aitraining image-classification \
  --model google/vit-base-patch16-224 \
  --data-path ./images/ \
  --project-name image-classifier

images/
├── cat/
│   ├── cat1.jpg
│   └── cat2.jpg
├── dog/
│   ├── dog1.jpg
│   └── dog2.jpg

image,label
/path/to/cat1.jpg,cat
/path/to/dog1.jpg,dog

aitraining image-classification \
  --model microsoft/resnet-50 \
  --data-path ./product_images/ \
  --project-name product-classifier \
  --epochs 10 \
  --batch-size 32 \
  --lr 5e-5

aitraining image-regression \
  --model google/vit-base-patch16-224 \
  --data-path ./images.csv \
  --image-column image \
  --target-column score \
  --project-name quality-scorer

aitraining image-regression \
  --model microsoft/resnet-50 \
  --data-path ./faces.csv \
  --image-column photo \
  --target-column age \
  --project-name age-predictor \
  --epochs 20

aitraining object-detection \
  --model facebook/detr-resnet-50 \
  --data-path ./coco_format/ \
  --project-name detector

{
  "image": "image.jpg",
  "objects": {
    "bbox": [[x, y, width, height], ...],
    "categories": [0, 1, ...]
  }
}

aitraining object-detection \
  --model facebook/detr-resnet-50 \
  --data-path ./annotations/ \
  --project-name custom-detector \
  --epochs 50 \
  --batch-size 8

aitraining vlm \
  --model google/paligemma-3b-pt-224 \
  --data-path ./image_captions.jsonl \
  --project-name vlm-model

{
  "image": "image.jpg",
  "conversations": [
    {"role": "user", "content": "What's in this image?"},
    {"role": "assistant", "content": "A cat sitting on a couch."}
  ]
}

aitraining vlm \
  --model Qwen/Qwen2-VL-2B-Instruct \
  --data-path ./captions.jsonl \
  --project-name captioner \
  --epochs 3 \
  --batch-size 2 \
  --peft \
  --lora-r 16

aitraining vlm \
  --model Qwen/Qwen2-VL-2B-Instruct \
  --data-path ./data.jsonl \
  --project-name vlm \
  --peft \
  --lora-r 16 \
  --batch-size 1 \
  --gradient-accumulation 8