atom-predict/msunet/Metrics_.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "1e532855-9e9d-4839-8a5b-80ef9fc1f496",
   "metadata": {},
   "outputs": [
    {
     "ename": "ImportError",
     "evalue": "cannot import name 'get_mask' from 'utils.labelme' (/home/andrewtal/Workspace/metrials/atom/code/msunet/utils/labelme.py)",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mImportError\u001b[0m                               Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[1], line 9\u001b[0m\n\u001b[1;32m      6\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtqdm\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m tqdm\n\u001b[1;32m      7\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mmultiprocessing\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m Pool\n\u001b[0;32m----> 9\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mutils\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mlabelme\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m get_mask\n\u001b[1;32m     10\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mutils\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01me2e_metrics\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m get_metrics\n",
      "\u001b[0;31mImportError\u001b[0m: cannot import name 'get_mask' from 'utils.labelme' (/home/andrewtal/Workspace/metrials/atom/code/msunet/utils/labelme.py)"
     ]
    }
   ],
   "source": [
    "import json\n",
    "import glob\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "from tqdm import tqdm\n",
    "from multiprocessing import Pool\n",
    "\n",
    "from utils.labelme import get_mask\n",
    "from utils.e2e_metrics import get_metrics"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "83c85338-5689-45f1-8286-51ff697aa04a",
   "metadata": {},
   "source": [
    "# metrics"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "79e3c40d-6ac2-41da-a3b1-a25c6bc6f1e4",
   "metadata": {},
   "outputs": [],
   "source": [
    "def get_score():\n",
    "    res = []\n",
    "\n",
    "    for id in range(nums):\n",
    "        res += [get_metrics(\n",
    "            label[id], \n",
    "            get_mask(pred[id], min_size=4)\n",
    "        )]\n",
    "    \n",
    "    return res"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "dfae81e3-1287-48d0-913f-c39542b689b7",
   "metadata": {},
   "outputs": [],
   "source": [
    "def get_score_v():\n",
    "    res = []\n",
    "\n",
    "    for id in range(nums):\n",
    "        res += [get_metrics(\n",
    "            np.array(label[id] > 1),\n",
    "            get_mask(pred[id], min_size=4)\n",
    "        )]\n",
    "    \n",
    "    return res"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "cc070f47-9910-436a-a1dc-49c48bbbc41e",
   "metadata": {},
   "outputs": [],
   "source": [
    "with open('./logs/0/version_0/result.json') as f:\n",
    "    data = json.load(f)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "31f61d06-34c5-4595-883b-b240304993f0",
   "metadata": {},
   "outputs": [],
   "source": [
    "img_path = np.array(data['img_path'])\n",
    "metric_idx = np.array([item.split('/')[-1].split('.')[0] not in ['4', '8'] for item in img_path])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "ebeb8904-4125-4709-a88b-7ef8c3d4a482",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "8"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "label = np.array(data['label']) # [metric_idx]\n",
    "pred = np.array(data['pred']) # [metric_idx]\n",
    "\n",
    "nums = label.shape[0]; nums"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "a94f789b-8ec9-4637-a523-1ea93e183eb5",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0.99447763, 0.995673  , 0.99507427])"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.mean(get_score(), axis=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "3ab02e37-ee18-496b-98ca-155432178551",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0.08341605, 0.97570966, 0.15249978])"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.mean(get_score_v(), axis=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "40ea70e0-0bdb-4c17-adc6-a2c492d1d842",
   "metadata": {},
   "outputs": [],
   "source": [
    "# array([0.99489517, 0.99558528, 0.99523956])\n",
    "# array([0.08338148, 0.97506031, 0.15243086])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "a91a73ae-96c3-49e0-acd7-fde7d8138998",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "5534b4ac-5726-49ee-a5f1-17a3be7eed30",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "a4338b46-d62a-4867-868d-96b9056935de",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "8b092391-cad2-4ce8-a9e3-556a0b95d64b",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "4f4f3a57-35fa-41a1-b3cc-e2cef8e94ce7",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "5189ddc5-e955-47bd-9b6c-7ecb4fa75520",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "cmae",
   "language": "python",
   "name": "cmae"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.16"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}