Error when running detectnet_v2 while following object detection detectnet from isaac sdk 2019.3

I am following the tutorial mentioned under object detection with detectnet v2 in isaac sdk 2019.3. I have succesfully generated unity3d_kitti_dataset and the mounted it to the said container and did all the edits mentioned in the following steps in specs folder in the article. WHen training the model i get following error ,
"2021-03-19 10:25:23,831 [INFO] tensorflow: Graph was finalized.
INFO:tensorflow:Restoring parameters from /tmp/tmpm7qil01j/model.ckpt-0
2021-03-19 10:25:23,834 [INFO] tensorflow: Restoring parameters from /tmp/tmpm7qil01j/model.ckpt-0
INFO:tensorflow:Running local_init_op.
2021-03-19 10:25:25,111 [INFO] tensorflow: Running local_init_op.
INFO:tensorflow:Done running local_init_op.
2021-03-19 10:25:25,892 [INFO] tensorflow: Done running local_init_op.
INFO:tensorflow:Saving checkpoints for step-0.
2021-03-19 10:25:32,341 [INFO] tensorflow: Saving checkpoints for step-0.
Traceback (most recent call last):
File “/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/client/”, line 1365, in _do_call
return fn(*args)
File “/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/client/”, line 1350, in _run_fn
target_list, run_metadata)
File “/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/client/”, line 1443, in _call_tf_sessionrun
tensorflow.python.framework.errors_impl.InvalidArgumentError: Conv2DCustomBackpropInputOp only supports NHWC.
[[{{node gradients/resnet18_nopool_bn_detectnet_v2/output_bbox/convolution_grad/Conv2DBackpropInput}}]]

Can anyone please help me solve this ?
OS:ubuntu 18.04
isaac sdk:2019.3
GPU: Nvidia GTX 950M
cuda compatibility: 5.1
Nvidia Driver: 460.56