{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "import json\n", "import numpy as np\n", "import cv2\n", "from glob import glob\n", "from os.path import join as pjoin\n", "from tqdm import tqdm\n", "\n", "\n", "def resize_label(bboxes, d_height, gt_height, bias=0):\n", " bboxes_new = []\n", " scale = gt_height / d_height\n", " for bbox in bboxes:\n", " bbox = [int(b * scale + bias) for b in bbox]\n", " bboxes_new.append(bbox)\n", " return bboxes_new\n", "\n", "\n", "def draw_bounding_box(org, corners, color=(0, 255, 0), line=2, show=False):\n", " board = org.copy()\n", " for i in range(len(corners)):\n", " board = cv2.rectangle(board, (corners[i][0], corners[i][1]), (corners[i][2], corners[i][3]), color, line)\n", " if show:\n", " cv2.imshow('a', cv2.resize(board, (500, 1000)))\n", " cv2.waitKey(0)\n", " return board\n", "\n", "\n", "def load_detect_result_json(reslut_file_root, shrink=0):\n", " def is_bottom_or_top(corner):\n", " column_min, row_min, column_max, row_max = corner\n", " if row_max < 36 or row_min > 725:\n", " return True\n", " return False\n", "\n", " result_files = glob(pjoin(reslut_file_root, '*.json'))\n", " compos_reform = {}\n", " print('Loading %d detection results' % len(result_files))\n", " for reslut_file in tqdm(result_files):\n", " img_name = reslut_file.split('\\\\')[-1].split('.')[0]\n", " compos = json.load(open(reslut_file, 'r'))['compos']\n", " for compo in compos:\n", " if is_bottom_or_top((compo['column_min'], compo['row_min'], compo['column_max'], compo['row_max'])):\n", " continue\n", " if img_name not in compos_reform:\n", " compos_reform[img_name] = {'bboxes': [[compo['column_min'] + shrink, compo['row_min'] + shrink, compo['column_max'] - shrink, compo['row_max'] - shrink]],\n", " 'categories': [compo['category']]}\n", " else:\n", " compos_reform[img_name]['bboxes'].append([compo['column_min'] + shrink, compo['row_min'] + shrink, compo['column_max'] - shrink, compo['row_max'] - shrink])\n", " compos_reform[img_name]['categories'].append(compo['category'])\n", " return compos_reform\n", "\n", "\n", "def load_ground_truth_json(gt_file):\n", " def get_img_by_id(img_id):\n", " for image in images:\n", " if image['id'] == img_id:\n", " return image['file_name'].split('/')[-1][:-4], (image['height'], image['width'])\n", "\n", " def cvt_bbox(bbox):\n", " '''\n", " :param bbox: [x,y,width,height]\n", " :return: [col_min, row_min, col_max, row_max]\n", " '''\n", " bbox = [int(b) for b in bbox]\n", " return [bbox[0], bbox[1], bbox[0] + bbox[2], bbox[1] + bbox[3]]\n", "\n", " data = json.load(open(gt_file, 'r'))\n", " images = data['images']\n", " annots = data['annotations']\n", " compos = {}\n", " print('Loading %d ground truth' % len(annots))\n", " for annot in tqdm(annots):\n", " img_name, size = get_img_by_id(annot['image_id'])\n", " if img_name not in compos:\n", " compos[img_name] = {'bboxes': [cvt_bbox(annot['bbox'])], 'categories': [annot['category_id']], 'size': size}\n", " else:\n", " compos[img_name]['bboxes'].append(cvt_bbox(annot['bbox']))\n", " compos[img_name]['categories'].append(annot['category_id'])\n", " return compos\n", "\n", "\n", "def eval(detection, ground_truth, img_root, show=True, no_text=False, only_text=False):\n", " def compo_filter(compos, flag):\n", " if not no_text and not only_text:\n", " return compos\n", " compos_new = {'bboxes': [], 'categories': []}\n", " for k, category in enumerate(compos['categories']):\n", " if only_text:\n", " if flag == 'det' and category != 'TextView':\n", " continue\n", " if flag == 'gt' and int(category) != 14:\n", " continue\n", " elif no_text:\n", " if flag == 'det' and category == 'TextView':\n", " continue\n", " if flag == 'gt' and int(category) == 14:\n", " continue\n", "\n", " compos_new['bboxes'].append(compos['bboxes'][k])\n", " compos_new['categories'].append(category)\n", " return compos_new\n", "\n", " def match(org, d_bbox, gt_bboxes, matched):\n", " '''\n", " :param matched: mark if the ground truth component is matched\n", " :param d_bbox: [col_min, row_min, col_max, row_max]\n", " :param gt_bboxes: list of ground truth [[col_min, row_min, col_max, row_max]]\n", " :return: Boolean: if IOU large enough or detected box is contained by ground truth\n", " '''\n", " area_d = (d_bbox[2] - d_bbox[0]) * (d_bbox[3] - d_bbox[1])\n", " for i, gt_bbox in enumerate(gt_bboxes):\n", " if matched[i] == 0:\n", " continue\n", " area_gt = (gt_bbox[2] - gt_bbox[0]) * (gt_bbox[3] - gt_bbox[1])\n", " col_min = max(d_bbox[0], gt_bbox[0])\n", " row_min = max(d_bbox[1], gt_bbox[1])\n", " col_max = min(d_bbox[2], gt_bbox[2])\n", " row_max = min(d_bbox[3], gt_bbox[3])\n", " # if not intersected, area intersection should be 0\n", " w = max(0, col_max - col_min)\n", " h = max(0, row_max - row_min)\n", " area_inter = w * h\n", " if area_inter == 0:\n", " continue\n", " iod = area_inter / area_d\n", " iou = area_inter / (area_d + area_gt - area_inter)\n", " # if show:\n", " # cv2.putText(org, (str(round(iou, 2)) + ',' + str(round(iod, 2))), (d_bbox[0], d_bbox[1]),\n", " # cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 0, 255), 2)\n", "\n", " if iou > 0.9 or iod == 1:\n", " matched[i] = 0\n", " return True\n", " return False\n", "\n", " amount = len(detection)\n", " TP, FP, FN = 0, 0, 0\n", " pres, recalls, f1s = [], [], []\n", " for i, image_id in enumerate(detection):\n", " TP_this, FP_this, FN_this = 0, 0, 0\n", " img = cv2.imread(pjoin(img_root, image_id + '.jpg'))\n", " d_compos = detection[image_id]\n", " gt_compos = ground_truth[image_id]\n", "\n", " org_height = gt_compos['size'][0]\n", "\n", " d_compos = compo_filter(d_compos, 'det')\n", " gt_compos = compo_filter(gt_compos, 'gt')\n", "\n", " d_compos['bboxes'] = resize_label(d_compos['bboxes'], 800, org_height)\n", " matched = np.ones(len(gt_compos['bboxes']), dtype=int)\n", " for d_bbox in d_compos['bboxes']:\n", " if match(img, d_bbox, gt_compos['bboxes'], matched):\n", " TP += 1\n", " TP_this += 1\n", " else:\n", " FP += 1\n", " FP_this += 1\n", " FN += sum(matched)\n", " FN_this = sum(matched)\n", "\n", " try:\n", " pre_this = TP_this / (TP_this + FP_this)\n", " recall_this = TP_this / (TP_this + FN_this)\n", " f1_this = 2 * (pre_this * recall_this) / (pre_this + recall_this)\n", " except:\n", " print('empty')\n", " continue\n", "\n", " pres.append(pre_this)\n", " recalls.append(recall_this)\n", " f1s.append(f1_this)\n", " if show:\n", " print(image_id + '.jpg')\n", " print('[%d/%d] TP:%d, FP:%d, FN:%d, Precesion:%.3f, Recall:%.3f' % (\n", " i, amount, TP_this, FP_this, FN_this, pre_this, recall_this))\n", " cv2.imshow('org', cv2.resize(img, (500, 1000)))\n", " broad = draw_bounding_box(img, d_compos['bboxes'], color=(255, 0, 0), line=3)\n", " draw_bounding_box(broad, gt_compos['bboxes'], color=(0, 0, 255), show=True, line=2)\n", "\n", " if i % 200 == 0:\n", " precision = TP / (TP + FP)\n", " recall = TP / (TP + FN)\n", " f1 = 2 * (precision * recall) / (precision + recall)\n", " print(\n", " '[%d/%d] TP:%d, FP:%d, FN:%d, Precesion:%.3f, Recall:%.3f, F1:%.3f' % (i, amount, TP, FP, FN, precision, recall, f1))\n", "\n", " precision = TP / (TP + FP)\n", " recall = TP / (TP + FN)\n", " print('[%d/%d] TP:%d, FP:%d, FN:%d, Precesion:%.3f, Recall:%.3f, F1:%.3f' % (i, amount, TP, FP, FN, precision, recall, f1))\n", " # print(\"Average precision:%.4f; Average recall:%.3f\" % (sum(pres)/len(pres), sum(recalls)/len(recalls)))\n", "\n", " return pres, recalls, f1s" ] }, { "cell_type": "code", "execution_count": 71, "metadata": {}, "outputs": [], "source": [ "import matplotlib.pyplot as plt\n", "import numpy as np\n", "import math\n", "\n", "def draw_plot(data, title='Score for our approach'):\n", " for i in range(len(data)):\n", " data[i] = [d for d in data[i] if not math.isnan(d)]\n", "# plt.title(title)\n", " labels = ['Precision', 'Recall', 'F1']\n", " bplot = plt.boxplot(data, patch_artist=True, labels=labels) # 设置箱型图可填充\n", " colors = ['pink', 'lightblue', 'lightgreen']\n", " for patch, color in zip(bplot['boxes'], colors):\n", " patch.set_facecolor(color) \n", " plt.grid(axis='y')\n", " plt.xticks(fontsize=16)\n", " plt.yticks(fontsize=16)\n", " plt.savefig(title + '.png')\n", " plt.show()" ] }, { "cell_type": "code", "execution_count": 9, "metadata": { "scrolled": true }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ " 9%|███████▏ | 442/4708 [00:00<00:01, 4173.66it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Loading 4708 detection results\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "100%|████████████████████████████████████████████████████████████████████████████| 4708/4708 [00:01<00:00, 4404.67it/s]\n" ] } ], "source": [ "detect = load_detect_result_json('E:\\\\Mulong\\\\Result\\\\rico\\\\rico_uied\\\\rico_new_uied_cls\\\\merge')" ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ " 8%|█████▉ | 6915/86646 [00:00<00:01, 68670.52it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Loading 86646 ground truth\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "100%|██████████████████████████████████████████████████████████████████████████| 86646/86646 [00:11<00:00, 7576.11it/s]\n" ] } ], "source": [ "gt = load_ground_truth_json('E:\\\\Mulong\\\\Datasets\\\\rico\\\\instances_test.json')" ] }, { "cell_type": "code", "execution_count": 23, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[0/4707] TP:16, FP:0, FN:0, Precesion:1.000, Recall:1.000, F1:1.000\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "D:\\Anaconda\\lib\\site-packages\\ipykernel_launcher.py:165: RuntimeWarning: invalid value encountered in double_scalars\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[200/4707] TP:2222, FP:2920, FN:1705, Precesion:0.432, Recall:0.566, F1:0.490\n", "[400/4707] TP:4616, FP:5737, FN:3346, Precesion:0.446, Recall:0.580, F1:0.504\n", "[600/4707] TP:6963, FP:8682, FN:4812, Precesion:0.445, Recall:0.591, F1:0.508\n", "[800/4707] TP:9367, FP:11432, FN:6305, Precesion:0.450, Recall:0.598, F1:0.514\n", "[1000/4707] TP:11222, FP:14346, FN:7511, Precesion:0.439, Recall:0.599, F1:0.507\n", "[1200/4707] TP:13680, FP:17278, FN:8901, Precesion:0.442, Recall:0.606, F1:0.511\n", "[1400/4707] TP:16274, FP:20664, FN:10379, Precesion:0.441, Recall:0.611, F1:0.512\n", "[1600/4707] TP:18431, FP:23002, FN:11556, Precesion:0.445, Recall:0.615, F1:0.516\n", "[1800/4707] TP:20718, FP:25600, FN:13049, Precesion:0.447, Recall:0.614, F1:0.517\n", "[2000/4707] TP:23009, FP:28626, FN:14588, Precesion:0.446, Recall:0.612, F1:0.516\n", "[2200/4707] TP:25424, FP:31555, FN:16191, Precesion:0.446, Recall:0.611, F1:0.516\n", "[2400/4707] TP:27559, FP:34176, FN:17388, Precesion:0.446, Recall:0.613, F1:0.517\n", "[2600/4707] TP:29820, FP:37065, FN:18617, Precesion:0.446, Recall:0.616, F1:0.517\n", "[2800/4707] TP:32108, FP:39846, FN:20018, Precesion:0.446, Recall:0.616, F1:0.518\n", "[3000/4707] TP:34188, FP:43112, FN:21399, Precesion:0.442, Recall:0.615, F1:0.515\n", "[3200/4707] TP:36558, FP:46011, FN:23002, Precesion:0.443, Recall:0.614, F1:0.514\n", "[3400/4707] TP:38783, FP:48918, FN:24365, Precesion:0.442, Recall:0.614, F1:0.514\n", "[3600/4707] TP:40958, FP:51829, FN:25605, Precesion:0.441, Recall:0.615, F1:0.514\n", "[3800/4707] TP:43270, FP:54963, FN:26841, Precesion:0.440, Recall:0.617, F1:0.514\n", "[4000/4707] TP:45512, FP:57838, FN:28141, Precesion:0.440, Recall:0.618, F1:0.514\n", "[4200/4707] TP:47544, FP:60789, FN:29420, Precesion:0.439, Recall:0.618, F1:0.513\n", "[4400/4707] TP:49907, FP:64407, FN:30897, Precesion:0.437, Recall:0.618, F1:0.512\n", "[4600/4707] TP:52181, FP:67592, FN:32399, Precesion:0.436, Recall:0.617, F1:0.511\n", "[4706/4707] TP:53393, FP:69230, FN:33248, Precesion:0.435, Recall:0.616, F1:0.511\n" ] } ], "source": [ "no_text = False\n", "only_text = False\n", "pres_all, recalls_all, f1_all = eval(detect, gt, 'E:\\\\Mulong\\\\Datasets\\\\rico\\\\combined', show=False, no_text=no_text, only_text=only_text)" ] }, { "cell_type": "code", "execution_count": 21, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[0/4707] TP:1, FP:0, FN:0, Precesion:1.000, Recall:1.000, F1:1.000\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "D:\\Anaconda\\lib\\site-packages\\ipykernel_launcher.py:165: RuntimeWarning: invalid value encountered in double_scalars\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[200/4707] TP:973, FP:2022, FN:891, Precesion:0.325, Recall:0.522, F1:0.400\n", "empty\n", "[400/4707] TP:1921, FP:3905, FN:1788, Precesion:0.330, Recall:0.518, F1:0.403\n", "[600/4707] TP:2847, FP:6079, FN:2717, Precesion:0.319, Recall:0.512, F1:0.393\n", "empty\n", "empty\n", "empty\n", "[800/4707] TP:3774, FP:7895, FN:3574, Precesion:0.323, Recall:0.514, F1:0.397\n", "empty\n", "[1000/4707] TP:4478, FP:9951, FN:4229, Precesion:0.310, Recall:0.514, F1:0.387\n", "empty\n", "empty\n", "[1200/4707] TP:5451, FP:12055, FN:4960, Precesion:0.311, Recall:0.524, F1:0.391\n", "empty\n", "empty\n", "empty\n", "[1400/4707] TP:6493, FP:14405, FN:5804, Precesion:0.311, Recall:0.528, F1:0.391\n", "empty\n", "empty\n", "empty\n", "empty\n", "[1600/4707] TP:7372, FP:15980, FN:6375, Precesion:0.316, Recall:0.536, F1:0.397\n", "empty\n", "empty\n", "empty\n", "[1800/4707] TP:8273, FP:17814, FN:7156, Precesion:0.317, Recall:0.536, F1:0.399\n", "empty\n", "empty\n", "[2000/4707] TP:9273, FP:19993, FN:8051, Precesion:0.317, Recall:0.535, F1:0.398\n", "empty\n", "[2200/4707] TP:10293, FP:22055, FN:8869, Precesion:0.318, Recall:0.537, F1:0.400\n", "[2400/4707] TP:11207, FP:23944, FN:9524, Precesion:0.319, Recall:0.541, F1:0.401\n", "empty\n", "empty\n", "[2600/4707] TP:12103, FP:25932, FN:10276, Precesion:0.318, Recall:0.541, F1:0.401\n", "[2800/4707] TP:12994, FP:27792, FN:11122, Precesion:0.319, Recall:0.539, F1:0.400\n", "empty\n", "empty\n", "[3000/4707] TP:13839, FP:30256, FN:11943, Precesion:0.314, Recall:0.537, F1:0.396\n", "[3200/4707] TP:14758, FP:32276, FN:12851, Precesion:0.314, Recall:0.535, F1:0.395\n", "empty\n", "[3400/4707] TP:15718, FP:34337, FN:13627, Precesion:0.314, Recall:0.536, F1:0.396\n", "[3600/4707] TP:16695, FP:36424, FN:14263, Precesion:0.314, Recall:0.539, F1:0.397\n", "[3800/4707] TP:17641, FP:38693, FN:14932, Precesion:0.313, Recall:0.542, F1:0.397\n", "empty\n", "empty\n", "[4000/4707] TP:18651, FP:40641, FN:15653, Precesion:0.315, Recall:0.544, F1:0.399\n", "empty\n", "[4200/4707] TP:19554, FP:42631, FN:16305, Precesion:0.314, Recall:0.545, F1:0.399\n", "empty\n", "empty\n", "[4400/4707] TP:20584, FP:45335, FN:17197, Precesion:0.312, Recall:0.545, F1:0.397\n", "[4600/4707] TP:21416, FP:47595, FN:17950, Precesion:0.310, Recall:0.544, F1:0.395\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "[4706/4707] TP:21870, FP:48657, FN:18391, Precesion:0.310, Recall:0.543, F1:0.395\n" ] } ], "source": [ "no_text = True\n", "only_text = False\n", "pres_non_text, recalls_non_text, f1_non_text = eval(detect, gt, 'E:\\\\Mulong\\\\Datasets\\\\rico\\\\combined', show=False, no_text=no_text, only_text=only_text)" ] }, { "cell_type": "code", "execution_count": 14, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[0/4707] TP:15, FP:0, FN:0, Precesion:1.000, Recall:1.000, F1:1.000\n", "empty\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "D:\\Anaconda\\lib\\site-packages\\ipykernel_launcher.py:165: RuntimeWarning: invalid value encountered in double_scalars\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "[200/4707] TP:1041, FP:1106, FN:1022, Precesion:0.485, Recall:0.505, F1:0.495\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "[400/4707] TP:2185, FP:2342, FN:2068, Precesion:0.483, Recall:0.514, F1:0.498\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "[600/4707] TP:3272, FP:3447, FN:2939, Precesion:0.487, Recall:0.527, F1:0.506\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "[800/4707] TP:4505, FP:4625, FN:3819, Precesion:0.493, Recall:0.541, F1:0.516\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "[1000/4707] TP:5426, FP:5713, FN:4600, Precesion:0.487, Recall:0.541, F1:0.513\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "[1200/4707] TP:6649, FP:6803, FN:5521, Precesion:0.494, Recall:0.546, F1:0.519\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "[1400/4707] TP:7890, FP:8150, FN:6466, Precesion:0.492, Recall:0.550, F1:0.519\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "[1600/4707] TP:8964, FP:9117, FN:7276, Precesion:0.496, Recall:0.552, F1:0.522\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "[1800/4707] TP:10052, FP:10179, FN:8286, Precesion:0.497, Recall:0.548, F1:0.521\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "[2000/4707] TP:11126, FP:11243, FN:9147, Precesion:0.497, Recall:0.549, F1:0.522\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "[2200/4707] TP:12213, FP:12418, FN:10240, Precesion:0.496, Recall:0.544, F1:0.519\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "[2400/4707] TP:13243, FP:13341, FN:10973, Precesion:0.498, Recall:0.547, F1:0.521\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "[2600/4707] TP:14377, FP:14473, FN:11681, Precesion:0.498, Recall:0.552, F1:0.524\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "[2800/4707] TP:15494, FP:15674, FN:12516, Precesion:0.497, Recall:0.553, F1:0.524\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "[3000/4707] TP:16471, FP:16734, FN:13334, Precesion:0.496, Recall:0.553, F1:0.523\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "[3200/4707] TP:17644, FP:17891, FN:14307, Precesion:0.497, Recall:0.552, F1:0.523\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "[3400/4707] TP:18711, FP:18935, FN:15092, Precesion:0.497, Recall:0.554, F1:0.524\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "[3600/4707] TP:19710, FP:19958, FN:15895, Precesion:0.497, Recall:0.554, F1:0.524\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "[3800/4707] TP:20845, FP:21054, FN:16693, Precesion:0.498, Recall:0.555, F1:0.525\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "[4000/4707] TP:21881, FP:22177, FN:17468, Precesion:0.497, Recall:0.556, F1:0.525\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "[4200/4707] TP:22842, FP:23306, FN:18263, Precesion:0.495, Recall:0.556, F1:0.524\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "[4400/4707] TP:23930, FP:24465, FN:19093, Precesion:0.494, Recall:0.556, F1:0.524\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "[4600/4707] TP:25015, FP:25747, FN:20199, Precesion:0.493, Recall:0.553, F1:0.521\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "empty\n", "[4706/4707] TP:25638, FP:26458, FN:20742, Precesion:0.492, Recall:0.553, F1:0.521\n" ] } ], "source": [ "no_text = False\n", "only_text = True\n", "pres_text, recalls_text, f1_text = eval(detect, gt, 'E:\\\\Mulong\\\\Datasets\\\\rico\\\\combined', show=False, no_text=no_text, only_text=only_text)" ] }, { "cell_type": "code", "execution_count": 15, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "D:\\Anaconda\\lib\\site-packages\\matplotlib\\figure.py:448: UserWarning: Matplotlib is currently using module://ipykernel.pylab.backend_inline, which is a non-GUI backend, so cannot show the figure.\n", " % get_backend())\n" ] }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "draw_plot([pres_all, recalls_all])" ] }, { "cell_type": "code", "execution_count": 16, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "D:\\Anaconda\\lib\\site-packages\\matplotlib\\figure.py:448: UserWarning: Matplotlib is currently using module://ipykernel.pylab.backend_inline, which is a non-GUI backend, so cannot show the figure.\n", " % get_backend())\n" ] }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "draw_plot([pres_non_text, recalls_non_text])" ] }, { "cell_type": "code", "execution_count": 32, "metadata": {}, "outputs": [], "source": [ "import matplotlib.pyplot as plt\n", "import seaborn as sns\n", "import pandas as pd\n", "\n", "pres1 = pd.DataFrame({'score_type':'Precision', 'score': pres_non_text, 'class':'Non_text'})\n", "pres2 = pd.DataFrame({'score_type':'Precision', 'score': pres_all, 'class':'All_element'})\n", "\n", "recalls1 = pd.DataFrame({'score_type':'Recall', 'score':recalls_non_text, 'class':'Non_text'})\n", "recalls2 = pd.DataFrame({'score_type':'Recall', 'score':recalls_all, 'class':'All_element'})\n", "\n", "f1s1 = pd.DataFrame({'score_type':'F1', 'score':f1_non_text, 'class':'Non_text'})\n", "f1s2 = pd.DataFrame({'score_type':'F1', 'score':f1_all, 'class':'All_element'})\n", "\n", "data=pd.concat([pres1, pres2, recalls1, recalls2, f1s1, f1s2])" ] }, { "cell_type": "code", "execution_count": 36, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 36, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "sns.boxenplot(x='score_type', y='score', hue='class', data=data, width=0.5, linewidth=1.0, palette=\"Set3\")" ] }, { "cell_type": "code", "execution_count": 74, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "draw_plot([pres_all, recalls_all, f1_all], title='Scores for All Elements')" ] }, { "cell_type": "code", "execution_count": 75, "metadata": {}, "outputs": [ { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYEAAAEBCAYAAACe6Rn8AAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDMuMC4wLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvqOYd8AAAF2hJREFUeJzt3X2QXFWdxvHvQ3gzKDoRGBadZIhhgaDCuoOmFtedRAVcNIHKCpaKIEpgESQobkGh4S2LUiBBodCEZQWBclkBTVYQAySDgkQJCJggQthMEhYUJIEQXgKB3/5xb1NtpzN9e6Z7embO86nq6vTpe/r+uk+mn77n3u6riMDMzNK0VasLMDOz1nEImJklzCFgZpYwh4CZWcIcAmZmCXMImJklzCFgZpYwh4CZWcIcAmZmCdu61QXUstNOO0VnZ2eryzAzG1buvffev0TEzrWWG/Ih0NnZydKlS1tdhpnZsCJpVZHlPB1kZpYwh4CZWcIcAmZmCSsUApLeKekSSXdLelFSSOos2HcrSadL6pX0sqQHJE0fSNFmZtYYRbcEJgCHA+uAX9W5jnOBs4BLgY8BS4AfS/rnOh/HzMwarOjRQb+MiHYASV8EDizSSdIuwKnAtyLiwrx5saQJwLeAm+us18zMGqjQlkBEvN7Pxz8I2Ba4pqL9GuA9knbv5+OamVkDNHvH8D7ARmBFRfvy/Hpik9dvZmZ9aPaXxcYAz8bmJzJeW3b/ZiTNAGYAtLe309PT07QCm2ny5MkNeZzFixc35HGsPo0YP49da/hvr7hmh4CAameyV1+dImIeMA+gq6sruru7G1/ZINg8+zYnqdByNvhqjYvHbujy315xzZ4OWgu0Sap8028ru9/MzFqk2SGwHNgOeFdFe2lfwENNXr+ZmfWh2SFwC/AK8JmK9s8CyyJiZZPXb2ZmfSi8T0DSv+T//Pv8+mOSngaejog78mU2AVdFxBcAIuIpSXOA0yU9D9wHHAFMAaY16DmYmVk/1bNj+McVty/Lr+8AuvN/j8ov5c4ANgAnA7sCfwQOj4j/qatSMzNruMIhEBF9HtGzpWUi4jVgdn4xM7MhxL8iamaWMIeAmVnCHAJmZglzCJiZJcwhYGaWMIeAmVnCHAJmZglzCJiZJcwhYGaWMIeAmVnCHAJmZglzCJiZJcwhYGaWMIeAmVnCHAJmZglzCJiZJcwhYGaWMIeAJWnsuHFIGtAFGPBjjB03rsWvhKWunnMMm40Ya1av5oaHn2h1GUzfa7dWl2CJ85aAmVnCHAJmZglzCJiZJcwhYGaWMIeAmVnCHAJmZglzCJiZJaxQCEjqkHS9pOckrZd0o6SxBfuOlXSVpNWSXpT0iKTZknYYWOlmZjZQNb8sJmk0sAjYCBwFBDAbWCzpvRHxQh99dwBuA7YBvgGsBvYHzgb2AI4Y6BMwM7P+K/KN4WOB8cCeEbECQNKDwKPAccBFffQ9gOzN/qCIWJi3LZY0BjhV0uiIeLHf1ZuZ2YAUmQ6aCiwpBQBARKwE7gKm1ei7bX69vqL92XzdKlinmZk1QZEQ2AdYVqV9OTCxRt/byLYYzpc0UdKbJU0BTga+39dUkpmZNV+REBgDrKvSvhZo66tjRLwMfDBfz3LgeeB24GfAiXVVamZmDVf0V0SjSlvNqRxJ2wPXAbsAR5LtGH4/MAvYBPzrFvrNAGYAtLe309PTU7DM4WmkPz/rm8e/dfzagyKqvb+XLSD9GfhpRBxX0X4Z8MmI2LmPvl8CLgUmRMRjZe3HAvOA/SLigb7W39XVFUuXLq35RIYrSdQaA2s8SUPmp6Q9/q0x0v/2JN0bEV21lisyHbScbL9ApYnAQzX6vgdYVx4Aud/m13sXWL+ZmTVJkRBYAEySNL7UIKmT7PDPBTX6/glokzShov0D+fX/FSvTzMyaoUgIXA70AvMlTZM0FZgPrAHmlhaSNE7SJkmzyvpeSbYz+GZJR0maLOlrwIXAvWSHmZqZWYvUDIH8MM4pwCPA1cC1wEpgSkRsKFtUwKjyx4yIXmAScD/Zt4xvJvvy2TzgoxHxekOehZmZ9Uuho4MiYjUwvcYyvVQ5YigiHgIO709xZmbWXP4VUTOzhDkEzMwS5hAwM0uYQ8DMLGEOATOzhDkEzMwS5hAwM0uYQ8DMLGEOATOzhDkEzMwS5hAwM0uYQ8DMLGEOATOzhDkEzMwS5hAwM0uYQ8DMLGEOATOzhDkEzMwS5hAwM0uYQ2AAOseOQ9KALsCA+neOHdfiV8Fs8HV0drT8b6+js6PFr0JjFDrRvFW3as1qoueeltag7v1bun6zVnh81eNcvPbiltYwc8zMlq6/UbwlYGaWMIeAmVnCHAJmZglzCJiZJcwhYGaWMIeAmVnCCh0iKqkDmAN8FBBwGzAzIlYX7L83cA4wGdgBWA1cFhHf6U/RZgMVZ+4IP9qr1WVkdZi1UM0QkDQaWARsBI4CApgNLJb03oh4oUb/rrx/D/BF4DlgD+DNA6rcbAB09npuePiJVpfB9L12I85qdRWWsiJbAscC44E9I2IFgKQHgUeB44CLttRR0lbAVcDtEXFY2V2L+12xmZk1TJF9AlOBJaUAAIiIlcBdwLQafbuBifQRFGZm1jpFQmAfYFmV9uVkb/B9+WB+vb2kJZJelfSUpO9KelM9hZqZWeMVmQ4aA6yr0r4WaKvRd7f8+jrgUuA0oItsJ3EHcFi1TpJmADMA2tvb6enpKVBmuvz6DG8ev+FrJIxd0R+QiyptKtCvtKVxTUTMyv/dI2kU8C1JEyPioc1WFjEPmAfQ1dUV3d3dBctMk1+f4c3jN3yNhLErMh20jmxroFIb1bcQyj2TX99a0b4wv96vwPrNzKxJioTAcrL9ApUmApt9iq/SFzbfkihtRbxeYP1mZtYkRUJgATBJ0vhSg6RO4ID8vr78nOz7BQdXtB+UXy8tVKWZmTVFkRC4HOgF5kuaJmkqMB9YA8wtLSRpnKRNkkpz/0TEM8A3geMlnSfpI5JOA2YBV5UfdmpmZoOv5o7hiHhB0hSyn424mmwq53ayn43YULaogFFsHiznAM8DJwCnAk8CFwDnDrh6MzMbkEJHB+W/ETS9xjK9VDliKCKC7Mti/sKYmdkQ418RNTNLmEPAzCxhDgEzs4Q5BMzMEuYQMDNLmEPAzCxhDgEzs4Q5BMzMEuYQMDNLmEPAzCxhDgEzs4Q5BMzMEuYQMDNLmEPAzCxhDgEzs4Q5BMzMEuYQMDNLmEPAzCxhhU4vaWY2lMSZO8J3ZrW0hpPP3LGl628Uh4CZDTs6ez0Xr724pTXMHDOTOKulJTSEp4PMzBLmEDAzS5hDwMwsYQ4BM7OEOQTMzBLmEDAzS1ihEJDUIel6Sc9JWi/pRklj612ZpNMlhaQ76y/VzMwarWYISBoNLAL2Ao4CjgT2ABZL2qHoiiSNB84AnupfqWZm1mhFvix2LDAe2DMiVgBIehB4FDgOuKjgur4HXAvsWXC9ZmbWZEWmg6YCS0oBABARK4G7gGlFViLp08D7gNP7U6SZmTVHkRDYB1hWpX05MLFWZ0ltwBzg3yJibX3lmZlZMxUJgTHAuirta4G2Av0vAB4BrixelpmZDYaic/NRpU21Okn6R+BzwPsiotpjbKnfDGAGQHt7Oz09PUW7Dqo4c0dY/OGW1zBUXx8rxuM3fI2EsSsSAuvItgYqtVF9C6HcXOAK4HFJbytb56j89ksRsbGyU0TMA+YBdHV1RXd3d4EyB58mryd67mltDd37E2d1t7QGG5ih+v/bahsJY1ckBJaT7ReoNBF4qEbfvfPL8VXuWwecArT292DNzBJWJAQWABdKGh8R/wsgqRM4ADitRt/JVdouBkYBJwErqtxvZmaDpEgIXA6cCMyX9HWy/QPnAmvIpnsAkDQOeAw4JyLOAYiInsoHk/QssHW1+8zMbHDVDIGIeEHSFLLDPK8m2yF8OzAzIjaULSqyT/j+PSIb8jrGjmX6Xru1ugw6xtb96ytmDVXo6KCIWA1Mr7FMLwWOGIqI7iLrNGum1atWDfgxJFHHQW9mQ5I/tZuZJcwhYGaWMIeAmVnCHAJmZglzCJiZJcwhYGaWMIeAmVnCHAJmZglzCJiZJcwhYGaWMIeAmVnCHAJmZglzCJiZJcwhYGaWMIeAmVnCHAJmZglzCJiZJazQmcXMzIaSd457JzPHzGx5DSOBQ8DMhp01vWsG/Bg+PWjG00FmZglzCJiZJcwhYGaWMIeAmVnCHAJmZglzCJiZJcwhYGaWMIeAmVnCCoWApA5J10t6TtJ6STdKGlugX5ekeZIelvSipNWSrpW0+8BLNzOzgaoZApJGA4uAvYCjgCOBPYDFknao0f1TwD7Ad4GPAacB7wOWSuoYQN1mZtYARX424lhgPLBnRKwAkPQg8ChwHHBRH33Pj4inyxsk3QWszB93Vn+KNjOzxigyHTQVWFIKAICIWAncBUzrq2NlAORtq4CngXfUV6qZmTVakRDYB1hWpX05MLHeFUraG9gF+EO9fc3MrLGKTAeNAdZVaV8LtNWzMklbA98n2xK4oo/lZgAzANrb2+np6alnNcnx69M6fu2HN49f8Z+SrvZ7q+rH+i4F/gE4JCKqBUu2soh5wDyArq6u6O7u7seq0uHXp3X82g9vHr9iIbCObGugUhvVtxCqkvRNsk/3R0XEwqL9zMyseYqEwHKy/QKVJgIPFVmJpDPIDg/9ckRcXbw8MzNrpiI7hhcAkySNLzVI6gQOyO/rk6QvA7OBMyLikv6VaWZmzVAkBC4HeoH5kqZJmgrMB9YAc0sLSRonaZOkWWVtnwIuBm4BFkmaVHap+8giMzNrrJrTQRHxgqQpwBzgarIdwrcDMyNiQ9miAkbx18FycN5+cH4pdwfQ3e/Kh4BxHWNR9/4tr8HMrL801E+03NXVFUuXLm11GU3jk10PXx674W2kj5+keyOiq9Zy/hVRM7OEOQTMzBLmEDAzS5hDwMwsYQ4BM7OEOQTMzBLmEDAzS5hDwMwsYQ4BM7OEOQTMzBLmEDAzS5hDwMwsYQ4BM7OEOQTMzBLmEDAzS5hDwMwsYQ4BM7OEOQTMzBLmEDAzS5hDwMwsYQ4BM7OEOQTMzBLmEDAzS5hDwMwsYQ4BM7OEOQTMzBJWKAQkdUi6XtJzktZLulHS2IJ9t5d0gaQnJb0k6W5JHxpY2WZm1gg1Q0DSaGARsBdwFHAksAewWNIOBdZxBXAsMAv4OPAk8AtJ+/W3aDMza4ytCyxzLDAe2DMiVgBIehB4FDgOuGhLHSXtC3waOCYifpC33QEsB84Bpg6oejMzG5Ai00FTgSWlAACIiJXAXcC0An1fBa4r67sJ+C/gIEnb1V2xmZk1TJEQ2AdYVqV9OTCxQN+VEfFilb7bAhMKrN/MrC6Sal6KLJeCItNBY4B1VdrXAm0D6Fu638ysoSKi1SUMG0VCAKDaK1okJtWfvpJmADMA2tvb6enpKbCqoWfy5MmFlqv1iWPx4sWNKMfqVGT8PHY23BUJgXVU/8TeRvVP+eXWAtUOJW0ru38zETEPmAfQ1dUV3d3dBcocevxpZHjz+FkKiuwTWE42t19pIvBQgb6754eZVvZ9BVixeRczMxssRUJgATBJ0vhSg6RO4ID8vlp9twE+WdZ3a+AIYGFEbKyzXjMza6AiIXA50AvMlzRN0lRgPrAGmFtaSNI4SZskzSq1RcT9ZIeHXizpi5I+THZ46O7AmY17GmZm1h81QyAiXgCmAI8AVwPXAiuBKRGxoWxRAaOqPObngR8As4GbgA7g4Ii4b8DVm5nZgBQ6OigiVgPTayzTS5WjfiLiJeAr+cXMzIYQ/4qomVnCHAJmZglzCJiZJUxD/Qsxkp4GVrW6jibaCfhLq4uwfvHYDW8jffzGRcTOtRYa8iEw0klaGhFdra7D6uexG948fhlPB5mZJcwhYGaWMIdA681rdQHWbx674c3jh/cJmJklzVsCZmYJSzIEJB0tKcouz0t6QNKJ+a+cDlYdZ0mqa1NMUo+kniaVNOJUGetXJD0m6TxJ27e4tl5JV5bdLtXa2bKiRpAqY19++Ui+zHmSFkp6Jm8/usVlD7pBe8Mboj4JPA7smP/7EmAXYFZfnRroP4Bb6uxzQjMKSUBprN8CHAacnv/7pFYWZYOiNPblSudCOQm4H/gZ8LnBLGqoSD0E7o+I0oltFkqaAMykSggoO4/gNhHxSqNWHhGPs/l/zlp9ap3Ix6orH+tbJe0BfEHSyRHxeisLs6YrH/tKb42I1/O//SRDIMnpoD7cA7xF0i75pvo1ko6R9DDZmdAOAZA0WtL5klbm0wsrJZ0h6a9eT0k7S7pM0hpJG/PrqyVtl9+/2XSQpJMl/UHSS5LWSVoq6bCy+zebDpK0p6SfSHo277dE0sEVy5yVb+7uIekmSRskrZI0q7LuRNwHvInsW6MASNpd0rWSns7H6/7y175suX3z1/uZ/PX+o6TTy+4/UNLNkp6U9KKkZZK+KmnU4Dw1K8ofALwlUGl34DWgdJ6EycB+wNnAU0Bvvs/gF2SnyDwX+D0wCfgG2bmYvwogqQ34dd42G3iQbKppGrAtsNlZ1SR9Bvg2cA7wK7I3qfdS/RzPpT67AXcCzwMnAs8BXwJukvTxiPh5RZefkJ3fYQ7wify5rcnbUtJJ9lo9AyCpA/gN2TifAjxNdga8GyQdGhEL8uXeD/SQnRr1FLItuT3IxqlkPHA72fTiy0AXcBawM3BaU5+VVTOqYl9fRMRrLatmqImI5C7A0UAAe5IFYRtwHFkA/DRfphd4Edi1ou+Red8PVbSfQba1sEt++5z88f6ujzrOyobgjduXAvfVqL0H6Cm7fSGwCZhQ1jYK+GP5Y5XWBXy+4vF+T3aqz5aPyyCO9TH5a3Zi2XJXkL3xv72i/61k0wml278kC83RBdevfL1nAOuArcru6wWurFJrZ6tft5FwKXs9Ky93Vll2Qn7f0a2ue7AvKU4DlHsYeBVYC1xGdta0Y8ruXxIRf6roczDZD9r9WtLWpQuwkOx8ypPy5Q4E7omI39VRzz3AfpIukfQRSaML9PlQXucbc56Rfcr5Uf5YO1Ysf1PF7WXA2DpqHK7Kx/oKYG5EXFp2/8HAzcBzFeP6C2BfSTvm43EAcG1EvLilFUn6G0lzJa0i+2DwKtnW4NvItgZtcB0G7F92+UJryxlaUp8OOoxsc/55YFVEvFxx/5NV+uwCjCP7w67m7WXXD9RZzw+B7cn+k54AvCrpZuArkZ25rZoxQLWg+RPZp9A2YH1Z+9qK5Tbm6xzpSmO9M9lZ7k6Q9JuI+GF+/y5kOwa3tHPw7WRv6FvRx878fP/KAmA3sq2vh4GXgEPJtgZSeK2HmmWx5R3DyUs9BGr956h2DP8zZOdYPnwLfXrz678A76inmMi2S+cCc/N9CgeS7SO4DvjAFrqtBXat0r4rWf2Vb/qpemOsJS0i20dzgaQbIjuP9jNk+2HO30L/J8im2V6n73F9F9k+gCMj4ppSo6RPDPwpmDVe6tNB/XEL0AFsiIilVS6l3ydfCLxf0r79WUlErIuI64D/Bt7dx6J3AJPKv2CUH4VyBPC7iHi+P+sfySJiI/A1sk//pe9d3EK2c3f5FsZ1Yz4FdCfwWUlv2sLDl6bw3thSlLQN8JmmPBmzAUp9S6A/rgU+D9wu6dtkUz7bkn0CnAocmr9ZzAE+DdwmaTbZDtidyI4OOr7am7OkeWRTU3eTHaXyt2Q7ohf2Uc8csh1gt0o6k2zq54S87yEDfbIjVUQskHQPcKqkS8m+G/Jb4Jf57V6yqbR3A+MjorSv6FSy4L07H//HyY4G2i8iTgL+QLbP6N8lvUYWBqcM3jOzekj6J7IpwtLWdJekDQARcX3LChtEDoE6RcSrkg4iO9RvBtlhpS8Aj5HtdH0lX+5ZSQeQ7RA8jWxO+c/AotIyVdxFFjBHAm8lm4K4Bjizj3qekPRBsmmM7wHbkX0D8pCIqPfbyKn5OtmO3+MjYo6k0qGc55G9MTxDtuP8qlKHiLgnH9dzyA4B3Y7sTf8H+f2vSDqU7EivH5JNx/0nsBq4fHCeltXhbOCfym5/Kb9Atk9txPOviJqZJcz7BMzMEuYQMDNLmEPAzCxhDgEzs4Q5BMzMEuYQMDNLmEPAzCxhDgEzs4Q5BMzMEvb/ucuWDpfEXmUAAAAASUVORK5CYII=\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "draw_plot([pres_non_text, recalls_non_text, f1_non_text], title='Score for Non-text Elements')" ] }, { "cell_type": "code", "execution_count": 51, "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": "3.5.6" } }, "nbformat": 4, "nbformat_minor": 2 }