{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "42e4027f",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "/home/jovyan/shared/Chima/ml_project/repos/MYSMP\n"
     ]
    }
   ],
   "source": [
    "%cd \"../../MYSMP\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "ef6ea33e",
   "metadata": {},
   "outputs": [],
   "source": [
    "# %pip install -r requirements.txt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "30812aed",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "/home/jovyan/shared/Chima/ml_project/repos/MYSMP/semantic-segmentation\n"
     ]
    }
   ],
   "source": [
    "%cd \"../MYSMP/semantic-segmentation\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "aaa4a036",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "/home/jovyan/shared/Chima/ml_project/repos/MYSMP/semantic-segmentation\n"
     ]
    }
   ],
   "source": [
    "!pwd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "099239c4",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Loading pretrained model...\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/srv/conda/envs/notebook/lib/python3.8/site-packages/segmentation_models_pytorch/base/modules.py:116: UserWarning: Implicit dimension choice for softmax has been deprecated. Change the call to include dim=X as an argument.\n",
      "  return self.activation(x)\n"
     ]
    }
   ],
   "source": [
    "# Initialize the model\n",
    "from SemanticModel.model_core import SegmentationModel\n",
    "\n",
    "model = SegmentationModel(\n",
    "    classes=['bg', 'cacao', 'matarraton', 'abarco'],\n",
    "    architecture='unet',\n",
    "    encoder='timm-regnety_120',\n",
    "    weights='../data/model_outputs-unet[timm-regnety_120]-01-23-2025_075803/best_model.pth'\n",
    ")\n",
    "\n",
    "# Initialize prediction pipeline\n",
    "from SemanticModel.prediction import PredictionPipeline\n",
    "\n",
    "predictor = PredictionPipeline(model)\n",
    "output_dir='../predictions'\n",
    "image_path= '../data/Images/2019-Mission2-odm_1_42.jpg'\n",
    "\n",
    "# Make prediction\n",
    "prediction = predictor.predict_single_image(image_path=image_path,output_dir=output_dir)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "e0ae4c21",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "Predictions saved to: path/to/folderofImages/predictions\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'path/to/folderofImages/predictions'"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Directory of images\n",
    "image_path= 'path/to/folderofImages'\n",
    "predictor.predict_directory(image_path)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "fc4f2a48",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Loading raster...\n",
      "Processed 6/6 tiles\n",
      "Prediction saved to: ../predictions/prediction.tif\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "(array([[[0, 0, 0],\n",
       "         [0, 0, 0],\n",
       "         [0, 0, 0],\n",
       "         ...,\n",
       "         [0, 0, 0],\n",
       "         [0, 0, 0],\n",
       "         [0, 0, 0]],\n",
       " \n",
       "        [[0, 0, 0],\n",
       "         [0, 0, 0],\n",
       "         [0, 0, 0],\n",
       "         ...,\n",
       "         [0, 0, 0],\n",
       "         [0, 0, 0],\n",
       "         [0, 0, 0]],\n",
       " \n",
       "        [[0, 0, 0],\n",
       "         [0, 0, 0],\n",
       "         [0, 0, 0],\n",
       "         ...,\n",
       "         [0, 0, 0],\n",
       "         [0, 0, 0],\n",
       "         [0, 0, 0]],\n",
       " \n",
       "        ...,\n",
       " \n",
       "        [[0, 0, 0],\n",
       "         [0, 0, 0],\n",
       "         [0, 0, 0],\n",
       "         ...,\n",
       "         [0, 0, 0],\n",
       "         [0, 0, 0],\n",
       "         [0, 0, 0]],\n",
       " \n",
       "        [[0, 0, 0],\n",
       "         [0, 0, 0],\n",
       "         [0, 0, 0],\n",
       "         ...,\n",
       "         [0, 0, 0],\n",
       "         [0, 0, 0],\n",
       "         [0, 0, 0]],\n",
       " \n",
       "        [[0, 0, 0],\n",
       "         [0, 0, 0],\n",
       "         [0, 0, 0],\n",
       "         ...,\n",
       "         [0, 0, 0],\n",
       "         [0, 0, 0],\n",
       "         [0, 0, 0]]], dtype=uint8),\n",
       " {'driver': 'GTiff', 'dtype': 'uint8', 'nodata': None, 'width': 2365, 'height': 1797, 'count': 3, 'crs': CRS.from_epsg(32618), 'transform': Affine(0.03564594364277113, 0.0, 740295.5186183113,\n",
       "        0.0, -0.03564594364276106, 485117.0212715292), 'tiled': False, 'interleave': 'pixel'})"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Large raster\n",
    "output_path='../predictions/prediction.tif'\n",
    "raster_path = '../data/2021-Mission7_clipped_2.tif'\n",
    "predictor.predict_raster(raster_path, tile_size=1024,output_path=output_path,format='color')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "8e4ab5a5",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "AgLab - 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": "3.8.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}