{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from fastsam import FastSAM, FastSAMPrompt\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "model = FastSAM(\"FastSAM-x.pt\")\n",
    "IMAGE_PATH = \"./sample_images/3.jpg\"\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "DEVICE = \"cpu\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "image 1/1 /home/ravi.naik/learning/era/s19/sample_images/3.jpg: 704x1024 5 objects, 5524.6ms\n",
      "Speed: 77.9ms preprocess, 5524.6ms inference, 75.1ms postprocess per image at shape (1, 3, 1024, 1024)\n"
     ]
    }
   ],
   "source": [
    "everything_results = model(\n",
    "    IMAGE_PATH,\n",
    "    device=DEVICE,\n",
    "    retina_masks=True,\n",
    "    imgsz=1024,\n",
    "    conf=0.4,\n",
    "    iou=0.9,\n",
    ")\n",
    "prompt_process = FastSAMPrompt(IMAGE_PATH, everything_results, device=DEVICE)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|███████████████████████████████████████| 338M/338M [00:32<00:00, 10.9MiB/s]\n"
     ]
    }
   ],
   "source": [
    "# everything prompt\n",
    "ann = prompt_process.everything_prompt()\n",
    "\n",
    "# bbox default shape [0,0,0,0] -> [x1,y1,x2,y2]\n",
    "# ann = prompt_process.box_prompt(bbox=[[200, 200, 300, 300]])\n",
    "\n",
    "# text prompt\n",
    "ann = prompt_process.text_prompt(text=\"a photo of a dog\")\n",
    "\n",
    "# point prompt\n",
    "# points default [[0,0]] [[x1,y1],[x2,y2]]\n",
    "# point_label default [0] [1,0] 0:background, 1:foreground\n",
    "# ann = prompt_process.point_prompt(points=[[620, 360]], pointlabel=[1])\n",
    "\n",
    "prompt_process.plot(\n",
    "    annotations=ann,\n",
    "    output_path=\"./output/dog.jpg\",\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}