I have pc with two 1080 gtx-ti and 32gb of ram. I want to train model from scratch on my own dataset and to utilize my gpu during training.
Whenever I want to train model with width and height above 544 I got Out Of Memory Error.
[[Node: mul_31/_397 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device_incarnation=1, tensor_name="edge_5148_mul_31", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"]()]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info.
I have try various combination of batch-size and subdivision but got error whenever width and height is greater than 544.
I have pc with two 1080 gtx-ti and 32gb of ram. I want to train model from scratch on my own dataset and to utilize my gpu during training. Whenever I want to train model with width and height above 544 I got Out Of Memory Error.
[[Node: mul_31/_397 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device_incarnation=1, tensor_name="edge_5148_mul_31", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"]()]] Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info.
I have try various combination of batch-size and subdivision but got error whenever width and height is greater than 544.