Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

高斯热力图执行太慢 #10

Open
wting861006 opened this issue Nov 10, 2020 · 2 comments
Open

高斯热力图执行太慢 #10

wting861006 opened this issue Nov 10, 2020 · 2 comments

Comments

@wting861006
Copy link

@brooklyn1900 作者您好,我在跑train_synthText.py的时候,发现生成高斯热力图的函数执行太慢,可能是导致GPU利用率过低的原因,请问有没有高效的算法?

#获取图片的高斯热力图 def get_region_scores(self, heat_map_size, char_boxes_list): # 高斯热力图 gaussian_generator = GaussianGenerator() region_scores = gaussian_generator.gen(heat_map_size, char_boxes_list) return region_scores

@jelly-Ding
Copy link

@brooklyn1900 作者您好,我在跑train_synthText.py的时候,发现生成高斯热力图的函数执行太慢,可能是导致GPU利用率过低的原因,请问有没有高效的算法?

#获取图片的高斯热力图 def get_region_scores(self, heat_map_size, char_boxes_list): # 高斯热力图 gaussian_generator = GaussianGenerator() region_scores = gaussian_generator.gen(heat_map_size, char_boxes_list) return region_scores

你好,请问您解决了吗

@wting861006
Copy link
Author

@jelly-Ding 我先把所有数据事先处理完,单独保存为npy文件,训练的时候直接np.load。建议在固态硬盘上操作,机械硬盘读取一样会慢。

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants