Closed siarez closed 5 years ago
Thanks a lot, sorry for delay!
@siarez I read your code for create the target heatmap, but I have some question for this: your bbox is not 256256, you get the heat map is 6464, how to make the heat map get point in the bbox? Its say your bbox will resize to 256*256 to train, I cant understand that. could you help to explain that? Thanks!
@flyduck FAN outputs 64x64 heatmaps, even tough the input image is 256x256. That's why the target heatmaps are 64x64.
@siarez thank you for your answer. I have another question, did you do some data enhance for the train data? such as rotation, scale, transform?
@flyduck I didn't, but it sounds like a good idea. You can look at the original lua code for FAN to see if they did it originally.
@siarez thank you very much! I use your code to generate the 646468 heat map, and then I use the "get_preds_fromhm" function to get the cordinate from the gt heat map, but the point is some like not really correct, have you do some experiment like this?
@flyduck what do you mean by not really correct?
@siarez Its means that when I use the gt heat map by the function "get_preds_fromhm" to get landmark in the ori image, the landmark is not the same as the GT.
@flyduck Hmm, you will loose some accuracy due to quantization. Because your landmarks coordinates are scaled down from their original scale to fit the 64x64 grid. To make sure nothing fishy is going on, check the mean of the error residuals. It should be close to zero.
create_target_heatmap()
is useful for people who want to fine-tune or train the model from scratch. Figuring it out was not trivial, so I thought it will save people time. It addresses #128