Famico Product Detection — YOLOv8 Pipeline

~4 images/class → trained detector in ~2 hours (CPU) or ~15 min (GPU)

Quick start

pip install ultralytics albumentations opencv-python tqdm pyyaml

or using conda

conda env create -f enviroment.yml

Step-by-step

Step 1 — Set up folders

python 1_prepare_dataset.py

Edit CLASS_NAMES in the script first to list all 13 of your product classes.

Step 2 — Label your images

Put your raw product photos into dataset/images/train/.

Use Roboflow (recommended) or LabelImg to draw bounding boxes and export in YOLO format:

Roboflow — free, web-based, exports directly to YOLO format
LabelImg: pip install labelImg && labelImg or download it from here

Each image needs a matching .txt in dataset/labels/train/:

# famico_veloute_01.txt
0 0.512 0.483 0.320 0.541

Format: class_id cx cy width height (all normalised 0–1)

Step 3 — Augment

python 2_augment.py

Expands 4 images → ~200 augmented training images per original photo. Takes 2–5 minutes.

Augmentations applied:

Perspective warp, rotation, scale shift
Brightness / contrast / hue jitter
Blur, noise, JPEG compression
Random cutout (occlusion simulation)
Horizontal flip

Step 4 — Train

python 3_train.py

Hardware	Expected time
Laptop CPU	60–90 min
GPU (any)	5–15 min
Google Colab (free)	~10 min

Output: runs/detect/famico_v1/weights/best.pt

Training on Google Colab (recommended if no GPU)

# Paste into a Colab cell:
!pip install ultralytics albumentations

# Upload your dataset folder to Colab, then:
!python 3_train.py

Or use Roboflow's free training pipeline which runs YOLOv8 on their GPU.

Step 5 — Detect

# Single image
python 4_detect.py --source scene.jpg

# Folder of images
python 4_detect.py --source my_scenes/

# Webcam (live)
python 4_detect.py --source 0

# Custom confidence threshold
python 4_detect.py --source scene.jpg --conf 0.4

Results saved to detections/.

Tuning tips

Problem	Fix
Too many false positives	Raise `--conf` to 0.45–0.55
Missing detections	Lower `--conf` to 0.25
Boxes overlap too much	Lower `--iou` in detect.py
mAP < 0.5 after training	Add 5–10 more labeled images per class
Training loss doesn't converge	Lower `LR0` to 0.002 in train.py

Expected results

With 4 original images + augmentation and 13 classes:

mAP50 ≈ 0.65–0.80 (good for production)
Inference speed ≈ 15–30ms/image on CPU, <5ms on GPU

Adding even 2–3 more labeled images per class typically pushes mAP above 0.85.

2.8 KiB Raw Blame History Unescape Escape