James Hennessey

@ aalzaid I am getting very similar errors regarding std::thread and result_type to you but nothing regarding CUDNN. I have checked my CUDA 7.5 and cuDNN 5.1 installations. I am...

@vrv - Do you recall how many steps you trained for in those 15hours? I've trained on GPU for >24hrs but performance is below yours, so trying why there is...

Thanks for responding. I'm using 8 x V100 GPUS, Batch size of 1 and num_cell_centers=512 (training only). So far trained for 22K steps. mAP/L1 for Vehicles is 0.4135 on validation....

Thanks for the reply @vrv. I added `tf.compat.v1.disable_v2_behavior()` which has stoped the error above. I also had to change ``` SUPPORTED_SPLIT_SIZE = { 1: [1, 1, 1, 1], .... ```...