FCHD-Fully-Convolutional-Head-Detector
FCHD-Fully-Convolutional-Head-Detector copied to clipboard
Code for FCHD - A fast and accurate head detector
hello,To bother you,i have some questions. l test you final train model by using the picture of hollywood dataset,its accuracy is bad,should i need using hollywood dataset to try again?
I can't find the AP part of the code
![image](https://user-images.githubusercontent.com/14344027/66898803-70034300-f02c-11e9-92fd-8af489cd0843.png)
Has the paper been accepted by ICIP? If yes, when can it be retrieved
Is it necessary to download and use Hollywoods dataset? Is it ok if i just use brainwash dataset? Thanks
function eval in train.py doesn't look like computing this AP metric. someone know how to get ap of own models? thank you very much for your help
I have followed the steps to run demo but I get inaccurate results. The boxes of heads are seen to be offset from their original coordinate(see the results). ![Figure_1](https://user-images.githubusercontent.com/31055972/62670889-54921100-b9c7-11e9-8c6d-2cdf8650d04a.png) ![Figure_2](https://user-images.githubusercontent.com/31055972/62670891-56f46b00-b9c7-11e9-8ec7-a0879d799ff9.png)
Hello author, I use your code and data set to retrain. Model training that is retrained is very strange, but it is good to use the model you provide.Do the...
The code of train.py is used to train and dataset is brainwash,but i don't get good model,can you help me ? Thankyou!
hello,when i train ,I encountered the following problems:A figure window is always new and closed,It was caused by matplotlib,I annotated everything about plot.show(),but it didn't.It seems that the new figure...