def __init__(self, input_size=(640, 480)):
self.C = config.Config()
self.C.offset = True
self.C.size_test = input_size
input_shape_img = (self.C.size_test[0], self.C.size_test[1], 3)
img_input = Input(shape=input_shape_img)
# define the network prediction
preds = nn.nn_p3p4p5(img_input, offset=self.C.offset, num_scale=self.C.num_scale, trainable=True)
self.model = Model(img_input, preds)
self.model_path = '/root/webapp/detector/models_weight'
self.detec_hum(np.random.rand(200, 300, 3))
from keras.models import Model
from eval_city.dt_txt2json import convert_file
from eval_city.eval_script.coco import COCO
from eval_city.eval_script.eval_MR_multisetup import COCOeval
from keras_csp import config, bbox_process
from keras_csp.utilsfunc import *
# parse experiment name
if len(sys.argv) == 1:
exp_name = ''
else:
exp_name = '_{}'.format(sys.argv[1])
os.environ["CUDA_VISIBLE_DEVICES"] = '0'
C = config.Config()
C.offset = True
cache_path = 'data/cache/cityperson/val_500'
with open(cache_path, 'rb') as fid:
val_data = cPickle.load(fid)
num_imgs = len(val_data)
print('num of val samples: {}'.format(num_imgs))
C.size_test = (1024, 2048)
input_shape_img = (C.size_test[0], C.size_test[1], 3)
img_input = Input(shape=input_shape_img)
# define the base network (resnet here, can be MobileNet, etc)
if C.network == 'resnet50':
from keras_csp import resnet50 as nn
elif C.network == 'mobilenet':
