def ms_eval(ms_res_dirs, cfg):
merge_box = cfg.TEST.MERGE_BOX
'''
for scale in ms_res_dirs["scales"]:
print("*************** Scale:", scale, " ***************")
result_dir = ms_res_dirs["result_prefix"] + "_" + str(scale)
model = RRPNDemo(
cfg,
min_image_size=scale,
confidence_threshold=0.6,
)
image_list = os.listdir(ms_res_dirs['ori_im_dir'])
num_images = len(image_list)
cnt = 0
for idx in range(len(image_list)):
image = 'img_' + str(idx+1) + '.jpg'
impath = os.path.join(ms_res_dirs['ori_im_dir'], image)
# print('image:', impath)
img = cv2.imread(impath)
cnt += 1
tic = time.time()
predictions, bounding_boxes = model.run_on_opencv_image(img)
toc = time.time()
print('time cost:', str(toc - tic)[:6], '|', str(cnt) + '/' + str(num_images))
# img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
bboxes_np = bounding_boxes.bbox.data.cpu().numpy()
scores = bounding_boxes.get_field("scores").data.cpu().numpy()
# ms_scores = bounding_boxes.get_field("mask_score").data.cpu().numpy()
# bboxes_np[:, 2:4] /= cfg.MODEL.RRPN.GT_BOX_MARGIN
# if merge_box:
# bboxes_np_reverse = bboxes_np.copy()
# bboxes_np_reverse[:, 2:4] = bboxes_np_reverse[:, 3:1:-1]
# bboxes_np_reverse = merge(bboxes_np_reverse)
# bboxes_np_reverse[:, 2:4] = bboxes_np_reverse[:, 3:1:-1]
# bboxes_np = bboxes_np_reverse
width, height = bounding_boxes.size
# if vis:
# pil_image = vis_image(Image.fromarray(img), bboxes_np)
# pil_image.save(os.path.join(image_vis_dir, image))
# pil_image.show()
# time.sleep(20)
# else:
write_result_ICDAR_RRPN2polys(image[:-4],
bboxes_np,
threshold=0.7,
result_dir=result_dir,
height=height,
width=width,
cls_prob=scores,
# ms_scores=ms_scores,
scale=[scale for i in range(bboxes_np.shape[0])])
del model
'''
f_list = os.listdir(ms_res_dirs["result_prefix"] + "_" +
str(ms_res_dirs["scales"][0]))
nms_thres = 0.1
cnt = 0
if len(os.listdir(fuse_resdir)) > 0:
print(os.popen("rm -rf " + fuse_resdir).read())
os.makedirs(fuse_resdir)
for resname in f_list:
if resname[-4:] == '.txt':
# print('resname:', resname)
all_boxes = []
for scale in ms_res_dirs["scales"]:
result_dir = ms_res_dirs["result_prefix"] + "_" + str(scale)
all_boxes.append(get_rboxes(os.path.join(result_dir, resname)))
# sboxes = get_rboxes(os.path.join(ms_res_dirs['S'], resname)).reshape(-1, 6)
# mboxes = get_rboxes(os.path.join(ms_res_dirs['M'], resname)).reshape(-1, 6)
# lboxes = get_rboxes(os.path.join(ms_res_dirs['L'], resname)).reshape(-1, 6)
# print('shape:', sboxes.shape, mboxes.shape, lboxes.shape)
# idx = int(((int(resname[-9:-4]) - 1) / 5000)) + 1
imdir = os.path.join(ms_res_dirs['ori_im_dir'], resname[4:-4])
# imdir = os.path.join(ms_res_dirs['ori_im_dir']) + '/tr_' + resname[4:-4]
# print('resname:', resname[-9:-4])
im = cv2.imread(imdir + '.jpg')
'''
if im is None:
im = cv2.imread(imdir + '.JPG')
if im is None:
im = cv2.imread(imdir + '.png')
if im is None:
tmp = imageio.mimread(imdir + '.gif')
im_tmp = np.array(tmp)
im_tmp = im_tmp[0]
im = im_tmp[:, :, 0:3]
'''
height, width = im.shape[:2]
all_boxes = np.concatenate(all_boxes, axis=0)
# all_boxes[:, -1] = 1 - all_boxes[:, -1]
# cls_score, ms_score, scales
arg = np.argsort(-all_boxes[:, 6])
all_boxes = all_boxes[arg]
keep = rnms(
np.concatenate([all_boxes[:, :5], all_boxes[:, 5:6]], axis=1),
nms_thres)
# print(keep)
# all_boxes = all_boxes[keep]
# merge_keep = merge_closest(all_boxes[:, :5], all_boxes[:, 5], 0.85)
# all_boxes = all_boxes[merge_keep]
all_boxes = all_boxes[all_boxes[:, 5] > 0.8]
# all_boxes = all_boxes[all_boxes[:, 6] > 0.55]
# print('all_boxes:', all_boxes.shape)
cnt += 1
print('cnt:', str(cnt) + '/' + str(len(f_list)), resname)
write_result_ICDAR_RRPN2polys(
resname[4:-4],
all_boxes,
0.7,
fuse_resdir_4save,
height,
width,
cls_prob=all_boxes[:, 5],
# ms_scores=all_boxes[:, 6],
scale=all_boxes[:, 6])
write_result_ICDAR_RRPN2polys(
resname[4:-4],
all_boxes,
0.7,
fuse_resdir,
height,
width,
# cls_prob=all_boxes[:, 5],
# ms_scores=all_boxes[:, 6],
# scale=all_boxes[:, 7]
)
zipfilename = os.path.join(fuse_resdir, 'submit_MS_test.zip')
if os.path.isfile(zipfilename):
print('Zip file exists, removing it...')
os.remove(zipfilename)
zip_dir(fuse_resdir, zipfilename)
# res_dict = compute_hmean(zipfilename)
# res_samples = res_dict["per_sample"]
# print("res_sample:", res_samples.keys())
pkl_cache = "res_cache.pkl"
# if not os.path.isfile(pkl_cache):
res_dict = compute_hmean(zipfilename)
# res_samples = res_dict["per_sample"]
res_samples = res_dict["per_sample"]
pkl_f = open(pkl_cache, "wb")
pickle.dump(res_samples, pkl_f)
pkl_f.close()
# else:
# pkl_f = open(pkl_cache, "rb")
# res_samples = pickle.load(pkl_f)
# print("res_sample:", res_samples.keys())
'''
comm = 'curl -i -F "submissionFile=@' + zipfilename + '" http://127.0.0.1:8080/evaluate'
# print(comm)
print(os.popen(comm, 'r'))
'''
vis_eval(res_samples, ms_res_dirs['ori_im_dir'], fuse_resdir_4save)
width, height = bounding_boxes.size
if vis:
pil_image = vis_image(Image.fromarray(img), bboxes_np)
pil_image.show()
time.sleep(10)
write_result_ICDAR_RRPN2polys(image[:-4],
bboxes_np,
threshold=0.7,
result_dir=result_dir,
height=height,
width=width)
#im_file, dets, threshold, result_dir, height, width
#cv2.imshow('win', predictions)
#cv2.waitKey(0)
if dataset_name == 'IC15':
zipfilename = os.path.join(
result_dir, 'submit_' + config_file.split('/')[-1].split('.')[0] +
'_' + cfg.MODEL.WEIGHT.split('/')[-1].split('.')[0] + '.zip')
if os.path.isfile(zipfilename):
print('Zip file exists, removing it...')
os.remove(zipfilename)
zip_dir(result_dir, zipfilename)
comm = 'curl -i -F "submissionFile=@' + zipfilename + '" http://127.0.0.1:8080/evaluate'
# print(comm)
print(os.popen(comm, 'r'))
else:
pass
def gotest(setting_weights, config_file, remove_output_dir=False):
# config_file = "configs/arpn/e2e_rrpn_R_50_C4_1x_train_AFPN_RT.yaml" #'configs/rrpn/e2e_rrpn_R_50_C4_1x_LSVT_test_RFPN.yaml' #'#"configs/ICDAR2019_det_RRPN/e2e_rrpn_R_50_C4_1x_LSVT_val_4scales_angle_norm.yaml" #e2e_rrpn_R_50_C4_1x_ICDAR13_15_trial_test.yaml
# update the config options with the config file
cfg.merge_from_file(config_file)
# manual override some options
cfg.merge_from_list(["MODEL.DEVICE", "cuda"])
if remove_output_dir:
cfg.merge_from_list(["OUTPUT_DIR", ""])
opts = ["MODEL.WEIGHT", setting_weights]
cfg.merge_from_list(opts)
# cfg.MODEL.WEIGHT = setting_weights
# cfg.freeze()
vis = True
merge_box = cfg.TEST.MERGE_BOX
result_dir = os.path.join('results',
config_file.split('/')[-1].split('.')[0],
cfg.MODEL.WEIGHT.split('/')[-1].split('.')[0])
if merge_box:
result_dir += '_merge_box'
if not os.path.isdir(result_dir):
os.makedirs(result_dir)
else:
print(os.popen("rm -rf " + result_dir).read())
os.makedirs(result_dir)
coco_demo = RRPNDemo(
cfg,
min_image_size=1260,
confidence_threshold=0.4,
)
#
dataset_name = cfg.TEST.DATASET_NAME
print("dataset_name:", dataset_name)
testing_dataset = {
'LSVT': {
'testing_image_dir':
'../datasets/LSVT/train_full_images_0/train_full_images_0/',
'off': [0, 3000]
},
'ArT': {
'testing_image_dir':
'../datasets/ArT/ArT_detect_train/train_images',
'off': [4000, 5603]
},
'ReCTs': {
'testing_image_dir': '',
'off': [0, 1000000]
},
'MLT': {
'testing_image_dir': '/mnt/nvme/Dataset/MLT/val/image/',
'off': [0, 1000000]
},
'MLT_test': {
'testing_image_dir': [
'/mnt/nvme/Dataset/MLT/test/MLT19_TestImagesPart1/TestImagesPart1',
'/mnt/nvme/Dataset/MLT/test/MLT19_TestImagesPart2/TestImagesPart2'
],
'off': [0, 1000000]
},
'IC15': {
'testing_image_dir': '../dataset/ICDAR15/ch4_test_images/',
'off': [0, 500],
'gt_dir': "../dataset/ICDAR15/Challenge4_Test_Task4_GT"
},
'docVQA': {
'testing_image_dir':
'../dataset/docVQA/docvqa_train_v0.1/documents/',
'off': [4000, 4330],
# 'gt_dir':"../dataset/ICDAR15/Challenge4_Test_Task4_GT"
},
'docVQA_TEST': {
'testing_image_dir': '../dataset/docVQA/test/documents/',
'off': [0, 1000000] # [4000, 4330],
# 'gt_dir':"../dataset/ICDAR15/Challenge4_Test_Task4_GT"
},
'docVQA_VAL': {
'testing_image_dir': '../dataset/docVQA/val/documents/',
'off': [0, 1000000]
}
}
image_dir = testing_dataset[dataset_name]['testing_image_dir']
# vocab_dir = testing_dataset[dataset_name]['test_vocal_dir']
off_group = testing_dataset[dataset_name]['off']
# load image and then run prediction
# image_dir = '../datasets/ICDAR13/Challenge2_Test_Task12_Images/'
# imlist = os.listdir(image_dir)[off_group[0]:off_group[1]]
image_vis_dir = "vis_results_" + dataset_name + "/"
if not os.path.isdir(image_vis_dir):
os.makedirs(image_vis_dir)
print('************* META INFO ***************')
print('config_file:', config_file)
print('result_dir:', result_dir)
print('image_dir:', image_dir)
print('weights:', cfg.MODEL.WEIGHT)
print('merge_box:', merge_box)
print('***************************************')
imlist = []
if type(image_dir) == list:
for dir in image_dir:
tmp_list = os.listdir(dir)
for im_name in tmp_list:
imlist.append(os.path.join(dir, im_name))
else:
imlist = os.listdir(image_dir)
imlist.sort()
num_images = len(imlist)
cnt = 0
if dataset_name in ['ReCTs', 'MLT']:
for image in imlist:
# image = 'gt_' + str(idx) + '.jpg'
if type(image_dir) == list:
impath = image
else:
impath = os.path.join(image_dir, image)
# print('image:', impath)
img = cv2.imread(impath)
cnt += 1
tic = time.time()
predictions, bounding_boxes = coco_demo.run_on_opencv_image(img)
toc = time.time()
print('time cost:',
str(toc - tic)[:6], '|',
str(cnt) + '/' + str(num_images))
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
bboxes_np = bounding_boxes.bbox.data.cpu().numpy()
# bboxes_np[:, 2:4] /= cfg.MODEL.RRPN.GT_BOX_MARGIN
if merge_box:
bboxes_np_reverse = bboxes_np.copy()
bboxes_np_reverse[:, 2:4] = bboxes_np_reverse[:, 3:1:-1]
bboxes_np_reverse = merge(bboxes_np_reverse)
bboxes_np_reverse[:, 2:4] = bboxes_np_reverse[:, 3:1:-1]
bboxes_np = bboxes_np_reverse
width, height = bounding_boxes.size
if vis:
pil_image = vis_image(Image.fromarray(img), bboxes_np)
# pil_image.show()
# time.sleep(20)
else:
results_prefix = image[:-4].replace(
'tr_', '') if dataset_name == 'MLT' else image[:-4]
write_result_ICDAR_RRPN2polys(results_prefix,
bboxes_np,
threshold=0.7,
result_dir=result_dir,
height=height,
width=width)
# im_file, dets, threshold, result_dir, height, width
# cv2.imshow('win', predictions)
# cv2.waitKey(0)
else:
num_images = min(off_group[1], len(imlist)) - off_group[0]
for idx in range(off_group[0], min(off_group[1], len(imlist))):
if dataset_name == "IC15":
image = 'img_' + str(idx + 1) + '.jpg' #idx
else:
image = imlist[idx]
impath = os.path.join(image_dir, image)
# print('image:', impath)
img = cv2.imread(impath)
# img = padding32(img)
cnt += 1
tic = time.time()
predictions, bounding_boxes = coco_demo.run_on_opencv_image(img)
toc = time.time()
print('time cost:',
str(toc - tic)[:6], '|',
str(cnt) + '/' + str(num_images), image)
bboxes_np = bounding_boxes.bbox.data.cpu().numpy()
# bboxes_np[:, 2:4] /= cfg.MODEL.RRPN.GT_BOX_MARGIN
# bboxes_np[:, :2] = bboxes_np[:, :2] - 16.
if merge_box:
bboxes_np_reverse = bboxes_np.copy()
bboxes_np_reverse[:, 2:4] = bboxes_np_reverse[:, 3:1:-1]
bboxes_np_reverse = merge(bboxes_np_reverse)
bboxes_np_reverse[:, 2:4] = bboxes_np_reverse[:, 3:1:-1]
bboxes_np = bboxes_np_reverse
width, height = bounding_boxes.size
scores = bounding_boxes.get_field("scores").data.cpu().numpy()
if bboxes_np.shape[0] > 0:
# merge_keep = merge_closest(bboxes_np, scores, 0.81)
# bboxes_np = bboxes_np[merge_keep]
# scores = scores[merge_keep]
pass
if vis:
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
pil_image = Image.fromarray(img)
# print("bboxes_np:", bboxes_np)
if "gt_dir" in testing_dataset[dataset_name]:
gt_file = os.path.join(
testing_dataset[dataset_name]["gt_dir"],
"gt_" + image.split(".")[0] + ".txt")
gt_lines = open(gt_file, "r").readlines()
gt_boxes = []
for line in gt_lines:
splts = line.replace("\r", "").replace("\n",
"").split(",")
if len(splts) > 8:
gt_boxes.append(
np.array(splts[:8]).astype(np.int32))
pil_image = vis_image(pil_image,
np.array(gt_boxes),
mode=1,
repre="poly")
# gt_image.save(os.path.join(image_vis_dir, "gt_" + image))
pil_image = vis_image(pil_image, bboxes_np, mode=2)
pil_image.save(os.path.join(image_vis_dir, image))
# cv2.imwrite(os.path.join(image_vis_dir, "mask_" + image), predictions)
# pil_image.show()
# time.sleep(20)
# else:
# print("bboxes_np", bboxes_np.shape)
write_result_ICDAR_RRPN2polys(image[:-4],
bboxes_np,
threshold=0.7,
result_dir=result_dir,
height=height,
width=width)
#im_file, dets, threshold, result_dir, height, width
# print("predictions:", predictions.shape)
# cv2.imshow('win', predictions)
# cv2.waitKey(0)
del coco_demo
if dataset_name == 'IC15':
zipfilename = os.path.join(
result_dir, 'submit_' + config_file.split('/')[-1].split('.')[0] +
'_' + cfg.MODEL.WEIGHT.split('/')[-1].split('.')[0] + '.zip')
if os.path.isfile(zipfilename):
print('Zip file exists, removing it...')
os.remove(zipfilename)
zip_dir(result_dir, zipfilename)
comm = 'curl -i -F "submissionFile=@' + zipfilename + '" http://127.0.0.1:8080/evaluate'
print(comm)
print(os.popen(comm, 'r'))
res_dict = compute_hmean(zipfilename)
del res_dict["per_sample"]
print(res_dict)
return res_dict
elif dataset_name == 'MLT':
zipfilename = os.path.join(
result_dir, 'submit_' + config_file.split('/')[-1].split('.')[0] +
'_' + cfg.MODEL.WEIGHT.split('/')[-1].split('.')[0] + '.zip')
if os.path.isfile(zipfilename):
print('Zip file exists, removing it...')
os.remove(zipfilename)
zip_dir(result_dir, zipfilename)
comm = 'curl -i -F "submissionFile=@' + zipfilename + '" http://127.0.0.1:8080/evaluate'
# print(comm)
print(os.popen(comm, 'r'))
elif dataset_name == 'LSVT':
# input_json_path = 'results/e2e_rrpn_R_50_C4_1x_LSVT_val/model_0190000/res.json'
gt_json_path = '../datasets/LSVT/train_full_labels.json'
# to json
input_json_path = res2json(result_dir)
eval_func(input_json_path, gt_json_path)
elif dataset_name == 'ArT':
# input_json_path = 'results/e2e_rrpn_R_50_C4_1x_LSVT_val/model_0190000/res.json'
gt_json_path = '../datasets/ArT/ArT_detect_train/train_labels.json'
# to json
input_json_path = res2json(result_dir)
eval_func(input_json_path, gt_json_path)
else:
pass
return None