why throws a ResourceExhaustedError after a 30 epochs training process?

taki0112 / Densenet-Tensorflow

Simple Tensorflow implementation of Densenet using Cifar10, MNIST

MIT License

506 stars 196 forks source link

why throws a ResourceExhaustedError after a 30 epochs training process? #14

Open eroszip opened 6 years ago

eroszip commented 6 years ago

i have encounted a problem with a ResourceExhaustedError ,while i have train this model with 30 epochs，some details as follows: image_size=224*224,batch_size=16,bn_blocks=2.and my GPU memory is about 16G.