def model_evaluate_and_save(self, _actor, _critic, _class_name):
# self.model_actor.compile(optimizer='rmsprop', loss=_loss_func, metrics=['accuracy'])
# loss, accuracy = self.model_actor.evaluate(self.eval_x, self.eval_y)
#
# _, best_loss = self.get_best_loss_file(_class_name)
# if best_loss > loss:
today = utils.get_today()
time_now = utils.get_time()
path = self.get_model_weight_path(_class_name)
file_path = path + _class_name + '_' + today + '_' + time_now + '_'
_actor.save_weights(file_path + 'actor.h5')
_critic.save_weights(file_path + 'critic.h5')
size_upsample = (image_size[1], image_size[0])
b, nc, h, w = feature_conv.shape
# weight softmax x convolution weight and normalize
cam = weight_softmax[class_idx].dot(feature_conv.reshape((nc, h * w)))
cam = cam.reshape(h, w)
cam = cam - np.min(cam)
cam_img = (255 * cam / np.max(cam)).astype(np.uint8)
output_cam = cv2.resize(cam_img, size_upsample)
return output_cam
if __name__ == '__main__':
args = parser.parse_args()
# make folder
today = utils.get_today() + '_cam'
save_dir = Path(args.save_dir) / today
utils.make_folder(save_dir)
# transform
transform = transforms.Compose([
transforms.Resize((128, 128)),
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
])
#load CIFAR10 DATASETS
testset = torchvision.datasets.CIFAR10(root=args.data_dir,
train=False,
download=True,
transform=transform)
def get_index():
print('CALL old TS...')
df = ts_utils_api.call_sh_index()
write_data(df, 'stock_index')
return df
def get_calender(start, end):
print('CALL pro ...')
df = ts_pro_api.call_calender(start, end)
write_data(df, 'calender')
return df
if __name__ == '__main__':
print('clear stock_index...')
DBUtils.truncate('stock_index')
print('set stock_index...')
df = get_index()
print('clear calender...')
DBUtils.truncate('calender')
print('set calender...')
df = get_calender(Utils.day0, Utils.get_today())
print('SAMPLE:')
df = read_data('calender')
print(df.tail())
parser.add_argument('--num_workers', type=int, default=2, help='number of workers for training')
parser.add_argument('--lr', '--learning_rate', type=float, default=0.0001, help='learning rate')
parser.add_argument('--num_class', type=int, default=10, help='number of classes to classify of datasets')
parser.add_argument('--momentum', default=0.9, type=float, metavar='M',
help='momentum for sgd, alpha parameter for adam')
parser.add_argument('--beta', default=0.999, type=float, metavar='M', help='beta parameters for adam')
parser.add_argument('--model', required=True, type=str, help='beta parameters for adam optimizer')
# classes index for CIFAR10
classes = ('plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck')
if __name__ == '__main__':
args = parser.parse_args()
# make folder for experiment
today = utils.get_today()
save_dir = Path(args.save_dir) / today
utils.make_folder(save_dir)
# summary writer
writer = SummaryWriter(save_dir)
# transform data
transform = transforms.Compose([
transforms.Resize((args.img_size, args.img_size)),
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
])
# load data
trainset = torchvision.datasets.CIFAR10(root=args.data_dir, train=True, download=True, transform=transform)
import requests
from data import DataGather
from utils import utils
mStock_num_dic = {}
mStock_name_dic = {}
def get_dic_data_path():
paths = os.getcwd() + '/data/dic_data/'
if not os.path.exists(paths):
os.makedirs(paths)
return paths
DIC_NAME_FILE = get_dic_data_path() + utils.get_today() + '_stock_name_dic.csv'
DIC_NUM_FILE = get_dic_data_path() + utils.get_today() + '_stock_num_dic.csv'
def parse_stock_dictionary():
global mStock_num_dic
global mStock_name_dic
base_url_kospi = 'https://finance.naver.com/sise/sise_market_sum.nhn?sosok=0&page='
base_url_kosdaq = 'https://finance.naver.com/sise/sise_market_sum.nhn?sosok=1&page='
mStock_num_dic = {}
mStock_name_dic = {}
for base_url in [base_url_kospi, base_url_kosdaq]:
for i in range(1, 11):
url = base_url + str(i)