kwotsin / TensorFlow-ENet

TensorFlow implementation of ENet
MIT License
257 stars 123 forks source link

LookupError: No gradient defined for operation 'ENet/bottleneck2_0_main_max_pool' (op type: MaxPoolWithArgmax) #1

Closed zhangxgu closed 7 years ago

zhangxgu commented 7 years ago

When I run ./train.sh, I find this error. Is this because of the Tensorflow version or I need to define the gradient of ENet/bottleneck2_0_main_max_pool myself? Thx!

kwotsin commented 7 years ago

Are you using a TF version lesser than r1.2? In r1.1 and below the gradient for this argmax isn't defined but this was fixed in r1.2.

zhangxgu commented 7 years ago

@kwotsin Thx! I did not update TF for a long time ....Let me see it .