Hello, would it be possible to have ENet ready for Caffe2?
ENet seems perfect for real time image segmentation on smartphones.
Tensorflow implementation by Kwotsin cannot be deployed into CPU-only powered phones because of max_pooling_with_argmax kernel not being implemented for CPU by Tensorflow.
Hello, would it be possible to have ENet ready for Caffe2? ENet seems perfect for real time image segmentation on smartphones. Tensorflow implementation by Kwotsin cannot be deployed into CPU-only powered phones because of max_pooling_with_argmax kernel not being implemented for CPU by Tensorflow.