Upload 6 files

.gitattributes

@@ -25,7 +25,6 @@
 *.safetensors filter=lfs diff=lfs merge=lfs -text
 saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
 *.tgz filter=lfs diff=lfs merge=lfs -text
 *.wasm filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,7 @@
+flagged/
+*.pt
+*.png
+*.jpg
+*.mp4
+*.mkv
+gradio_cached_examples/

README.md

@@ -1,10 +1,10 @@
 ---
-title: DRIVER DETECT
-emoji: 😻
-colorFrom: gray
-colorTo: yellow
+title: Pothole Yolov8 Nano
+emoji: 🌖
+colorFrom: pink
+colorTo: blue
 sdk: gradio
-sdk_version: 6.0.2
+sdk_version: 3.16.1
 app_file: app.py
 pinned: false
 license: mit

app.py

@@ -1,92 +1,104 @@
-import gradio as gr
-from transformers import pipeline
-import PyPDF2
-
-# Model tốt nhất cho tiếng Anh + chạy được trên HF Free
-summarizer = pipeline(
-    "summarization",
-    model="google/pegasus-xsum"
-)
-
-def read_pdf(file_obj):
-    """Đọc PDF từ Gradio file object."""
-    try:
-        with open(file_obj.name, "rb") as f:
-            reader = PyPDF2.PdfReader(f)
-            text = ""
-            for page in reader.pages:
-                t = page.extract_text()
-                if t:
-                    text += t + "\n"
-        return text
-    except Exception as e:
-        return None
-
-
-def chunk_text(text, max_chars=512):
-    """
-    Chia text thành đoạn nhỏ an toàn cho Pegasus.
-    Pegasus chịu tối đa ~512 tokens → nên dùng 512 chars để chắc chắn không crash.
-    """
-    chunks = []
-    text = text.strip()
-
-    while len(text) > max_chars:
-        # tìm dấu chấm gần nhất để chia tự nhiên
-        cut = text.rfind('.', 0, max_chars)
-        if cut == -1:
-            # không có dấu chấm → cắt cứng
-            cut = max_chars
-        chunk = text[:cut].strip()
-        if len(chunk) > 0:
-            chunks.append(chunk)
-        text = text[cut:].strip()
-
-    if len(text) > 0:
-        chunks.append(text)
-
-    return chunks
-
-
-def summarize_pdf(pdf_file):
-    if pdf_file is None:
-        return "Hãy upload một file PDF."
-
-    text = read_pdf(pdf_file)
-    if text is None:
-        return "Lỗi đọc PDF — có thể file bị mã hóa hoặc không phải PDF chuẩn."
-
-    text = text.strip()
-    if len(text) < 50:
-        return "PDF quá ngắn hoặc không có nội dung văn bản."
-
-    # chia nhỏ text → tránh lỗi CPU + tránh timeout HF
-    chunks = chunk_text(text)
-    summaries = []
-
-    for i, chunk in enumerate(chunks):
-        try:
-            result = summarizer(
-                chunk,
-                max_length=120,  # phù hợp Pegasus
-                min_length=20,
-                do_sample=False
-            )
-            summaries.append(result[0]["summary_text"])
-        except Exception as e:
-            summaries.append(f"[Lỗi khi tóm tắt đoạn {i+1}]: {e}")
-
-    # nối summaries lại
-    return "\n\n".join(summaries)
-
-
-with gr.Blocks() as demo:
-    gr.Markdown("## 📝 Tóm tắt PDF bằng AI (Pegasus + Gradio)")
-
-    pdf = gr.File(label="Upload PDF", file_types=[".pdf"])
-    output = gr.Textbox(lines=12, label="Kết quả tóm tắt")
-
-    btn = gr.Button("Tóm tắt PDF")
-    btn.click(fn=summarize_pdf, inputs=pdf, outputs=output)
-
-demo.launch()
+import gradio as gr
+import cv2
+import requests
+import os
+
+from ultralytics import YOLO
+
+file_urls = [
+    'https://www.dropbox.com/s/b5g97xo901zb3ds/pothole_example.jpg?dl=1',
+    'https://www.dropbox.com/s/86uxlxxlm1iaexa/pothole_screenshot.png?dl=1',
+    'https://www.dropbox.com/s/7sjfwncffg8xej2/video_7.mp4?dl=1'
+]
+
+def download_file(url, save_name):
+    url = url
+    if not os.path.exists(save_name):
+        file = requests.get(url)
+        open(save_name, 'wb').write(file.content)
+
+for i, url in enumerate(file_urls):
+    if 'mp4' in file_urls[i]:
+        download_file(
+            file_urls[i],
+            f"video.mp4"
+        )
+    else:
+        download_file(
+            file_urls[i],
+            f"image_{i}.jpg"
+        )
+
+model = YOLO('best.pt')
+path  = [['image_0.jpg'], ['image_1.jpg']]
+video_path = [['video.mp4']]
+
+def show_preds_image(image_path):
+    image = cv2.imread(image_path)
+    outputs = model.predict(source=image_path)
+    results = outputs[0].cpu().numpy()
+    for i, det in enumerate(results.boxes.xyxy):
+        cv2.rectangle(
+            image,
+            (int(det[0]), int(det[1])),
+            (int(det[2]), int(det[3])),
+            color=(0, 0, 255),
+            thickness=2,
+            lineType=cv2.LINE_AA
+        )
+    return cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
+
+inputs_image = [
+    gr.components.Image(type="filepath", label="Input Image"),
+]
+outputs_image = [
+    gr.components.Image(type="numpy", label="Output Image"),
+]
+interface_image = gr.Interface(
+    fn=show_preds_image,
+    inputs=inputs_image,
+    outputs=outputs_image,
+    title="Pothole detector",
+    examples=path,
+    cache_examples=False,
+)
+
+def show_preds_video(video_path):
+    cap = cv2.VideoCapture(video_path)
+    while(cap.isOpened()):
+        ret, frame = cap.read()
+        if ret:
+            frame_copy = frame.copy()
+            outputs = model.predict(source=frame)
+            results = outputs[0].cpu().numpy()
+            for i, det in enumerate(results.boxes.xyxy):
+                cv2.rectangle(
+                    frame_copy,
+                    (int(det[0]), int(det[1])),
+                    (int(det[2]), int(det[3])),
+                    color=(0, 0, 255),
+                    thickness=2,
+                    lineType=cv2.LINE_AA
+                )
+            yield cv2.cvtColor(frame_copy, cv2.COLOR_BGR2RGB)
+
+inputs_video = [
+    gr.components.Video(type="filepath", label="Input Video"),
+
+]
+outputs_video = [
+    gr.components.Image(type="numpy", label="Output Image"),
+]
+interface_video = gr.Interface(
+    fn=show_preds_video,
+    inputs=inputs_video,
+    outputs=outputs_video,
+    title="Pothole detector",
+    examples=video_path,
+    cache_examples=False,
+)
+
+gr.TabbedInterface(
+    [interface_image, interface_video],
+    tab_names=['Image inference', 'Video inference']
+).queue().launch()

best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce9a23590d666fcca004d3a2330f3e30b229bbe9df0dbf4b0fd390c20fbe67fe
+size 6233272

requirements.txt

@@ -1,6 +1,47 @@
-transformers
-torch
-gradio
-PyPDF2
-sentencepiece
-accelerate
+# Ultralytics requirements
+# Usage: pip install -r requirements.txt
+
+# Base ----------------------------------------
+hydra-core>=1.2.0
+matplotlib>=3.2.2
+numpy>=1.18.5
+opencv-python>=4.1.1
+Pillow>=7.1.2
+PyYAML>=5.3.1
+requests>=2.23.0
+scipy>=1.4.1
+torch>=1.7.0
+torchvision>=0.8.1
+tqdm>=4.64.0
+ultralytics
+
+# Logging -------------------------------------
+tensorboard>=2.4.1
+# clearml
+# comet
+
+# Plotting ------------------------------------
+pandas>=1.1.4
+seaborn>=0.11.0
+
+# Export --------------------------------------
+# coremltools>=6.0  # CoreML export
+# onnx>=1.12.0  # ONNX export
+# onnx-simplifier>=0.4.1  # ONNX simplifier
+# nvidia-pyindex  # TensorRT export
+# nvidia-tensorrt  # TensorRT export
+# scikit-learn==0.19.2  # CoreML quantization
+# tensorflow>=2.4.1  # TF exports (-cpu, -aarch64, -macos)
+# tensorflowjs>=3.9.0  # TF.js export
+# openvino-dev  # OpenVINO export
+
+# Extras --------------------------------------
+ipython  # interactive notebook
+psutil  # system utilization
+thop>=0.1.1  # FLOPs computation
+# albumentations>=1.0.3
+# pycocotools>=2.0.6  # COCO mAP
+# roboflow
+
+# HUB -----------------------------------------
+GitPython>=3.1.24