How can solve GPU problem for FCN ?

[xxchenchen]

trafficstars

I used

from keras_segmentation. models. fcn import fcn_8_resnet50

from keras_segmentation. models. fcn import fcn_32_resnet50

from keras_segmentation. models. fcn import fcn_8_mobilenet

from keras_segmentation. models. fcn import fcn_32_mobilenet

I received the error. How can I get rid of the problem? thanks ResourceExhaustedError: OOM when allocating tensor with shape[7,7,2048,4096] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc [[{{node training/Adadelta/add_849}} = Add[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:GPU:0"](training/Adadelta/Variable_437/read, training/Adadelta/add_133/y)]] 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.

 [[{{node metrics/jaccard_loss/Mean/_3417}} = _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_22923_metrics/jaccard_loss/Mean", 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.

[HoseinHashemi]

Same issue. Any work around?