yuanyao366

This problem could be solved after adding one input parameter for the _update_params_on_kvstore function in rfcn/core/module.py _update_params_on_kvstore(self._exec_group.param_arrays, self._exec_group.grad_arrays, self._kvstore, self._param_names)

After you run train_predict.py and get the pretrained model, you should run the ft_classfy.py first, and then use test_classify to test. Please refer to README.md

I have the same probelm with my own dataset. Did you find the solution? Thanks a lot! [session 1][epoch 1][iter 5400/33021] loss: 0.3792, lr: 1.00e-03 fg/bg=(113/399), time cost: 129.585304 rpn_cls:...

@jwyang I use caltech dataset for pedestrian detection. When training, I print num_boxes and gt_boxes under "print loss" like this: print("[session %d][epoch %2d][iter %4d] loss: %.4f, lr: %.2e" \ %...

My training command is : python trainval_net.py --dataset caltech --net vgg16 --bs 2 --gpu 0 --cuda This is my training print-out： [session 1][epoch 1][iter 100] loss: 0.6892, lr: 1.00e-03 fg/bg=(19/493),...

@ChenXuelinCXL If you make your customized dataset as the format of pascal voc , you can try make such change in pascal_voc.py: for ix, obj in enumerate(objs): bbox = obj.find('bndbox')...