Upload 4 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+demo_video.mp4 filter=lfs diff=lfs merge=lfs -text

demo_video.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cb921ae36d4d7ce8f9e13586166aaaba55ef9f3f384fcc43bffffae39f71cb0
+size 4432717

process_emotion_video.py

@@ -0,0 +1,119 @@
+import os
+import tempfile
+import torch
+import cv2
+from PIL import Image
+from torchvision import transforms
+from facenet_pytorch import MTCNN
+
+def process_emotion(input_video):
+ try:
+ # Load the pre-trained CNN model
+ model = torch.hub.load('pytorch/vision:v0.10.0', 'resnet18', pretrained=True)
+ num_ftrs = model.fc.in_features
+ model.fc = torch.nn.Linear(num_ftrs, 7) # 7 classes for emotions
+
+ # Load the pre-trained weights
+ model.eval()
+
+ # Define emotions
+ emotions = ["Angry", "Disgust", "Fear", "Happy", "Sad", "Surprise", "Neutral"]
+
+ # Initialize MTCNN for face detection
+ mtcnn = MTCNN()
+
+ # Open the video capture
+ cap = cv2.VideoCapture(input_video.name)
+
+ if not cap.isOpened():
+ return "Error: Could not open video capture."
+
+ # Create a temporary directory to store the frames
+ temp_dir = tempfile.mkdtemp()
+ frame_paths = []
+
+ # Define image transformations
+ preprocess = transforms.Compose([
+ transforms.Resize(224),
+ transforms.ToTensor(),
+ transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
+ ])
+
+ # Process each frame of the video
+ frame_count = 0
+ while cap.isOpened():
+ ret, frame = cap.read()
+
+ if not ret:
+ break
+
+ if frame is None:
+ print("Error: Empty frame.")
+ continue
+
+ frame_count += 1
+
+ pil_frame = Image.fromarray(cv2.cvtColor(frame, cv2.COLOR_BGR2RGB))
+ face_boxes, _ = mtcnn.detect(pil_frame)
+
+ if face_boxes is None:
+ print(f"No face detected in frame {frame_count}.")
+ else:
+ for box in face_boxes:
+ x1, y1, x2, y2 = box.astype(int)
+ w = x2 - x1
+ h = y2 - y1
+
+ face_roi = frame[y1:y2, x1:x2]
+ pil_face = Image.fromarray(cv2.cvtColor(face_roi, cv2.COLOR_BGR2RGB))
+
+ input_tensor = preprocess(pil_face)
+ input_batch = input_tensor.unsqueeze(0)
+
+ with torch.no_grad():
+ output = model(input_batch)
+
+ predicted_emotion = output.argmax().item()
+
+ emotion_label = emotions[predicted_emotion]
+
+ cv2.rectangle(frame, (x1, y1), (x2, y2), (0, 255, 0), 2)
+ cv2.putText(frame, emotion_label, (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.9, (0, 255, 0), 2)
+
+ frame_path = os.path.join(temp_dir, f"{frame_count:04d}.png")
+ cv2.imwrite(frame_path, frame)
+ frame_paths.append(frame_path)
+
+ cap.release()
+ cv2.destroyAllWindows()
+
+ if not frame_paths:
+ return "No faces detected in the video."
+
+ # Convert the frames to a video
+ output_path = "output_video.mp4"
+ fourcc = cv2.VideoWriter_fourcc(*'mp4v')
+
+ # Get dimensions from the first frame
+ sample_frame = cv2.imread(frame_paths[0])
+ if sample_frame is None:
+ return "Error: Unable to read sample frame."
+
+ frame_height, frame_width, _ = sample_frame.shape
+
+ out = cv2.VideoWriter(output_path, fourcc, 30, (frame_width, frame_height))
+
+ for frame_path in frame_paths:
+ frame = cv2.imread(frame_path)
+ if frame is not None:
+ out.write(frame)
+ os.remove(frame_path)
+ else:
+ print(f"Warning: Unable to read frame {frame_path}")
+
+ out.release()
+
+ return output_path
+
+ except Exception as e:
+ return f"An error occurred: {str(e)}"

requirements.txt

@@ -0,0 +1,7 @@
+ffmpeg
+facenet-pytorch
+torch 
+torchvision
+streamlit 
+opencv-python-headless 
+pyngrok

web.py

@@ -0,0 +1,41 @@
+import streamlit as st
+from process_emotion_video import process_emotion
+
+def main():
+ st.title("Emotion Recognition in Video")
+ option = st.radio("Choose an option:", ("Upload a video file", "Example Video"))
+ if option == "Upload a video file":
+ # Upload video file
+ uploaded_file = st.file_uploader("Upload a video file", type=["mp4"])
+ 
+ if uploaded_file is not None:
+ st.write("Processing...")
+ 
+ # Process the video and get the output path
+ output_path = process_emotion(uploaded_file)
+ 
+ if output_path.endswith(".mp4"):
+ st.video(output_path)
+ 
+ # Add a download button for the processed video
+ st.download_button(
+ label="Download Processed Video",
+ data=output_path,
+ key="download_processed_video",
+ file_name="processed_video.mp4",
+ )
+ else:
+ st.error("An error occurred during video processing.")
+ else:
+ example_video_path = 'demo_video.mp4'
+ st.video(example_video_path)
+ st.download_button(
+ label="Download Processed Video",
+ data=example_video_path,
+ key="download_demo_video",
+ file_name="demo_video.mp4",
+ )
+ 
+
+if __name__ == "__main__":
+ main()