search

sagieppel / Fully-convolutional-neural-network-FCN-for-semantic-segmentation-Tensorflow-implementation

68 stars 40 forks source link

TRIAN.PY Problem #9

Closed leishi2018 closed 5 years ago

leishi2018 commented 5 years ago

Hello, I meet this issues that I take my own RGB test picture and PNG labels .but it comes this (and RGB test picture are not the same size)

ResourceExhaustedError (see above for traceback): OOM when allocating tensor of shape [7,7,512,4096] and type float[[Node: W6/Adam/Initializer/zeros = Const[_class=["loc:@W6"], dtype=DT_FLOAT, value=Tensor<type: float shape: [7,7,512,4096] values: [[[0 0 0]]]...>, _device="/job:localhost/replica:0/task:0/device:GPU:0"]()]]

sagieppel commented 5 years ago

Out of memory issue. Use a smaller image. Smaller batch size. Larger GPU or other lighter network,