Skip to content

Face Detection: Make corrections to training script and README #8

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.

Sign up for GitHub

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

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Face Detection: Make corrections to training script and README #8

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 3 additions & 4 deletions face_detection/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,12 +30,11 @@ First, we introduce the functionality of each sub directory.

Second, we present a common procedure for running the code for training (taking v2 as an example).

1. prepare net model `net_farm/naivenet.py`
2. prepare the training data by using the code in `data_provider_farm`. We provide a packed
training data of WIDERFACE trainset. Please download from **Data Download**.
1. prepare net model by running `python3 ./net_farm/naivenet.py`
2. prepare the training data by downloading the training data and saving it in `face_detection/data_provider_farm/data_folder`.
3. adjust the code around the line 241 in `data_iterator_farm/multithread_dataiter_for_cross_entropy_v2`.
4. set the variables in configuration py script in `config_farm`.
5. run `python configuration_10_320_20L_5scales_v2.py` in `config_farm` directory.
5. run `python3 ./face_detection/configuration_10_320_20L_5scales_v2.py` from the top level directory.

### Data Download
We have packed the training data of WIDERFACE train set. In the data, the faces less than 8 pixels are ignored, and some pure negative
Expand Down
2 changes: 2 additions & 0 deletions face_detection/config_farm/configuration_10_320_20L_5scales_v2.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,8 @@
import logging
sys.path.append('..')
sys.path.append('../..')
sys.path.append('./')
sys.path.append('./face_detection')
from ChasingTrainFramework_GeneralOneClassDetection import logging_GOCD
from ChasingTrainFramework_GeneralOneClassDetection import train_GOCD
from ChasingTrainFramework_GeneralOneClassDetection.loss_layer_farm.loss import *
Expand Down