Update main.py

main.py

@@ -2,13 +2,23 @@ import gradio as gr
 from ultralytics import YOLO
 import ai_gym
 import cv2
+import tempfile
+from PIL import Image
+import subprocess
 
-def process(video_path):
+# Function to upgrade pip
+def upgrade_pip():
+    subprocess.run(['pip', 'install', '--upgrade', 'pip'])
+
+# Process video function
+def process(video_path, pose_type):
+    upgrade_pip()  # Upgrade pip before executing the main function
     model = YOLO("yolov8n-pose.pt")
     cap = cv2.VideoCapture(video_path)
     assert cap.isOpened(), "Error reading video file"
     w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS))
 
+    temp_dir = tempfile.mkdtemp()  # Create a temporary directory to store processed frames
     video_writer = cv2.VideoWriter("output_video.mp4",
                                    cv2.VideoWriter_fourcc(*'mp4v'),
                                    fps,
@@ -17,7 +27,7 @@ def process(video_path):
     gym_object = ai_gym.AIGym()  # init AI GYM module
     gym_object.set_args(line_thickness=2,
                         view_img=False,  # Set view_img to False to prevent displaying the video in real-time
-                        pose_type="pullup",
+                        pose_type=pose_type,
                         kpts_to_check=[6, 8, 10])
 
     frame_count = 0
@@ -27,26 +37,32 @@ def process(video_path):
             print("Video processing has been successfully completed.")
             break
         frame_count += 1
-        results = model.track(im0, verbose=True)  # Tracking recommended
-        im0 = gym_object.start_counting(im0, results, frame_count)
-        video_writer.write(im0)
+        if frame_count % 5 == 0:  # Process every 5th frame
+            results = model.track(im0, verbose=False)  # Tracking recommended
+            im0 = gym_object.start_counting(im0, results, frame_count)
+            # Save processed frame as an image in the temporary directory
+            cv2.imwrite(f"{temp_dir}/{frame_count}.jpg", im0)
+
+    # Use PIL to create the final video from the processed frames
+    images = [Image.open(f"{temp_dir}/{i}.jpg") for i in range(1, frame_count + 1)]
+    images[0].save("output_video.mp4", save_all=True, append_images=images[1:], duration=1000/fps, loop=0)
 
     cap.release()
-    video_writer.release()
     cv2.destroyAllWindows()
 
     return "output_video.mp4"
 
 title = "Push-up Counter"
 description = "This app counts the number of push-ups in a video."
-# inputs = gr.inputs.Video(label='Input Video')
-# outputs = gr.outputs.Video(label='Processed Video')
+inputs = [gr.Video(label='Input Video'),  
+          gr.Radio(["pullups", "pushups", "absworkout"], label="Pose Type")]
+outputs = gr.Video(label='Output Video')
 example_list = ['Examples/PULL-UPS.mp4','Examples/PUSH-UPS.mp4']
 
 # Create the Gradio demo
 demo = gr.Interface(fn=process,
-                    inputs=gr.Video(label='Input Video'),  
-                    outputs=gr.Video(label='Output Video')
+                    inputs=inputs,
+                    outputs=outputs,
                     title=title,
                     description=description,
                     examples=example_list,
@@ -55,9 +71,3 @@ demo = gr.Interface(fn=process,
 
 # Launch the demo!
 demo.launch(show_api=True)
-
-
-
-
-
-