def eval_all(args):
devs = args.devices.split(',')
misc.ensure_dir(config.eval_dir)
eval_file = open(os.path.join(config.eval_dir, 'results.txt'), 'a')
dataset_dict = dataset.val_dataset()
records = dataset_dict['records']
nr_records = len(records)
read_func = dataset_dict['read_func']
nr_devs = len(devs)
for epoch_num in range(args.start_epoch, args.end_epoch + 1):
model_file = osp.join(
config.output_dir, 'model_dump',
'epoch_{:d}'.format(epoch_num) + '.ckpt')
pbar = tqdm(total=nr_records)
all_results = []
if nr_devs == 1:
func, inputs = load_model(model_file, devs[0])
for record in records:
data_dict = read_func(record)
result_dict = inference(func, inputs, data_dict)
all_results.append(result_dict)
if args.show_image:
image = result_dict['data']
for db in result_dict['result_boxes']:
if db.score > config.test_vis_threshold:
db.draw(image)
'''if 'boxes' in result_dict.keys():
for db in result_dict['boxes']:
db.draw(image)'''
path_img_unique = '/home/erik/Documents/light_head_rcnn-master/output/predictions/'+str(uuid.uuid4())+'.jpg'
cv2.imwrite(path_img_unique, image)
cv2.imshow('image', image)
cv2.waitKey(0)
pbar.update(1)
else:
nr_image = math.ceil(nr_records / nr_devs)
result_queue = Queue(500)
procs = []
for i in range(nr_devs):
start = i * nr_image
end = min(start + nr_image, nr_records)
split_records = records[start:end]
proc = Process(target=worker, args=(
model_file, devs[i], split_records, read_func,
result_queue))
print('process:%d, start:%d, end:%d' % (i, start, end))
proc.start()
procs.append(proc)
for i in range(nr_records):
t = result_queue.get()
all_results.append(t)
pbar.update(1)
for p in procs:
p.join()
save_filename = save_result(all_results, config.eval_dir, model_file)
print('Save to %s finished, start evaulation!' % save_filename)
saved_stdout = sys.stdout
sys.stdout = eval_file
print("\nevaluation epoch {}".format(epoch_num))
'''if config.test_save_type == 'motherboard': #'coco':
from datasets_odgt.cocoval import cocoval
cocoval(save_filename)
else:
print("not implement")
embed()'''
sys.stdout = saved_stdout
eval_file.flush()
eval_file.close()
print("\n")
import os.path as osp
import network_desp
import tensorflow as tf
from tqdm import tqdm
from utils.py_utils import misc
if __name__ == '__main__':
parser = make_parser()
args = parser.parse_args()
args.devices = misc.parse_devices(args.devices)
if args.end_epoch == -1:
args.end_epoch = args.start_epoch
devs = args.devices.split(',')
misc.ensure_dir(config.eval_dir)
eval_file = open(os.path.join(config.eval_dir, 'results.txt'), 'a')
dataset_dict = dataset.val_dataset()
records = dataset_dict['records']
nr_records = len(records)
read_func = dataset_dict['read_func']
nr_devs = len(devs)
for epoch_num in range(args.start_epoch, args.end_epoch + 1):
model_file = osp.join(config.output_dir, 'model_dump',
'epoch_{:d}'.format(epoch_num) + '.ckpt')
pbar = tqdm(total=nr_records)
all_results = []
if nr_devs > 1:
with tf.variable_scope('', reuse=tf.AUTO_REUSE):
def eval_all(args):
devs = args.devices.split(',')
misc.ensure_dir(config.eval_dir)
eval_file = open(os.path.join(config.eval_dir, 'results.txt'), 'a')
dataset_dict = dataset.val_dataset()
records = dataset_dict['records']
nr_records = len(records)
read_func = dataset_dict['read_func']
nr_devs = len(devs)
for epoch_num in range(args.start_epoch, args.end_epoch + 1):
model_file = osp.join(
config.output_dir, 'model_dump',
'epoch_{:d}'.format(epoch_num) + '.ckpt')
pbar = tqdm(total=nr_records)
all_results = []
if nr_devs == 1:
func, inputs = load_model(model_file, devs[0])
for record in records:
data_dict = read_func(record)
result_dict = inference(func, inputs, data_dict)
all_results.append(result_dict)
if args.show_image:
image = result_dict['data']
for db in result_dict['result_boxes']:
if db.score > config.test_vis_threshold:
db.draw(image)
if 'boxes' in result_dict.keys():
for db in result_dict['boxes']:
db.draw(image)
cv2.imwrite('/tmp/hehe.png', image)
# cv2.imshow('image', image)
# cv2.waitKey(0)
pbar.update(1)
else:
nr_image = math.ceil(nr_records / nr_devs)
result_queue = Queue(500)
procs = []
for i in range(nr_devs):
start = i * nr_image
end = min(start + nr_image, nr_records)
split_records = records[start:end]
proc = Process(target=worker, args=(
model_file, devs[i], split_records, read_func,
result_queue))
print('process:%d, start:%d, end:%d' % (i, start, end))
proc.start()
procs.append(proc)
for i in range(nr_records):
t = result_queue.get()
all_results.append(t)
pbar.update(1)
for p in procs:
p.join()
save_filename = save_result(all_results, config.eval_dir, model_file)
print('Save to %s finished, start evaulation!' % save_filename)
saved_stdout = sys.stdout
sys.stdout = eval_file
print("\nevaluation epoch {}".format(epoch_num))
if config.test_save_type == 'coco':
from datasets_odgt.cocoval import cocoval
cocoval(save_filename)
else:
print("not implement")
embed()
sys.stdout = saved_stdout
eval_file.flush()
eval_file.close()
print("\n")
def eval_all(args):
devs = args.devices.split(',')
misc.ensure_dir(config.eval_dir)
eval_file = open(os.path.join(config.eval_dir, 'results.txt'), 'a')
'''e.g. {
'record': files,
'nr_records': total_files,
'read_func': read_func,
}'''
dataset_dict = dataset.val_dataset()
records = dataset_dict['records']
nr_records = len(records)
read_func = dataset_dict['read_func'] # 数据处理
nr_devs = len(devs)
for epoch_num in range(args.start_epoch, args.end_epoch + 1):
model_file = osp.join(
config.output_dir, 'model_dump',
'epoch_{:d}.ckpt-{:d}'.format(epoch_num, args.step))
pbar = tqdm(total=nr_records)
all_results = []
if nr_devs == 1:
func, inputs = load_model(model_file, devs[0])
for record in records:
data_dict = read_func(record) # 返回一个包含测试文件信息的dict
result_dict = inference(func, inputs, data_dict)
all_results.append(result_dict)
# result_dict包含gt和检出框
# result_dict['boxes'] --> gt
# result_dict['result_boxes'] --> 检出框
if args.show_image:
image = result_dict['data']
# 咦,这里是把检出框画上去,db是一个对象,概率信息包含在db里面
for db in result_dict['result_boxes']:
if db.score > config.test_vis_threshold:
db.draw(image)
# 咦,这里是把gt画上去
if 'boxes' in result_dict.keys():
for db in result_dict['boxes']:
db.draw(image)
fname = os.path.basename(data_dict['image_path'])
cv2.imwrite(os.path.join('images', fname), image)
# cv2.imshow('image', image)
# cv2.waitKey(0)
# pbar.update(1)
else:
nr_image = math.ceil(nr_records / nr_devs)
result_queue = Queue(500)
procs = []
for i in range(nr_devs):
start = i * nr_image
end = min(start + nr_image, nr_records)
split_records = records[start:end]
proc = Process(target=worker, args=(
model_file, devs[i], split_records, read_func,
result_queue))
print('process:%d, start:%d, end:%d' % (i, start, end))
proc.start()
procs.append(proc)
for i in range(nr_records):
t = result_queue.get()
all_results.append(t)
pbar.update(1)
for p in procs:
p.join()
save_filename = save_result(all_results, config.eval_dir, model_file)
print('Save to %s finished, start evaulation!' % save_filename)
saved_stdout = sys.stdout
sys.stdout = eval_file
print("\nevaluation epoch {}".format(epoch_num))
if config.test_save_type == 'adas':
from datasets_odgt.cocoval import cocoval
cocoval(save_filename)
else:
print("not implement")
embed()
sys.stdout = saved_stdout
eval_file.flush()
eval_file.close()
print("\n")
def eval_all(args):
devs = args.devices.split(',')
misc.ensure_dir(config.eval_dir)
'''e.g. {
'record': files,
'nr_records': total_files,
'read_func': read_func,
}'''
dataset_dict = dataset.val_dataset()
records = dataset_dict['records']
nr_records = len(records)
read_func = dataset_dict['read_func'] # 数据处理
nr_devs = len(devs)
model_file = osp.join(
config.output_dir, 'model_dump',
'light-head.ckpt-{:d}'.format(args.step))
#pbar = tqdm(total=nr_records)
all_results = []
if nr_devs == 1:
print('restore from ckpt %s' % model_file)
func, inputs = load_model(model_file, devs[0])
num_records = len(records)
for i in range(num_records):
record = records[i]
'''data_dict, e.g. {
'data': xx,
'boxes': xx,
'image_id': xx,
'image_path': xx,
}
'''
sys.stdout.write('im_detect: {:d}/{:d}\r'.format(i, num_records))
data_dict = read_func(record) # 返回一个包含测试文件信息的dict
result_dict = inference(func, inputs, data_dict)
all_results.append(result_dict)
# result_dict包含gt和检出框
# result_dict['boxes'] --> gt
# result_dict['result_boxes'] --> 检出框
if args.show_image:
image = result_dict['data']
# 咦,这里是把检出框画上去,db是一个对象,概率信息包含在db里面
for db in result_dict['result_boxes']:
if db.score > config.test_vis_threshold:
# 见lib/detection_opr/box_utils/box.py
db.draw(image)
# 咦,这里是把gt画上去
if 'boxes' in result_dict.keys():
for db in result_dict['boxes']:
db.draw(image)
fname = os.path.basename(data_dict['image_path'])
cv2.imwrite(os.path.join('eval', fname), image)
# cv2.imshow('image', image)
# cv2.waitKey(0)
# pbar.update(1)
else:
nr_image = math.ceil(nr_records / nr_devs)
result_queue = Queue(500)
procs = []
for i in range(nr_devs):
start = i * nr_image
end = min(start + nr_image, nr_records)
split_records = records[start:end]
proc = Process(target=worker, args=(
model_file, devs[i], split_records, read_func,
result_queue))
print('process:%d, start:%d, end:%d' % (i, start, end))
proc.start()
procs.append(proc)
for i in range(nr_records):
t = result_queue.get()
all_results.append(t)
#pbar.update(1)
for p in procs:
p.join()
save_result_v2(all_results, config.eval_dir)
print('Save result finished, start evaulation!')
if config.test_save_type == 'adas':
from datasets_odgt.adasval import adasval
adasval(cfg)
else:
print("not implement")
embed()
def predict_video(args):
devs = args.devices.split(',')
misc.ensure_dir(config.eval_dir)
#vidpath = 'http://192.168.1.137:8080/video' #Home IP Camera
vidpath = 'http://10.42.0.37:8080/video' #Lab IP Camera
f = open("step-by-step_guide.txt", "r")
steps = [x.split('\n') for x in f.read().split("#") if x != '']
for i in range(len(steps)):
steps[i] = [x for x in steps[i] if x != '']
m = open("motherboard_database.txt", "r")
mb_info = [x.split('#') for x in m.read().split("\n") if x != '']
current_mb = []
cap = cv2.VideoCapture(vidpath)
w = cap.get(cv2.CAP_PROP_FRAME_WIDTH)
h = cap.get(cv2.CAP_PROP_FRAME_HEIGHT)
font = cv2.FONT_ITALIC
step = 0
epoch_num = args.predict_epoch
model_file = osp.join( config.output_dir, 'model_dump','epoch_{:d}'.format(epoch_num) + '.ckpt')
func, inputs = load_model(model_file, devs[0])
avg_fps = []
thresh = 0.4
thresh_list = {2:0.6,4:0.4,5:0.4,8:0.8,9:0.4,11:0.6,12:0.4,14:0.4,15:0.4,17:0.5,18:0.4,19:0.4,20:0.7,22:0.2,24:0.4,25:0.4,27:0.4,28:0.4,30:0.8,31:0.95,33:0.7,34:0.4,36:0.7,37:0.4}
frame_width = int(cap.get(3))
frame_height = int(cap.get(4))
#out = cv2.VideoWriter('/home/erik/Documents/light_head_rcnn-master/data/motherboard/test/test_to_result/output_video.avi',cv2.VideoWriter_fourcc('M','J','P','G'), 15, (frame_width,frame_height))
while(True):
#fps_start = time.time()
ret, frame = cap.read()
cv2.namedWindow('image',cv2.WINDOW_NORMAL)
if(ret == True and step < len(steps)):
draw_steps(steps, step, frame, w, h, font,current_mb)
specify_classes = get_specific_classes(steps,step)
if specify_classes != 0:
result_dict = inference(func, inputs, frame)
if type(specify_classes) == str:
specify_classes = [specify_classes]
if step in thresh_list.keys():
thresh = thresh_list[step]
else:
thresh = 0.4
for db in result_dict['result_boxes']:
if db.score > thresh and db.tag in specify_classes: #preferred score of box to apply to picture
#print(db)
db.draw(frame)
if db.tag in config.class_names[1:3+1]:
for i in mb_info:
if db.tag == i[0]:
current_mb = i
cv2.imshow('image', frame) #display results'
#out.write(frame)
else:
cv2.imshow('image', frame) # display results'
#out.write(frame)
#fps_end = time.time()
#frame_rate = 1 / (fps_end - fps_start)
#print("FPS: ",frame_rate)
#print(thresh)
#avg_fps.append(frame_rate)
k = cv2.waitKey(1)
if k:
if k == ord(' '): #Click 'space' to go to next step
step += 1
elif k == ord('i'): #increase threshold
if thresh < 1.0:
thresh += 0.05
elif k == ord('d'):
if thresh > 0.1: #decrease threshold
thresh -= 0.05
elif k == ord('p') and step > 0: #Click 'p' to go to previous step if step > 0
step -= 1
elif k == ord('q'): #Click 'q' to stop the guide
print("The step-by-step guide interrupted...")
break
else:
break
cap.release()
#out.release()
cv2.destroyAllWindows()
#total_fps = sum(avg_fps)/len(avg_fps)
#print("AVERAGE FPS: ",total_fps)
print("\n")