Update README.md

README.md

@@ -1,7 +1,12 @@
+---
+license: apache-2.0
+language:
+- en
+---
 # FaceNet Triplet ResNet Model (Grayscale, 112x112, Mobile-friendly)
 
 This repository provides a FaceNet-style triplet embedding model using ResNet backbones, optimized for mobile and edge devices:
-- Input: **Grayscale images** (`3` channel)
+- Input: **Grayscale images** (`3` channels)
 - Resolution: **112x112 pixels**
 - Output: **Embeddings** suitable for face recognition and verification
 
@@ -42,7 +47,7 @@ Obtain a face embedding from an input image, and compare embeddings (e.g., with
 import torch
 
 # Example: batch of 1 grayscale image of 112x112
-images = torch.randn(1, 1, 112, 112)  # (batch_size, channels, height, width)
+images = torch.randn(1, 3, 112, 112)  # (batch_size, channels, height, width)
 
 with torch.no_grad():
     embedding = model(images)  # embedding output suitable for face recognition
@@ -70,4 +75,4 @@ To perform recognition or verification, compare the embedding against a database
 
 ---
 
-*For contributions or issues, open a discussion or pull request.*
+*For contributions or issues, open a discussion or pull request.*