Xuan Lin
Xuan Lin
You should run `make` and then reinstall python package to validate the changes. @huynhthedang
@srireddy821 1. I use [0.6, 0.15, 0.05] while testing on FDDB. The thresholds are related to your training process(eg. epochs, number of images in training set). 2. The input is...
I use custom op in my code. See this issue [https://github.com/dmlc/mxnet/issues/2180](url) I can't find caffe code for training either.
@dtivger The missing part is computed in previous layers, softmax and linear_regression.
@mycastiel train.py cannot be used directly. You shall use example/train_P/R/O_net.py to train the three networks, and use prepare_data/gen_hard_example.py to collect training data for next stage.
You can have a look at README.md where I explained the data folder structure.
The training set is WIDER FACE and this code is for wider face not FDDB. If you're going to train FDDB, you should generate anno.txt from FDDB anno files, transform...
@anna0709 Place the wider face dataset in "data/wider". "data/mtcnn" stores training images cropped from wider face dataset. You can refer to readme for more details
Did you make any changes to the code?