import numpy as np import cv2 from matplotlib import pyplot as plt import torch # In the below line,remove '.' while working on your local system. However Make sure that '.' is present before face_recognition_model while uploading to the server, Do not remove it. from .face_recognition_model import * from PIL import Image import base64 import io import os import joblib import pickle # Add more imports if required ########################################################################################################################################### # Caution: Don't change any of the filenames, function names and definitions # # Always use the current_path + file_name for refering any files, without it we cannot access files on the server # ########################################################################################################################################### # Current_path stores absolute path of the file from where it runs. current_path = os.path.dirname(os.path.abspath(__file__)) # --- GLOBAL SETUP: Must match your training transforms --- # Define the transformation pipeline for inference trnscm = transforms.Compose([ transforms.Grayscale(num_output_channels=1), transforms.Resize((100, 100)), transforms.ToTensor() ]) CLASS_NAMES = ['Person0', 'Person1', 'Person2', 'Person3', 'Person4'] # ADJUST THIS! # --- Model Filenames --- SIAMESE_MODEL_PATH = current_path + '/siamese_model.t7' KNN_CLASSIFIER_PATH = current_path + '/decision_tree_model.sav' SCALER_PATH = current_path + '/face_recognition_scaler.sav' #1) The below function is used to detect faces in the given image. #2) It returns only one image which has maximum area out of all the detected faces in the photo. #3) If no face is detected,then it returns zero(0). def detected_face(image): eye_haar = current_path + '/haarcascade_eye.xml' face_haar = current_path + '/haarcascade_frontalface_default.xml' face_cascade = cv2.CascadeClassifier(face_haar) eye_cascade = cv2.CascadeClassifier(eye_haar) gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY) faces = face_cascade.detectMultiScale(gray, 1.3, 5) face_areas=[] images = [] required_image=0 for i, (x,y,w,h) in enumerate(faces): face_cropped = gray[y:y+h, x:x+w] face_areas.append(w*h) images.append(face_cropped) required_image = images[np.argmax(face_areas)] required_image = Image.fromarray(required_image) return required_image #1) Images captured from mobile is passed as parameter to the below function in the API call. It returns the similarity measure between given images. #2) The image is passed to the function in base64 encoding, Code for decoding the image is provided within the function. #3) Define an object to your siamese network here in the function and load the weight from the trained network, set it in evaluation mode. #4) Get the features for both the faces from the network and return the similarity measure, Euclidean,cosine etc can be it. But choose the Relevant measure. #5) For loading your model use the current_path+'your model file name', anyhow detailed example is given in comments to the function #Caution: Don't change the definition or function name; for loading the model use the current_path for path example is given in comments to the function def get_similarity(img1, img2): device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu") det_img1 = detected_face(img1) det_img2 = detected_face(img2) if(det_img1 == 0 or det_img2 == 0): det_img1 = Image.fromarray(cv2.cvtColor(img1, cv2.COLOR_BGR2GRAY)) det_img2 = Image.fromarray(cv2.cvtColor(img2, cv2.COLOR_BGR2GRAY)) face1 = trnscm(det_img1).unsqueeze(0) face2 = trnscm(det_img2).unsqueeze(0) ########################################################################################## ##Example for loading a model using weight state dictionary: ## ## feature_net = light_cnn() #Example Network ## ## model = torch.load(current_path + '/siamese_model.t7', map_location=device) ## ## feature_net.load_state_dict(model['net_dict']) ## ## ## ##current_path + '/' is path of the saved model if present in ## ##the same path as this file, we recommend to put in the same directory ## ########################################################################################## ########################################################################################## # YOUR CODE HERE, load the model # YOUR CODE HERE, return similarity measure using your model # 1. Initialize and Load Siamese Network try: # Assuming your Siamese Network class is named 'SiameseNetwork' siamese_net = SiameseNetwork().to(device) siamese_net.load_state_dict(torch.load(SIAMESE_MODEL_PATH, map_location=device)) siamese_net.eval() except Exception as e: print(f"Error loading Siamese Model get_similarity: {e}") return -1 # Return error code # 2. Get Features (Embeddings) with torch.no_grad(): # Get the feature vector from one tower/forward_once method # Ensure your SiameseNetwork class has a forward_once or get_embedding method embed1 = siamese_net.forward_once(face1).cpu().numpy() embed2 = siamese_net.forward_once(face2).cpu().numpy() # 3. Calculate Similarity Measure # The Euclidean distance is the fundamental metric used by the Triplet/Contrastive loss. # We return the NEGATIVE Euclidean distance or COSINE similarity, as *higher* value usually means *more* similar. # Option A: Euclidean Distance (Lower is better) -> return NEGATIVE distance for API expectation # distance = euclidean_distances(embed1, embed2)[0][0] # similarity = -distance # Option B: Cosine Similarity (Higher is better) -> Recommended similarity = cosine_similarity(embed1, embed2)[0][0] return float(similarity) #1) Image captured from mobile is passed as parameter to this function in the API call, It returns the face class in the string form ex: "Person1" #2) The image is passed to the function in base64 encoding, Code to decode the image provided within the function #3) Define an object to your network here in the function and load the weight from the trained network, set it in evaluation mode #4) Perform necessary transformations to the input(detected face using the above function). #5) Along with the siamese, you need the classifier as well, which is to be finetuned with the faces that you are training ##Caution: Don't change the definition or function name; for loading the model use the current_path for path example is given in comments to the function def get_face_class(img1): device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu") det_img1 = detected_face(img1) if(det_img1 == 0): det_img1 = Image.fromarray(cv2.cvtColor(img1, cv2.COLOR_BGR2GRAY)) ##YOUR CODE HERE, return face class here ##Hint: you need a classifier finetuned for your classes, it takes o/p of siamese as i/p to it ##Better Hint: Siamese experiment is covered in one of the labs face1_tensor = trnscm(det_img1).unsqueeze(0).to(device) # 1. Load Siamese Network (Feature Extractor) try: siamese_net = SiameseNetwork().to(device) siamese_net.load_state_dict(torch.load(SIAMESE_MODEL_PATH, map_location=device)) siamese_net.eval() except Exception as e: return f"Error loading Siamese Model get_face_class: {e}" # 2. Extract Embedding with torch.no_grad(): embedding_np = siamese_net.forward_once(face1_tensor).cpu().numpy() # 3. Load Sklearn Scaler and Classifier (Joblib) try: knn_classifier = joblib.load(KNN_CLASSIFIER_PATH) scaler = joblib.load(SCALER_PATH) except Exception as e: return f"Error loading Sklearn models: {e}" # 4. Preprocess Embedding and Predict # The embedding must be reshaped to (1, N_features) for the scaler embedding_scaled = scaler.transform(embedding_np.reshape(1, -1)) # Perform prediction (returns a NumPy array with the predicted label index) predicted_label_index = knn_classifier.predict(embedding_scaled)[0] # 5. Map index to Class Name if predicted_label_index < len(CLASS_NAMES): predicted_class_name = CLASS_NAMES[predicted_label_index] else: predicted_class_name = "UNKNOWN_CLASS" return predicted_class_name