Update README.md

README.md

@@ -2,16 +2,18 @@
 tags:
 - model_hub_mixin
 - pytorch_model_hub_mixin
+license: mit
+library_name: pytorch
 ---
 
 # ResMaskNet
 
 ## Model Description
-ResMaskNet is a convolutional neural network designed for robust face recognition and mask detection. It extends the ResNet architecture with specialized layers to handle masked face detection effectively. The model can distinguish between masked and unmasked faces and performs well even with variations in lighting, angles, and occlusions.
+resmasknet combines residual masking with unet architecture to predict 7 facial emotion categories from images. 
 
 ## Model Details
 - **Model Type**: Convolutional Neural Network (CNN)
-- **Architecture**: ResNet-based with custom mask detection layers
+- **Architecture**: Residual masking network with u-network. Output layer classifies 7 emotion categories
 - **Input Size**: 224x224 pixels
 - **Framework**: PyTorch
 
@@ -20,7 +22,7 @@ ResMaskNet is a convolutional neural network designed for robust face recognitio
 - **Paper**: [Facial Expression Recognition Using Residual Masking Network](https://ieeexplore.ieee.org/document/9411919)
 
 ## Citation
-If you use the ResMaskNet model in your research or application, please cite the following paper:
+If you use the svm_au model in your research or application, please cite the following paper:
 
 Pham Luan, The Huynh Vu, and Tuan Anh Tran. "Facial Expression Recognition using Residual Masking Network". In: Proc. ICPR. 2020.
 
@@ -37,3 +39,31 @@ Pham Luan, The Huynh Vu, and Tuan Anh Tran. "Facial Expression Recognition using
 
 ## Acknowledgements
 We thank Luan Pham for generously sharing this model with a permissive license. 
+
+## Example Useage
+
+```python
+import numpy as np
+import torch
+import torch.nn as nn
+from feat.emo_detectors.ResMaskNet.resmasknet_test import ResMasking
+from huggingface_hub import hf_hub_download
+
+device = 'cpu'
+emotion_detector = ResMasking("", in_channels=3)
+emotion_detector.fc = nn.Sequential(nn.Dropout(0.4), nn.Linear(512, 7))
+emotion_model_file = hf_hub_download(repo_id='py-feat/resmasknet', filename="ResMaskNet_Z_resmasking_dropout1_rot30.pth")
+emotion_checkpoint = torch.load(emotion_model_file, map_location=device)["net"]
+emotion_detector.load_state_dict(emotion_checkpoint)
+emotion_detector.eval()
+emotion_detector.to(device)
+
+
+# Test model
+face_image = "path/to/your/test_image.jpg"  # Replace with your extracted face image that is [224, 224]
+
+# Classification - [angry, disgust, fear, happy, sad, surprise, neutral]
+emotions = emotion_detector.forward(face_image)
+emotion_probabilities = torch.softmax(emotions, 1)
+        
+```