XavierFlow

@missliontheway Hi, I also have this problem, have you figured it out? If so, would you please share it? I have stuck in this code a few days. Thank you...

@lyz0305 Actually my dataset structure had been converted to VOC =.= It seems that I should rewrite the input module. Thanks though for your word.

Hi guys, any updates about this issue? Recently I plan to train efficient net on my own dataset. The image size is 36*36. I have tested it by using the...

Just an update: change image size to any nums seems OK since the maxpool and pad will do the work. I finally use 32*2=64 as input. Everything go smooth. I...

Hi @aditya1709 , have you solved this problem? I am also trying to convert the model to trt4.1, but issue #47 claims that only trt > 5.1.5 works. Any updates?

Hi @ZYX0106 @uber-research, I am also facing the libjpeg version issue right now? My error msg is 'Wrong JPEG library version: library is 90, caller expect 62'. But actually I...

Yes. To solve this problem, you should make sure you have correctly linked the libjpeg.62.so before you install jpeg2dct. In my case, I install libjpeg62 under `/usr/local/lib`. But I find...

@BichenWuUCB Hi, I also have similar question. Instead training on KITTI or VOC, I train it in my own dataset which have VOC structure. The loss decrease in the first...

Sorry, can’t help in this issue. I cannot solve the problem, so then I try some other network... Sent from my iPhone On Jun 26, 2018, at 22:38, alan20062006 wrote:...

Sorry but ... nope, I finally change to another structure. Not sure if this will work but from my perspective, the version of tensorflow and python should be the most...