Vladislav Radishevskii

Results 5 issues of Vladislav Radishevskii

I run your pretrained model on my data and I get this ![f43f0165f17fb92e0181a7bb0adf8c15](https://user-images.githubusercontent.com/22772416/123310964-4ef83280-d52f-11eb-8807-58882ce16970.jpg) ![f8236a7733d7307002118fc908279482](https://user-images.githubusercontent.com/22772416/123310985-528bb980-d52f-11eb-9829-2235ddd39b89.jpg) ![fda1a80ab27787e5ffa1c34e4972fdad](https://user-images.githubusercontent.com/22772416/123310999-5586aa00-d52f-11eb-8b49-9d62468016c7.jpg) ![f1a78df3e1c78acd756db160db96d52a](https://user-images.githubusercontent.com/22772416/123311012-58819a80-d52f-11eb-8e07-f5802c62fba6.jpg) ![fdf46b88d2400ecf3a6e2b3874cabf88](https://user-images.githubusercontent.com/22772416/123311079-69caa700-d52f-11eb-99b1-95dd205752ae.jpg) ![fe889de9380a9f65331c55bc38fa1fed](https://user-images.githubusercontent.com/22772416/123311021-5a4b5e00-d52f-11eb-843e-23a3f563a99a.jpg) What can be done to improve the quality?

Здравствуйте. Токенизатор правильно разбивает тексты, где содержатся названия городов: `Ростов-на-Дону Санкт-Петербург` Однако с диапазонами значений он поступает аналогично: `2016-2017` - один токен `5-кратное` - один токен `10ти-кратное` - разбивается на...

Hello! Have you tested the model with high resolution images (512, 1024, ...)? Pictures are also drawn with high quality? What parameters do you recommend to change to train 512x512...

Hello! Thank you for this repository and article. Could you please publish the pre-trained weights used in the article?

How can I add my own condition for example: a = hp.uniform('a', 0.0, 1.0) b = hp.uniform('b', 0.0, 1.0) c = hp.uniform('c', 0.0, 1.0) And sum of a, b and...