GeorgeJoe

 我出现了这种情况，是什么原因？ @yangxue0827 @yangJirui @toubasi

meet this error fasterrcnn_total_loss: nan

1

meet this error fasterrcnn_total_loss: nan,can anyone help me @yangJirui @yangxue0827 @toubasi

what is the biggest difference with the east?

1

I want to know the biggest difference with the east?the backbone or the postprocess? @huoyijie look forward to hearing from you

修改了anchor数量之后报错了， in bbox_transform_inv pred_ctr_x = dx * widths[:, np.newaxis] + ctr_x[:, np.newaxis] ValueError: operands could not be broadcast together with shapes (294912,1) (491520,1)？

增大ratios和scale之后，代码哪些地方需要修改？

如何进行多尺度的训练？

4

如何进行多尺度的训练？

how to continue train?

can't find FP_Net_end2end_merge_rcnn.sh?

2

can't find FP_Net_end2end_merge_rcnn.sh?

can't find FP_Net_end2end_merge_rcnn.sh? @unsky

can it be used in g++4.8?

2

i meet this error in g++4.8: /usr/local/lib/python2.7/dist-packages/tensorflow/include/tensorflow/core/util/cuda_kernel_helper.h:24:31: fatal error: cuda/include/cuda.h: No such file or directory look forward to hearing from you @Zardinality @JiahuiYu