zyc4me

Results 7 comments of zyc4me

Can you give an example on using the training conf. of the following training strategy of Applying the two-stage training strategy or the one-stage training strategy?

@liminghuiv @wizyoung @lovepan1 hi guys， i have met the same problem， i use the /misc/experiments_on_voc/args_voc.py， and do not use two stage train, just use one stage, my log is similar...

RuntimeError:PyDict_Check(elem) INTERNAL ASSERT FAILED at "/pytorch/torch/csrc/jit/passes/onnx/shape_type_inference.cpp":701,please report a bug to PyTorch.

how did you solved this problom?

感谢分享，请问网盘给出的model和deploy不能加载成功是什么原因？

@liuhengli I did not solved it. i try to get prototxt from caffemodel, there is layer type 'deconvoluton' not 'upsample', so the model i think is a lillte old, the...

The loss value didn't drop when it came down to about 7.X?

same question，have you solved it？

The loss value didn't drop when it came down to about 7.X?

just continue to train

training loss doesn't decrease after several hundreds steps

@Chanbluky HI，do you have the deploy_voc.caffemodel? Could you please share it to me?

training loss doesn't decrease after several hundreds steps

@Chanbluky [email protected], Thank you!