{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import numpy as np\n",
"import pandas as pd\n",
"import matplotlib.pyplot as plt\n",
"from tqdm import tqdm\n",
"import cv2 as cv"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Classes"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"classes = [\"cloth\", \"KN95\",\"N95\", \"surgical\"]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Format helper functions"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"def visualize(img_info, path):\n",
" img_name = path + img_info[\"ImageID\"] + \".jpg\"\n",
" bbox = eval(img_info[\"bbox\"])\n",
" img = cv.imread(img_name)\n",
" img = cv.cvtColor(img, cv.COLOR_RGB2BGR)\n",
" [x1, y1, x2, y2] = [int(coord) for coord in bbox]\n",
" cv.rectangle(img, (x1, y1), (x2, y2), (255,0,0), 2)\n",
" plt.imshow(img)\n",
" plt.axis(\"off\")\n",
" plt.title(img_info[\"masktype\"])\n",
" plt.show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Prepare data"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"train_df = pd.read_csv(\"data/train.csv\")\n",
"val_df = pd.read_csv(\"data/val.csv\")"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" ImageID | \n",
" bbox | \n",
" masktype | \n",
"
\n",
" \n",
" \n",
" \n",
" | 0 | \n",
" k8o0f | \n",
" [73, 197, 293, 400] | \n",
" N95 | \n",
"
\n",
" \n",
" | 1 | \n",
" 7a0l9 | \n",
" [47, 364, 300, 512] | \n",
" surgical | \n",
"
\n",
" \n",
" | 2 | \n",
" wfp7p | \n",
" [203, 221, 380, 403] | \n",
" N95 | \n",
"
\n",
" \n",
" | 3 | \n",
" 7qaw6 | \n",
" [87, 210, 322, 385] | \n",
" surgical | \n",
"
\n",
" \n",
" | 4 | \n",
" i4kqj | \n",
" [227, 283, 479, 475] | \n",
" surgical | \n",
"
\n",
" \n",
"
\n",
"