Duplicate from Enos-123/smoking-detection

Co-authored-by: Uppada Enos <Enos-123@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,51 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.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
+*.xz 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
+BoxF1_curve.png filter=lfs diff=lfs merge=lfs -text
+BoxP_curve.png filter=lfs diff=lfs merge=lfs -text
+BoxR_curve.png filter=lfs diff=lfs merge=lfs -text
+confusion_matrix_normalized.png filter=lfs diff=lfs merge=lfs -text
+labels_correlogram.jpg filter=lfs diff=lfs merge=lfs -text
+labels.jpg filter=lfs diff=lfs merge=lfs -text
+results.png filter=lfs diff=lfs merge=lfs -text
+train_batch0.jpg filter=lfs diff=lfs merge=lfs -text
+train_batch1.jpg filter=lfs diff=lfs merge=lfs -text
+train_batch2.jpg filter=lfs diff=lfs merge=lfs -text
+val_batch0_labels.jpg filter=lfs diff=lfs merge=lfs -text
+val_batch0_pred.jpg filter=lfs diff=lfs merge=lfs -text
+val_batch1_labels.jpg filter=lfs diff=lfs merge=lfs -text
+val_batch1_pred.jpg filter=lfs diff=lfs merge=lfs -text
+val_batch2_labels.jpg filter=lfs diff=lfs merge=lfs -text
+val_batch2_pred.jpg filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,98 @@
+---
+license: mit
+base_model:
+- Ultralytics/YOLO11
+pipeline_tag: object-detection
+tags:
+- english
+- YOLO
+- Ultralytics
+- Smoking
+---
+# 🚬 Smoke Detection with YOLOv11-Medium
+
+This repository contains a custom-trained **YOLOv11-Medium** object detection model designed to detect **cigarette smoke** in images and videos. It is ideal for use in **surveillance systems**, **public safety**, and **smoking zone enforcement**.
+
+---
+
+## 📊 Model Performance
+
+| Metric            | Value  |
+| ----------------- | ------ |
+| **Precision**     | 85.62% |
+| **Recall**        | 76.92% |
+| **mAP\@0.5**      | 82.90% |
+| **mAP\@0.5:0.95** | 44.69% |
+
+> Evaluated on a custom Roboflow dataset using YOLOv11 medium variant trained for optimal balance of accuracy and speed.
+
+---
+
+## 🧟‍♂️ Model Details
+
+* **Model**: YOLOv11-Medium
+* **Task**: Object Detection
+* **Classes**: `cigarette`
+* **Framework**: [Ultralytics YOLOv11](https://github.com/ultralytics/ultralytics)
+* **Training Source**: Roboflow Universe
+
+---
+
+## 📁 Dataset
+
+* **Name**: Cigarette Smoke Detection
+* **Source**: [Roboflow Dataset](https://universe.roboflow.com/yolo-pdvpx/cigarette-h2p1m)
+* **Format**: YOLO
+* **Annotations**: Bounding Boxes
+
+---
+
+## 💡 Usage
+
+### 1. Load the Model
+
+```python
+from ultralytics import YOLO
+
+model = YOLO("path/to/best.pt")  # Replace with your model path
+```
+
+### 2. Run Inference on an Image
+
+```python
+results = model("your_image.jpg", save=True)
+results.show()
+```
+
+### 3. Run Inference on a Video
+
+```python
+results = model("your_video.mp4", stream=True)
+for r in results:
+    r.show()
+```
+
+---
+
+```python
+model.export(format="onnx")
+```
+
+---
+
+## 📜 License
+
+This model is available under the MIT License. Refer to the LICENSE file for more details.
+
+---
+
+## 🤖 Author
+
+Uploaded and maintained by: **\[Uppada Enos]**
+Contact: \[[enosuppada2005@gmail.com](enosuppada2005@gmail.com)]
+
+---
+
+## 🌐 Model Hub
+
+You can access and test this model directly via Hugging Face Spaces or API once published.

best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ef558d3cf049d0acbb3f2322bc9e4e53db1a107426e3669622176c30c054d82
+size 40509349

results.csv

@@ -0,0 +1,19 @@
+epoch,time,train/box_loss,train/cls_loss,train/dfl_loss,metrics/precision(B),metrics/recall(B),metrics/mAP50(B),metrics/mAP50-95(B),val/box_loss,val/cls_loss,val/dfl_loss,lr/pg0,lr/pg1,lr/pg2
+1,61.6575,2.55441,4.17021,2.19689,0.54002,0.41393,0.39968,0.19368,1.74455,2.10085,1.5602,0.0673235,0.000330065,0.000330065
+2,119.92,2.24661,2.57943,1.9466,0.58516,0.55128,0.59652,0.27811,1.70036,1.52985,1.47648,0.0343016,0.000641507,0.000641507
+3,178.5,2.05606,2.20276,1.73122,0.76701,0.57692,0.67426,0.33289,1.72325,1.42233,1.42857,0.00125775,0.000930948,0.000930948
+4,236.78,1.96381,1.9806,1.62264,0.73032,0.57286,0.70852,0.33878,1.81984,1.28831,1.42777,0.000901,0.000901,0.000901
+5,295.481,1.9155,1.8592,1.58705,0.76849,0.64103,0.73533,0.36815,1.68015,1.17613,1.34742,0.000868,0.000868,0.000868
+6,353.902,1.85223,1.6956,1.53948,0.83522,0.71482,0.79398,0.39368,1.66345,1.10963,1.33195,0.000835,0.000835,0.000835
+7,411.908,1.82862,1.64859,1.51253,0.78807,0.66667,0.75795,0.36738,1.70381,1.1189,1.33361,0.000802,0.000802,0.000802
+8,470.188,1.77525,1.53503,1.48176,0.73839,0.76282,0.80984,0.41311,1.64764,1.09401,1.2848,0.000769,0.000769,0.000769
+9,528.329,1.74982,1.51936,1.44099,0.9057,0.67723,0.81205,0.41097,1.61583,1.02473,1.29448,0.000736,0.000736,0.000736
+10,586.372,1.74603,1.49073,1.4562,0.80603,0.75641,0.81043,0.4065,1.67276,1.06711,1.33151,0.000703,0.000703,0.000703
+11,644.238,1.70258,1.3957,1.41809,0.86302,0.72699,0.82452,0.40202,1.68068,1.03815,1.31049,0.00067,0.00067,0.00067
+12,702.568,1.66178,1.39864,1.40042,0.86215,0.73718,0.81874,0.40936,1.66186,1.03966,1.33055,0.000637,0.000637,0.000637
+13,760.768,1.64503,1.2869,1.3756,0.85704,0.77564,0.829,0.44806,1.57708,0.92028,1.2834,0.000604,0.000604,0.000604
+14,818.707,1.60885,1.29068,1.36613,0.89087,0.72436,0.83831,0.43034,1.64164,0.98011,1.32385,0.000571,0.000571,0.000571
+15,876.849,1.59296,1.24734,1.36747,0.84863,0.76282,0.84048,0.42416,1.64199,0.95917,1.30569,0.000538,0.000538,0.000538
+16,934.82,1.55322,1.18723,1.33105,0.89017,0.72736,0.84142,0.4201,1.65433,0.98758,1.2875,0.000505,0.000505,0.000505
+17,993.074,1.52138,1.16113,1.30727,0.88073,0.78205,0.85747,0.43186,1.65453,0.93064,1.29296,0.000472,0.000472,0.000472
+18,1053.66,1.49663,1.13472,1.29007,0.89096,0.74359,0.83689,0.44117,1.61746,0.94731,1.28846,0.000439,0.000439,0.000439

train.py

@@ -0,0 +1,21 @@
+from ultralytics import YOLO
+model = YOLO('yolo11m.pt')
+
+model.train(
+    data='/content/cigarette-3/data.yaml',
+    epochs=30,
+    imgsz=640,
+    batch=16,
+    patience=5,
+    optimizer="SGD",
+    lr0=0.001,
+    lrf=0.01,
+    momentum=0.937,
+    weight_decay=0.0005,
+    warmup_epochs=3,
+    hsv_h=0.015, hsv_s=0.7, hsv_v=0.4,
+    translate=0.1, scale=0.5,
+    fliplr=0.5, mosaic=1.0, mixup=0.1,
+    device=0,
+    cache=True
+)