Added files to spaces

Dockerfile

@@ -0,0 +1,14 @@
+FROM python:3.11
+
+RUN useradd -m -u 1000 user
+USER user
+ENV PATH="/home/user/.local/bin:$PATH"
+
+WORKDIR /app
+
+COPY --chown=user ./requirements.txt requirements.txt
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
+
+COPY --chown=user . /app
+
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

ModelCode.py

@@ -0,0 +1,51 @@
+import os
+import torch
+from transformers import CLIPProcessor, CLIPModel
+from PIL import Image
+import cv2
+from collections import Counter
+
+clip_model = CLIPModel.from_pretrained("openai/clip-vit-base-patch32")
+clip_processor = CLIPProcessor.from_pretrained("openai/clip-vit-base-patch32")
+
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+clip_model = clip_model.to(device)
+
+def extract_frames(video_path, frame_rate=5):
+    cap = cv2.VideoCapture(video_path)
+    fps = cap.get(cv2.CAP_PROP_FPS)
+    frames = []
+    count = 0
+
+    while cap.isOpened():
+        ret, frame = cap.read()
+        if not ret:
+            break
+        if int(count % (fps * frame_rate)) == 0:
+            img = Image.fromarray(cv2.cvtColor(frame, cv2.COLOR_BGR2RGB))
+            frames.append(img)
+        count += 1
+
+    cap.release()
+    return frames
+
+def classify_frame_with_clip(image):
+    texts = ["Ayurveda", "Non-Ayurveda"]
+    inputs = clip_processor(text=texts, images=image, return_tensors="pt", padding=True).to(device)
+    outputs = clip_model(**inputs)
+    logits_per_image = outputs.logits_per_image
+    probs = logits_per_image.softmax(dim=1)
+    pred = torch.argmax(probs, dim=1).item()
+    return texts[pred]
+
+def classify_video(video_path):
+    frames = extract_frames(video_path, frame_rate=5)  
+
+    clip_preds = []
+
+    for frame in frames:
+        clip_result = classify_frame_with_clip(frame)
+        clip_preds.append(clip_result)
+
+    final_pred = Counter(clip_preds).most_common(1)[0][0]
+    return {"Type": final_pred}

app.py

@@ -0,0 +1,45 @@
+from fastapi import FastAPI, UploadFile, File
+from fastapi.middleware.cors import CORSMiddleware
+import os
+import cv2
+from PIL import Image
+from ModelCode import classify_video
+
+app = FastAPI()
+
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],  
+    allow_credentials=True,
+    allow_methods=["*"],  
+    allow_headers=["*"],  
+)
+
+
+@app.get("/")
+async def root():
+    return {"message": "Welcome to Video Classification API!"}
+
+
+@app.post("/Video_Processing")
+async def process_video(file: UploadFile = File(...)):
+    try:
+        file_path = f"./{file.filename}"
+        if not file.filename.endswith(('.mp4', '.avi', '.mov')):
+            return {"error": "File is not a supported video format"}
+
+        with open(file_path, "wb") as video_file:
+            video_file.write(await file.read())
+
+        result = classify_video(file_path)
+
+        return {
+            "Type": result["Type"],
+        }
+
+    except Exception as e:
+        return {"error": str(e)}
+
+    finally:
+        if os.path.exists(file_path):
+            os.remove(file_path)

requirements.txt

@@ -0,0 +1,12 @@
+fastapi
+uvicorn
+torch
+transformers
+opencv-python
+pillow
+pytesseract
+python-multipart
+scikit-learn
+fastapi[all]
+tqdm
+numpy