Upload driver drowsiness detection model

README.md

@@ -0,0 +1,68 @@
+---
+language: en
+license: mit
+tags:
+  - vision
+  - image-classification
+  - drowsiness-detection
+  - driver-monitoring
+  - pytorch
+  - mobilenetv2
+datasets:
+  - custom
+---
+
+# Driver Drowsiness Detection Model
+
+This model detects whether a driver is alert or showing signs of drowsiness based on facial features.
+
+## Model Description
+
+This model is fine-tuned on a custom dataset of driver face images to detect drowsiness in real-time. It uses a MobileNetV2 architecture for efficient inference.
+
+### Model Architecture
+- Base model: MobileNetV2
+- Fine-tuned for binary classification (alert vs. drowsy)
+- Input size: 224x224 RGB images
+
+## Training Data
+
+The model was trained on custom-labeled face images extracted from driver-facing camera videos. The dataset includes various lighting conditions and driver appearances.
+
+## Performance
+
+The model can identify signs of drowsiness in drivers with high accuracy. It's designed to be fast enough for real-time inference.
+
+## Limitations
+
+- Requires good lighting conditions to detect faces properly
+- May have reduced accuracy with glasses or face coverings
+- Should be used as part of a comprehensive driver monitoring system and not as the sole safety mechanism
+
+## Usage
+
+```python
+from transformers import AutoImageProcessor, AutoModelForImageClassification
+from PIL import Image
+
+# Load model and processor
+processor = AutoImageProcessor.from_pretrained("ckcl/driver-drowsiness-detector")
+model = AutoModelForImageClassification.from_pretrained("ckcl/driver-drowsiness-detector")
+
+# Load an image
+image = Image.open("path/to/driver/face/image.jpg")
+
+# Process image and get prediction
+inputs = processor(images=image, return_tensors="pt")
+outputs = model(**inputs)
+predicted_class_idx = outputs.logits.argmax(-1).item()
+print(f"Predicted class: {model.config.id2label[str(predicted_class_idx)]}")
+```
+
+## Citation
+
+If you use this model in your research or project, please provide a link to this model card.
+
+## Contact
+
+For questions or feedback, please open an issue on the GitHub repository or contact the author on Hugging Face.

model/config.json

@@ -0,0 +1,19 @@
+{
+  "architectures": [
+    "MobileNetV2ForImageClassification"
+  ],
+  "model_type": "mobilenet_v2",
+  "hidden_act": "relu",
+  "hidden_dropout_prob": 0.2,
+  "num_channels": 3,
+  "num_labels": 2,
+  "id2label": {
+    "0": "alert",
+    "1": "drowsy"
+  },
+  "label2id": {
+    "alert": 0,
+    "drowsy": 1
+  },
+  "transformers_version": "4.18.0"
+}

model/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89173440c3531fde3a2d77be156f039cc4e68170a42da16bb74ede7dadc42ef7
+size 9152306

preprocessor/preprocessor_config.json

@@ -0,0 +1,18 @@
+{
+  "crop_size": 224,
+  "do_center_crop": true,
+  "do_normalize": true,
+  "do_resize": true,
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 3,
+  "size": 224
+}