = processor(image, return_tensors='pt')
+
+# Get predictions
+with torch.no_grad():
+    outputs = model(**inputs)
+    probabilities = torch.nn.functional.softmax(outputs.logits, dim=-1)
+    predicted_class_idx = torch.argmax(probabilities, dim=1).item()
+
+print(f'Predicted class index: {predicted_class_idx}')
+```
+
+## Mobile Usage
+This model is optimized for mobile deployment.

class_names.json

@@ -0,0 +1 @@
+["ugandan_rolex", "milk", "chicken_stew", "fish_stew", "nakati", "utensils", "peas_soup", "millet", "pumpkin", "_roasted_groundnuts", "beans_soup", "pilau", "sweet_potatoes", "Ground_nut_sauce", "banana_leaves", "chapati_street_food", "nsenene", "boiled_cassava", "irish_potatoes", "cassava", "chai", "yams", "ground_nuts", "beans", "tomatoes", "eggs", "maize", "posho", "beef_stew", "samosa", "matooke", "pumpkin_soup", "katogo", "onions", "matooke_meal", "ugandan_local_food", "pork_stew", "garlic", "peas", "rice"]

config.json

@@ -0,0 +1,7 @@
+{
+  "model_type": "vit",
+  "num_classes": 40,
+  "image_size": 224,
+  "mobile_optimized": true,
+  "task": "food-ingredient-utensil-detection"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22cc6f6f02e8b69e90badb7b24627fdafed5a3b593a6b7b462bcbbf675c5faab
+size 343340872

preprocessor_config.json

@@ -0,0 +1,23 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "ViTImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}