def main():
img_seq = []
# Get img_ids from lvis, instead.
img_ids = coco.getImgIds()
num_images = len(img_ids)
# import ipdb; ipdb.set_trace()
dets = []
dets.append(coco.loadRes(PRE_PATH))
prog_bar = mmcv.ProgressBar(len(img_ids))
for i, img_id in enumerate(img_ids):
# ipdb.set_trace()
if DEBUG_ is True:
if i == DEBUG_FRAMES: break
img_info = coco.loadImgs(ids=[img_id])[0]
img_path = IMG_PATH + img_info['file_name']
img = cv2.imread(img_path)
# Create a gt labeled img.
gt_ids = coco.getAnnIds(imgIds=[img_id])
gts = coco.loadAnns(gt_ids)
gt_img = img
for j, pred in enumerate(gts):
bbox = _coco_box_to_bbox(pred['bbox'])
cat_id = pred['category_id']
gt_img = add_box(gt_img, bbox, 1.00, cat_id)
gt_img = add_to_canvas(gt_img)
# Create a predictions labeled img.
for k in range(len(dets)):
pred_ids = dets[k].getAnnIds(imgIds=[img_id])
preds = dets[k].loadAnns(pred_ids)
pred_img = img.copy()
for j, pred in enumerate(preds):
bbox = _coco_box_to_bbox(pred['bbox'])
sc = pred['score']
cat_id = pred['category_id']
if sc > VIS_THR:
pred_img = add_box(pred_img, bbox, sc, cat_id)
# ipdb.set_trace()
pred_img = add_to_canvas(pred_img)
# Create a super image and save it.
sup_img = np.concatenate((gt_img, pred_img), axis=1)
sup_img_name = 'pre_{}.jpg'.format(str(img_id).zfill(12))
cv2.imwrite(os.path.join(OUT_PATH, sup_img_name), sup_img)
img_seq.append(sup_img)
prog_bar.update()
def evaluate_coco(model,
dataset,
coco,
eval_type="bbox",
limit=0,
image_ids=None):
"""Runs official COCO evaluation.
dataset: A Dataset object with valiadtion data
eval_type: "bbox" or "segm" for bounding box or segmentation evaluation
limit: if not 0, it's the number of images to use for evaluation
"""
# Pick COCO images from the dataset
image_ids = image_ids or dataset.image_ids
# Limit to a subset
if limit:
image_ids = image_ids[:limit]
# Get corresponding COCO image IDs.
coco_image_ids = [dataset.image_info[id]["id"] for id in image_ids]
t_prediction = 0
t_start = time.time()
results = []
for i, image_id in enumerate(image_ids):
# Load image
image = dataset.load_image(image_id)
# Run detection
t = time.time()
r = model.detect([image], verbose=0)[0]
t_prediction += (time.time() - t)
# Convert results to COCO format
image_results = build_coco_results(dataset, coco_image_ids[i:i + 1],
r["rois"], r["class_ids"],
r["scores"], r["masks"])
results.extend(image_results)
# Load results. This modifies results with additional attributes.
coco_results = coco.loadRes(results)
# Evaluate
cocoEval = COCOeval(coco, coco_results, eval_type)
cocoEval.params.imgIds = coco_image_ids
cocoEval.evaluate()
cocoEval.accumulate()
cocoEval.summarize()
print("Prediction time: {}. Average {}/image".format(
t_prediction, t_prediction / len(image_ids)))
print("Total time: ", time.time() - t_start)
cv2.putText(image,
txt, (bbox[0], bbox[1] - 2),
cv2.FONT_HERSHEY_SIMPLEX,
0.5, (0, 0, 0),
thickness=1)
cv2.rectangle(image, (bbox[0], bbox[1]), (bbox[2], bbox[3]), color, 2)
return image
if __name__ == '__main__':
dets = []
img_ids = coco.getImgIds()
num_images = len(img_ids)
for k in range(1, len(sys.argv)):
pred_path = sys.argv[k]
dets.append(coco.loadRes(pred_path))
# import pdb; pdb.set_trace()
for i, img_id in enumerate(img_ids):
img_info = coco.loadImgs(ids=[img_id])[0]
img_path = IMG_PATH + img_info['file_name']
img = cv2.imread(img_path)
gt_ids = coco.getAnnIds(imgIds=[img_id])
gts = coco.loadAnns(gt_ids)
gt_img = img.copy()
for j, pred in enumerate(gts):
bbox = _coco_box_to_bbox(pred['bbox'])
cat_id = pred['category_id']
gt_img = add_box(gt_img, bbox, 0, cat_id)
for k in range(len(dets)):
pred_ids = dets[k].getAnnIds(imgIds=[img_id])
preds = dets[k].loadAnns(pred_ids)
thickness=1)
cv2.rectangle(image, (bbox[0], bbox[1]), (bbox[2], bbox[3]), color, 2)
return image
if __name__ == '__main__':
dets = []
img_ids = coco.getImgIds()
num_images = len(img_ids)
ipdb.set_trace()
#for k in range(1, len(sys.argv)):
# pred_path = sys.argv[k]
# dets.append(coco.loadRes(pred_path))
dets.append(coco.loadRes(ANN_PATH))
# import pdb; pdb.set_trace()
for i, img_id in enumerate(img_ids):
img_info = coco.loadImgs(ids=[img_id])[0]
img_path = IMG_PATH + img_info['file_name']
img = cv2.imread(img_path)
gt_ids = coco.getAnnIds(imgIds=[img_id])
gts = coco.loadAnns(gt_ids)
gt_img = img.copy()
for j, pred in enumerate(gts):
bbox = _coco_box_to_bbox(pred['bbox'])
cat_id = pred['category_id']
gt_img = add_box(gt_img, bbox, 0, cat_id)
for k in range(len(dets)):
pred_ids = dets[k].getAnnIds(imgIds=[img_id])
return iou
def _box_inside(box2, box1):
inside = (box2[0] >= box1[0] and box2[1] >= box1[1] and \
box2[2] <= box1[2] and box2[3] <= box1[3])
return inside
if __name__ == '__main__':
if len(sys.argv) > 2:
ANN_PATH = sys.argv[2]
coco = coco.COCO(ANN_PATH)
pred_path = sys.argv[1]
out_path = pred_path[:-5] + '_no_ghost.json'
dets = coco.loadRes(pred_path)
img_ids = coco.getImgIds()
num_images = len(img_ids)
thresh = 4
out = []
for i, img_id in enumerate(img_ids):
if i % 500 == 0:
print(i)
pred_ids = dets.getAnnIds(imgIds=[img_id])
preds = dets.loadAnns(pred_ids)
num_preds = len(preds)
for j in range(num_preds):
overlap_score = 0
if preds[j]['score'] > 0.2:
for k in range(num_preds):
if preds[j]['category_id'] == preds[k]['category_id'] and \
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import pycocotools.coco as coco
from pycocotools.cocoeval import COCOeval
import sys
import cv2
import numpy as np
import pickle
import os
print("eval-coco")
this_dir = os.path.dirname(__file__)
# ANN_PATH = this_dir + '../../data/coco/annotations/instances_val2017.json'
ANN_PATH = this_dir + '/store/datasets/UA-Detrac/COCO-format/test.json'
print(ANN_PATH)
if __name__ == '__main__':
pred_path = sys.argv[1]
coco = coco.COCO(ANN_PATH)
dets = coco.loadRes(pred_path)
img_ids = coco.getImgIds()
num_images = len(img_ids)
coco_eval = COCOeval(coco, dets, "bbox")
coco_eval.evaluate()
coco_eval.accumulate()
coco_eval.summarize()
'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow',
'elephant', 'bear', 'zebra', 'giraffe', 'backpack', 'umbrella', 'handbag',
'tie', 'suitcase', 'frisbee', 'skis', 'snowboard', 'sports ball', 'kite',
'baseball bat', 'baseball glove', 'skateboard', 'surfboard',
'tennis racket', 'bottle', 'wine glass', 'cup', 'fork', 'knife', 'spoon',
'bowl', 'banana', 'apple', 'sandwich', 'orange', 'broccoli', 'carrot',
'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch', 'potted plant',
'bed', 'dining table', 'toilet', 'tv', 'laptop', 'mouse', 'remote',
'keyboard', 'cell phone', 'microwave', 'oven', 'toaster', 'sink',
'refrigerator', 'book', 'clock', 'vase', 'scissors', 'teddy bear',
'hair drier', 'toothbrush'
]
annot_path = "/home/user/home/user/Xinyuan/work/CenterNet-1/data/coco/annotations/instances_val2017.json"
coco = coco.COCO(annot_path)
save_dir = "/home/user/home/user/Xinyuan/work/CenterNet-1/exp/ctdet/coco_hg/"
coco_dets = coco.loadRes('{}/results.json'.format(save_dir))
coco_eval = COCOeval(coco, coco_dets, "bbox")
print(dir(coco_eval))
save_path = "src/cache/fail/"
coco_dets = coco.loadRes('{}/results.json'.format(save_dir))
coco_eval = COCOeval(coco, coco_dets, "bbox")
p = coco_eval.params
p.imgIds = list(np.unique(p.imgIds))
p.maxDets = sorted(p.maxDets)
coco_eval.params = p
coco_eval._prepare()
cat_dict = coco.cats
# print(cat_dict)
catIds = coco_eval.params.catIds
computeIoU = coco_eval.computeIoU
coco_eval.ious = {(imgId, catId): coco_eval.computeIoU(imgId, catId) \
det['bbox'] = [
ji[0], ji[1], ji[2] - ji[0] + 1, ji[3] - ji[1] + 1
]
dets.append(det)
return dets
ann_path = '/media/leo/data/code/pangnet/detection/object_as_point/Git/CenterNet/data/voc/annotations/pascal_test2007.json'
# pred_path = '/media/leo/data/code/pangnet/detection/object_as_point/Git/CenterNet/exp/ctdet/fatnet_frn_pascal_192_daspp_dcn_dla/results.json'
# pred_path = '/media/leo/data/code/pangnet/detection/object_as_point/Git/CenterNet/exp/ctdet/resnet_18_dcn_lr_1x/results.json'
pred_path = '/media/leo/data/code/pangnet/detection/object_as_point/Git/CenterNet/exp/ctdet/fatnet_frn_pascal_192_93/results.json'
ann_json = json.load(open(ann_path))
pred = json.load(open(pred_path))
jcoco = json.load(
open(
'/media/leo/data/code/mm_ped/work_dirs/faster_rcnn_r50_fpn_baseline/12.json'
))
pred_convert = convert(pred, ann_json)
pred_convert_path = pred_path[:-4] + '_convert.json'
json.dump(pred_convert, open(pred_convert_path, 'w'))
coco = coco.COCO(ann_path)
dets = coco.loadRes(pred_convert_path)
img_ids = coco.getImgIds()
num_images = len(img_ids)
coco_eval = COCOeval(coco, dets, "bbox")
coco_eval.evaluate()
coco_eval.accumulate()
coco_eval.summarize()
def eval(model_arch, model_path, img_dir, gt_annot_path):
output = "output"
if os.path.exists(output):
shutil.rmtree(output)
os.mkdir(output)
os.environ['CUDA_VISIBLE_DEVICES'] = "0"
if LoadImagesAndLabels.num_classes <= 5:
colors = [(55, 55, 250), (255, 155, 50), (128, 0, 0), (255, 0, 255),
(128, 255, 128), (255, 0, 0)]
else:
colors = [(v // 32 * 64 + 64, (v // 8) % 4 * 64, v % 8 * 32)
for v in range(1, LoadImagesAndLabels.num_classes + 1)][::-1]
detector = CtdetDetector(model_arch, model_path)
print('\n/****************** Eval ****************/\n')
import tqdm
import pycocotools.coco as coco
from pycocotools.cocoeval import COCOeval
print("gt path: {}".format(gt_annot_path))
result_file = '../evaluation/instances_det.json'
coco = coco.COCO(gt_annot_path)
images = coco.getImgIds()
num_samples = len(images)
print('find {} samples in {}'.format(num_samples, gt_annot_path))
#------------------------------------------------
coco_res = []
for index in tqdm.tqdm(range(num_samples)):
img_id = images[index]
file_name = coco.loadImgs(ids=[img_id])[0]['file_name']
image_path = os.path.join(img_dir, file_name)
img = cv2.imread(image_path)
results, hm = detector.work(img) # 返回检测结果和置信度图
class_num = {}
for res in results:
cls, conf, bbox = res[0], res[1], res[2]
coco_res.append({
'bbox':
[bbox[0], bbox[1], bbox[2] - bbox[0], bbox[3] - bbox[1]],
'category_id':
LoadImagesAndLabels.class_name.index(cls),
'image_id':
img_id,
'score':
conf
})
if cls in class_num:
class_num[cls] += 1
else:
class_num[cls] = 1
color = colors[LoadImagesAndLabels.class_name.index(cls)]
# 绘制标签&置信度
label_ = '{}:{:.1f}'.format(cls, conf)
plot_one_box(bbox,
img,
color=color,
label=label_,
line_thickness=2)
cv2.imwrite(output + "/" + os.path.basename(image_path), img)
cv2.namedWindow("heatmap", 0)
cv2.imshow("heatmap", np.hstack(hm[0].cpu().numpy()))
cv2.namedWindow("img", 0)
cv2.imshow("img", img)
key = cv2.waitKey(1)
#-------------------------------------------------
with open(result_file, 'w') as f_dump:
json.dump(coco_res, f_dump, cls=NpEncoder)
cocoDt = coco.loadRes(result_file)
cocoEval = COCOeval(coco, cocoDt, 'bbox')
# cocoEval.params.imgIds = imgIds
cocoEval.params.catIds = [1] # 1代表’Hand’类，你可以根据需要增减类别
cocoEval.evaluate()
print('\n/***************************/\n')
cocoEval.accumulate()
print('\n/***************************/\n')
cocoEval.summarize()
draw_pr(cocoEval)
import torch.nn
import torch.nn.functional as F
import matplotlib.pyplot as plt
import pycocotools.coco as coco
from pycocotools.cocoeval import COCOeval
# GT
coco = coco.COCO(
'/media/vincent/856c2c04-3976-4948-ba47-5539ecaa24be/vincent/Code/CenterNet-cuda10-multi-spectral/data/rgb/annotations/test.json'
)
# Prediction
coco_dets = coco.loadRes('{}/results.json'.format(
'/media/vincent/856c2c04-3976-4948-ba47-5539ecaa24be/vincent/Checkpoint/CenterNet-CentralNet/ctdet/default/'
))
coco_eval = COCOeval(coco, coco_dets, "bbox")
coco_eval.evaluate()
print('')
coco_eval.accumulate()
print('')
coco_eval.summarize()
# 返回mAP值
print(coco_eval.stats[1])
category_id = _valid_ids[cat_id]
bbox = item['bbox']
bbox[2] -= bbox[0]
bbox[3] -= bbox[1]
bbox_out = list(map(_to_float, bbox[0:4]))
detection = {
"image_id": int(image_id),
"category_id": int(category_id),
"bbox": bbox_out,
"score": float("{:.2f}".format(item['score']))
}
detections.append(detection)
return detections
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('--gt_path', type=str, default='')
parser.add_argument('--result_path', type=str, default='')
opt = parser.parse_args()
# path = 'C:/Users/zhuoyuhe/Desktop/incepio/CenterTrack/exp/results/'
coco = coco.COCO(opt.gt_path)
with open(opt.result_path + '/save_results_nuscenes.json') as f:
result = json.load(f)
det = convert_eval_format(result)
json.dump(det, open('{}/results_coco.json'.format(opt.result_path), 'w'))
coco_dets = coco.loadRes(opt.result_path + '/results_coco.json')
coco_eval = COCOeval(coco, coco_dets, "bbox")
coco_eval.evaluate()
coco_eval.accumulate()
coco_eval.summarize()
