Open balancap opened 7 years ago
Thanks Paul for porting it to TF.
confidence_threshold
(0.01) is used to filter out most of detections before select top_k detections for NMS.0.76 is decent. I think this specific model should give 0.81 mAP.
Thanks for your help ! Yes, I am trying to obtain 0.81 mAP, which is the score I got testing directly your code. It may be a bit different at the end, but I hope to be around 0.8.
One last question : I have seen that you're using the Fast NMS implementation. What is the default value of the eta
parameter you're using? I could not find it in the python script.
Thanks again!
Cool, thanks again :) So if without any adaptive, it is completely equivalent to the original NMS algorithm I guess. The mAP I got after fixing a few bugs is around 0.77. Still need to figure out why it is not closer to 0.8. Is there a way with your implementation to get the full recall-precision curve?
You can get this information out or plot it out.
I just noticed that you are calculating the AP per class, and then averaging over all the classes (https://github.com/weiliu89/caffe/blob/ssd/src/caffe/solver.cpp#L519-L547). I was computing a very crude AP on all classes mixed ! I'll implement your approach and see if I get closer results :)
Hello,
Finally managed to reproduce your results ! I had a few bugs remaining in my L2-normalization layer and the padding correction in TF. Everything seems consistent now :)
@balancap Thanks Paul for the wonderful work! Is the TF code able to train and get similar results? Or does it only support evaluating a converted Caffe model?
I have a basic training script on Pascal VOC datasets, but it is not working as well as yours for now ! I need in particular to improve the data augmentation parts which seems quite crucial.
I see. Thanks! I think most of the augmentation is already implemented in TF.
Yes, and I am using most of them ! I got some decent results when I played a bit with the KITTI dataset.
I need to look at a bit closer as despite the hard negative mining, I had still too much false positives at the end. It may have to do with the scaling and cropping parameters the data augmentation.
Hi there,
I'm trying to dig into the source code for the caffe ssd. @balancap mentioned about score_ssd_pascal_ft.py
. I searched the repository and couldn't find that file. Has the file been moved somewhere or is it merged with the score_ssd_*.py
files?
Thanks.
score_ssd_pascal_ft.py
is included in the fine-tuned model archives, rather than in the main code repository.
Hello,
I have been implementing your SSD paper to TensorFlow (if you want to have a look: https://github.com/balancap/SSD-Tensorflow). Before playing a bit around with different architecture, I am trying to reproduce your performances on Pascal VOC 2007. I have a few questions concerning the post-processing evaluation. I tried to understand the pipeline from your code, but I am not completely sure about it (I used weights from http://www.cs.unc.edu/~wliu/projects/SSD/models_VGGNet_VOC0712_SSD_300x300_ft.tar.gz):
ratio
andsizes
described in the filescore_ssd_pascal_ft.py
?confidence_threshold
used in the evaluation? Do you filter out some boxes after NMS based on their scores?I am sorry if it sounds a bit like a long enquiry! I am not too far away from reproducing your mAP score (I got around 0.76), but I think it would be great to have a TensorFlow implementation which is up to your performances!
Thanks for your help! Paul