You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
使用video 跑视频的时候,转换图像过程中,,100/350时,就提示
ResourceExhaustedError (see above for traceback): OOM when allocating tensor with shape[1,522,682,64] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc
[[Node: deconv2/conv_transpose/conv/MirrorPad = MirrorPad[T=DT_FLOAT, Tpaddings=DT_INT32, mode="REFLECT", _device="/job:localhost/replica:0/task:0/device:GPU:0"](deconv2/conv_transpose/resize_images/ResizeNearestNeighbor, conv2/conv/MirrorPad/paddings)]]
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.
当我在跑 video程序的时候,converting image 516/562 时就停止了,输出了mp4视频,但是无法打开,你知道怎么解决吗?
Converting image 516/562zsh: killed python3 fast-neural-style/video.py --model_file models/cubist.ckpt-done
The text was updated successfully, but these errors were encountered: