RuntimeError: cuDNN error: CUDNN_STATUS_EXECUTION_FAILED

[bostankhan6]

I am getting the following problem while training in colab:

Traceback (most recent call last):
File "train.py", line 94, in
main(config)
File "train.py", line 73, in main
trainer.train()
File "/content/EESRGAN/trainer/cowc_GAN_FRCNN_trainer.py", line 83, in train
self.model.optimize_parameters(current_step)
File "/content/EESRGAN/model/ESRGAN_EESN_FRCNN_Model.py", line 196, in optimize_parameters
l_g_total.backward(retain_graph=True)
File "/usr/local/lib/python3.7/dist-packages/torch/tensor.py", line 107, in backward
torch.autograd.backward(self, gradient, retain_graph, create_graph)
File "/usr/local/lib/python3.7/dist-packages/torch/autograd/init.py", line 93, in backward
allow_unreachable=True) # allow_unreachable flag
RuntimeError: cuDNN error: CUDNN_STATUS_EXECUTION_FAILED

Please help!