training code

[liyangliu]

Hi, @jshtok I find there is only testing code in your repository, could you please add usage of your code about how to train your model? thanks.

[liyangliu]

Hi, @fityanul, have you successfully trained a model with the reported mAP performance in the paper? Thanks.

[fityanul]

Hi, @fityanul, have you successfully trained a model with the reported mAP performance in the paper? Thanks.

Dear @liyangliu I am sorry for the late reply. I still try to training and get the reported results. How about you? Are you have done in achieved the results?

Thank You Fityanul Akhyar

[liyangliu]

Hi, @fityanul, actually I can not achieve the results in the paper by training with the uploaded code.

[cxcjcj]

Hi, @jshtok I tried to train your model,and here is a little problem that i found：

Traceback (most recent call last): File "./experiments/fpn_end2end_train_test.py", line 31, in train_end2end.main() File "./experiments/../fpn/train_end2end.py", line 292, in main config.TRAIN.begin_epoch, config.TRAIN.end_epoch, config.TRAIN.lr, config.TRAIN.lr_step) File "./experiments/../fpn/train_end2end.py", line 120, in train_net num_ex_per_class = num_ex_per_class) File "./experiments/../fpn/../lib/utils/load_data.py", line 10, in load_gt_roidb per_category_epoch_max=per_category_epoch_max,classes_list_fname=classes_list_fname,num_ex_per_class=num_ex_per_class) File "./experiments/../fpn/../lib/dataset/imagenet.py", line 58, in init synsets = sio.loadmat(os.path.join(self.devkitpath, 'data', 'meta'+base_modifier+'.mat')) File "/home/cx/.conda/envs/RepMet/lib/python2.7/site-packages/scipy/io/matlab/mio.py", line 207, in loadmat MR, file_opened = mat_reader_factory(file_name, appendmat, **kwargs) File "/home/cx/.conda/envs/RepMet/lib/python2.7/site-packages/scipy/io/matlab/mio.py", line 62, in mat_reader_factory byte_stream, file_opened = _open_file(file_name, appendmat) File "/home/cx/.conda/envs/RepMet/lib/python2.7/site-packages/scipy/io/matlab/mio.py", line 37, in _open_file return open(file_like, 'rb'), True IOError: [Errno 2] No such file or directory: './data/imagenet/ILSVRC/devkit/data/meta_clsloc.mat' I am looking forward to your replay.

[duynn912]

Dear @jshtok, Would you mind share your hyperparameters to get the results in your papers If training PASCAL and ImageNetLOC. For example, how many gpu you use, lr, ...? Because I follow your yaml to train, I think I cannot reach the performance like yours. And in this issue, I see others did not get to yours.

[shenglih]

@jshtok just to follow up on the bbox_overlaps_python ImportError: I have followed your previous comments and recompiled successfully on Linux, leaving the following files in /lib/utils/: init.py bbox.pyx bbox_utils.py pycache bbox.so build bbox.c bbox_cython.egg-info dist bbox.cpython-35m-x86_64-linux-gnu.so bbox_regression.py setup_linux.py bbox.cpython-36m-x86_64-linux-gnu.so bbox_transform.py setup_windows.py

Still the bbox_overlaps_python error... Would you mind illustrating what I missed here? Thanks so much

[jshtok]

Hi @cxcjcj,

I did not include the ILSVRC devkit in the shared data folder. Please download the ILSVRC 2012 devkit to ./data/imagenet/ILSVRC location.

[jshtok]

Hi @shenglih, I have tried to work this out in my environment, but unfortunately I cannot help you with this error.