My computer's gpu doesn't seem to support me

[Cristo-R]

tensorflow.python.framework.errors_impl.ResourceExhaustedError: OOM when allocating tensor with shape[4096,128,4,4] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc [[Node: inpaint_net/b1conv10_atrous/Conv2D = Conv2D[T=DT_FLOAT, data_format="NHWC", dilations=[1, 1, 1, 1], padding="VALID", strides=[1, 1, 1, 1], use_cudnn_on_gpu=true, _device="/job:localhost/replica:0/task:0/device:GPU:0"](inpaint_net/b1conv10_atrous/SpaceToBatchND, inpaint_net/b1conv10_atrous/kernel/read)]] 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. something like this

[vinits5]

Reduce the batch_size parameter from 16 to some lower value. Do it until your system doesn't stop giving ResourceExhaustedError. I hope you are using some GPU and not CPU.

[Cristo-R]

Reduce the batch_size parameter from 16 to some lower value. Do it until your system doesn't stop giving ResourceExhaustedError. I hope you are using some GPU and not CPU. I solved this problem last year, thank you for your reply.Less batch_size will reduce the model's performance so that I try to use colab to run it :)