Merge branch 'master' into IT20251000

Project/Backend/ML_Models/Emotion_Detection_Model/emotion_model.json

+{"class_name": "Sequential", "config": {"name": "sequential", "layers": [{"class_name": "InputLayer", "config": {"batch_input_shape": [null, 48, 48, 1], "dtype": "float32", "sparse": false, "ragged": false, "name": "conv2d_input"}}, {"class_name": "Conv2D", "config": {"name": "conv2d", "trainable": true, "batch_input_shape": [null, 48, 48, 1], "dtype": "float32", "filters": 32, "kernel_size": [3, 3], "strides": [1, 1], "padding": "valid", "data_format": "channels_last", "dilation_rate": [1, 1], "groups": 1, "activation": "relu", "use_bias": true, "kernel_initializer": {"class_name": "GlorotUniform", "config": {"seed": null}}, "bias_initializer": {"class_name": "Zeros", "config": {}}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}}, {"class_name": "Conv2D", "config": {"name": "conv2d_1", "trainable": true, "dtype": "float32", "filters": 64, "kernel_size": [3, 3], "strides": [1, 1], "padding": "valid", "data_format": "channels_last", "dilation_rate": [1, 1], "groups": 1, "activation": "relu", "use_bias": true, "kernel_initializer": {"class_name": "GlorotUniform", "config": {"seed": null}}, "bias_initializer": {"class_name": "Zeros", "config": {}}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}}, {"class_name": "MaxPooling2D", "config": {"name": "max_pooling2d", "trainable": true, "dtype": "float32", "pool_size": [2, 2], "padding": "valid", "strides": [2, 2], "data_format": "channels_last"}}, {"class_name": "Dropout", "config": {"name": "dropout", "trainable": true, "dtype": "float32", "rate": 0.25, "noise_shape": null, "seed": null}}, {"class_name": "Conv2D", "config": {"name": "conv2d_2", "trainable": true, "dtype": "float32", "filters": 128, "kernel_size": [3, 3], "strides": [1, 1], "padding": "valid", "data_format": "channels_last", "dilation_rate": [1, 1], "groups": 1, "activation": "relu", "use_bias": true, "kernel_initializer": {"class_name": "GlorotUniform", "config": {"seed": null}}, "bias_initializer": {"class_name": "Zeros", "config": {}}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}}, {"class_name": "MaxPooling2D", "config": {"name": "max_pooling2d_1", "trainable": true, "dtype": "float32", "pool_size": [2, 2], "padding": "valid", "strides": [2, 2], "data_format": "channels_last"}}, {"class_name": "Conv2D", "config": {"name": "conv2d_3", "trainable": true, "dtype": "float32", "filters": 128, "kernel_size": [3, 3], "strides": [1, 1], "padding": "valid", "data_format": "channels_last", "dilation_rate": [1, 1], "groups": 1, "activation": "relu", "use_bias": true, "kernel_initializer": {"class_name": "GlorotUniform", "config": {"seed": null}}, "bias_initializer": {"class_name": "Zeros", "config": {}}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}}, {"class_name": "MaxPooling2D", "config": {"name": "max_pooling2d_2", "trainable": true, "dtype": "float32", "pool_size": [2, 2], "padding": "valid", "strides": [2, 2], "data_format": "channels_last"}}, {"class_name": "Dropout", "config": {"name": "dropout_1", "trainable": true, "dtype": "float32", "rate": 0.25, "noise_shape": null, "seed": null}}, {"class_name": "Flatten", "config": {"name": "flatten", "trainable": true, "dtype": "float32", "data_format": "channels_last"}}, {"class_name": "Dense", "config": {"name": "dense", "trainable": true, "dtype": "float32", "units": 1024, "activation": "relu", "use_bias": true, "kernel_initializer": {"class_name": "GlorotUniform", "config": {"seed": null}}, "bias_initializer": {"class_name": "Zeros", "config": {}}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}}, {"class_name": "Dropout", "config": {"name": "dropout_2", "trainable": true, "dtype": "float32", "rate": 0.5, "noise_shape": null, "seed": null}}, {"class_name": "Dense", "config": {"name": "dense_1", "trainable": true, "dtype": "float32", "units": 7, "activation": "softmax", "use_bias": true, "kernel_initializer": {"class_name": "GlorotUniform", "config": {"seed": null}}, "bias_initializer": {"class_name": "Zeros", "config": {}}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}}]}, "keras_version": "2.4.0", "backend": "tensorflow"}
\ No newline at end of file

Project/Backend/Server_Python/controllers/audio_detect_controler.py

+from fastapi import APIRouter,FastAPI, UploadFile ,File,HTTPException
+from fastapi.responses import FileResponse
+
+import os
+from core.logger import setup_logger
+from services.audio_detect_service import EmotionPredictionService
+import tensorflow as tf
+
+app = FastAPI()
+router = APIRouter()
+audio: UploadFile
+logger = setup_logger()
+model = tf.keras.models.load_model('../ML_Models/Emotion_Detection_Model/mymodel.h5')
+prediction_service = EmotionPredictionService(model)
+
+
+@router.post("/upload_emotion/audio", tags=["Emotion Detection"])
+async def upload_audio(audio: UploadFile = File(...)):
+    try:
+        file_location = f"files/emotion/audio/{audio.filename}"
+        with open(file_location, "wb") as file:
+            file.write(audio.file.read())
+
+        return {"text": "OK"}
+    except Exception as e:
+        logger.info(f"Failed to upload file. {e}")
+        raise HTTPException(
+            status_code=500,
+            detail="Failed to upload the audio"
+        )
+    
+@router.post('/predict_emotion/audio', tags=["Emotion Detection"])
+def predict_using_audio(audio_request: UploadFile = File(...)):
+    try:
+        return prediction_service.predict_emotion_detection_audio_new(audio_request)
+    except Exception as e:
+        logger.info(f"Error. {e}")
+        raise HTTPException(
+            status_code=500,
+            detail="Request Failed."
+        )
+    
+        
+

Project/Backend/Server_Python/controllers/video_detect_controler.py

+from fastapi import APIRouter,FastAPI, UploadFile ,File,HTTPException
+from fastapi.responses import FileResponse
+from keras.models import model_from_json
+
+import os
+from core.logger import setup_logger
+from services.video_detection_service import EmotionPredictionService
+import tensorflow as tf
+
+import os
+
+# Get the absolute path to the 'model' directory
+model_directory = os.path.abspath('model')
+
+# Construct the absolute path to 'emotion_model.json'
+json_file_path = os.path.join(model_directory, 'emotion_model.json')
+
+# Open the JSON file
+# json_file = open(json_file_path, 'r')
+
+app = FastAPI()
+router = APIRouter()
+video: UploadFile
+logger = setup_logger()
+# Load emotion detection model
+json_file = open('../ML_Models/Emotion_Detection_Model/emotion_model.json', 'r')
+loaded_model_json = json_file.read()
+json_file.close()
+emotion_model = model_from_json(loaded_model_json)
+emotion_model.load_weights("../ML_Models/Emotion_Detection_Model/emotion_model.h5")
+prediction_service = EmotionPredictionService(emotion_model)
+
+@router.post("/upload_emotion/video", tags=["Emotion Detection"])
+async def upload_video(video: UploadFile = File(...)):
+    try:
+        file_location = f"files/emotion/video/{video.filename}"
+        with open(file_location, "wb") as file:
+            file.write(video.file.read())
+
+        return {"text": "OK2"}
+    except Exception as e:
+        logger.info(f"Failed to upload file. {e}")
+        raise HTTPException(
+            status_code=500,
+            detail="Failed to upload the video"
+        )
+    
+@router.post('/predict_emotion/video', tags=["Emotion Detection"])
+def predict_using_video(video_request: UploadFile = File(...)):
+    try:
+        return prediction_service.predict_emotion_detection_video_new(video_request= video_request)
+        return {"text": "OK5"}
+    except Exception as e:
+        logger.info(f"Error. {e}")
+        raise HTTPException(
+            status_code=500,
+            detail="Request Failed."
+        )
+    
+        
+

Project/Backend/Server_Python/main.py

@@ -3,6 +3,8 @@ from controllers import (
     translate_controler,
     users_controller,
     video_to_sign_language_controller,
+    audio_detect_controler,
+    video_detect_controler
 )
 from fastapi.responses import RedirectResponse
 from fastapi.middleware.cors import CORSMiddleware
@@ -42,6 +44,8 @@ logger = setup_logger()
 app.include_router(users_controller.router)
 app.include_router(translate_controler.router)
 app.include_router(video_to_sign_language_controller.router)
+app.include_router(audio_detect_controler.router)
+app.include_router(video_detect_controler.router)
 
 
 # Add cores middleware
@@ -72,4 +76,4 @@ app.add_middleware(
 @app.get("/")
 async def root():
     url = app.docs_url or "/docs"
-    return RedirectResponse(url)
+    return RedirectResponse(url)
\ No newline at end of file

Project/Backend/Server_Python/requirements.txt

@@ -7,4 +7,5 @@ moviepy==1.0.3
 SpeechRecognition==3.10.0
 tk==0.1.0
 requests==2.31.0
-pymongo==4.5.0
\ No newline at end of file
+pymongo==4.5.0
+librosa==0.10.1
\ No newline at end of file

Project/Backend/Server_Python/services/audio_detect_service.py

+# from fastapi.types import ModelNameMap
+# from sklearn import model_selection
+# import tensorflow as tf
+import numpy as np
+import librosa
+from fastapi import HTTPException, UploadFile
+from typing import Dict
+import os
+
+from core.logger import setup_logger
+
+
+logger = setup_logger()
+
+class EmotionPredictionService:
+    def __init__(self, model):
+        self.model = model
+        
+
+    def predict_emotion_detection_audio(self,audio_request: UploadFile) -> Dict[str, str]:
+        try:
+             # Create a temporary file to save the audio
+            audio_location = f"files/emotion/audio/{audio_request.filename}"
+            with open(audio_location, "wb") as file:
+                file.write(audio_request.file.read())
+
+            # Load the audio data from the saved file
+            y, sr = librosa.load(audio_location)
+            mfccs = np.mean(librosa.feature.mfcc(y=y, sr=sr, n_mfcc=40).T, axis=0)
+            test_point = np.reshape(mfccs, newshape=(1, 40, 1))
+            predictions = self.model.predict(test_point)
+
+
+           
+
+            emotions = {
+                1: 'neutral', 2: 'calm', 3: 'happy', 4: 'sad',
+                5: 'angry', 6: 'fearful', 7: 'disgust', 8: 'surprised'
+            }
+            predicted_emotion = emotions[np.argmax(predictions[0]) + 1]
+
+            return {"predicted_emotion": predicted_emotion}
+        except Exception as e:
+            logger.error(f"Failed to make predictions. {str(e)}")
+            raise HTTPException(
+                status_code=500,
+                detail=f"Failed to make predictions. Error: {str(e)}"
+            )
+
+
+    def predict_emotion_detection_audio_new(self, audio_request: UploadFile) -> Dict[str, str]:
+        try:
+
+             # Create a temporary file to save the audio
+            audio_location = f"files/emotion/audio/{audio_request.filename}"
+            with open(audio_location, "wb") as file:
+                file.write(audio_request.file.read())
+
+            # Load the audio data from the saved file
+            y, sr = librosa.load(audio_location)
+            mfccs = np.mean(librosa.feature.mfcc(y=y, sr=sr, n_mfcc=40).T, axis=0)
+            test_point = np.reshape(mfccs, newshape=(1, 40, 1))
+            predictions = self.model.predict(test_point)
+
+            emotions = {
+                1: 'neutral', 2: 'calm', 3: 'happy', 4: 'sad',
+                5: 'angry', 6: 'fearful', 7: 'disgust', 8: 'surprised'
+            }
+            predicted_emotion = emotions[np.argmax(predictions[0]) + 1]
+
+            return {"predicted_emotion": predicted_emotion}
+        except Exception as e:
+            logger.error(f"Failed to make predictions. {str(e)}")
+            raise HTTPException(
+                status_code=500,
+                detail=f"Failed to make predictions. Error: {str(e)}"
+            )
+
+
+

Project/Backend/Server_Python/services/video_detection_service.py

+from fastapi import FastAPI, UploadFile, HTTPException
+from typing import Dict
+import cv2
+import numpy as np
+from keras.models import model_from_json
+import os
+
+app = FastAPI()
+
+from core.logger import setup_logger
+
+
+logger = setup_logger()
+    # Define the emotion labels
+emotion_dict = {0: "Angry", 1: "Disgusted", 2: "Fearful", 3: "Happy", 4: "Neutral", 5: "Sad", 6: "Surprised"}
+
+# Load the emotion detection model
+json_file = open('../ML_Models/Emotion_Detection_Model/emotion_model.json', 'r')
+loaded_model_json = json_file.read()
+json_file.close()
+emotion_model = model_from_json(loaded_model_json)
+emotion_model.load_weights("../ML_Models/Emotion_Detection_Model/emotion_model.h5")
+
+class EmotionPredictionService:
+    def __init__(self, model):
+        self.model = model
+
+    def predict_emotion_detection_video(video_request: UploadFile) -> Dict[str, str]:
+        try:
+            # Create a temporary file to save the video
+            video_location = f"files/emotion/video/{video_request.filename}"
+            with open(video_location, "wb") as file:
+                file.write(video_request.file.read())
+
+            # Initialize video capture
+            cap = cv2.VideoCapture(video_location)
+            if not cap.isOpened():
+                raise HTTPException(
+                    status_code=400,
+                    detail="Failed to open video file."
+                )
+
+            predicted_emotions = []
+
+            while True:
+                ret, frame = cap.read()
+                if not ret:
+                    break
+
+                emotions = predict_emotion_from_frame(frame)
+                predicted_emotions.extend(emotions)
+
+            cap.release()
+            os.remove(video_location)
+
+            return {"predicted_emotions": predicted_emotions}
+        except Exception as e:
+            logger.error(f"Failed to make predictions. {str(e)}")
+            raise HTTPException(
+                status_code=500,
+                detail=f"Failed to make predictions. Error: {str(e)}"
+            )
+
+    def predict_emotion_detection_video_new(self,video_request: UploadFile) -> Dict[str, str]:
+        try:
+            
+            # Create a temporary file to save the video
+            video_location = f"files/emotion/video/{video_request.filename}"
+            with open(video_location, "wb") as file:
+                file.write(video_request.file.read())
+
+            # Initialize video capture
+            cap = cv2.VideoCapture(video_location)
+            if not cap.isOpened():
+                raise HTTPException(
+                    status_code=400,
+                    detail="Failed to open video file."
+                )
+
+            predicted_emotions = []
+
+            while True:
+                ret, frame = cap.read()
+                if not ret:
+                    break
+
+                emotions = predict_emotion_from_frame(frame)
+                predicted_emotions.extend(emotions)
+
+            cap.release()
+            os.remove(video_location)
+
+            return {"predicted_emotions": predicted_emotions}
+        except Exception as e:
+            logger.error(f"Failed to make predictions. {str(e)}")
+            raise HTTPException(
+                status_code=500,
+                detail=f"Failed to make predictions. Error: {str(e)}"
+            )
+        # Function to predict emotion from a video frame
+def predict_emotion_from_frame(frame):
+    gray_frame = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
+    face_detector = cv2.CascadeClassifier('../ML_Models/Emotion_Detection_Model/haarcascade_frontalface_default.xml')
+    num_faces = face_detector.detectMultiScale(gray_frame, scaleFactor=1.3, minNeighbors=5)
+
+    emotions = []
+
+    for (x, y, w, h) in num_faces:
+        roi_gray_frame = gray_frame[y:y + h, x:x + w]
+        cropped_img = np.expand_dims(np.expand_dims(cv2.resize(roi_gray_frame, (48, 48)), -1), 0)
+        emotion_prediction = emotion_model.predict(cropped_img)
+        maxindex = int(np.argmax(emotion_prediction))
+        emotions.append(emotion_dict[maxindex])
+
+    return emotions