PocketFlow
PocketFlow copied to clipboard
Tencent
An Automatic Model Compression (AutoMC) framework for developing smaller and faster AI applications.
Is there a plan to support the transformer framework?
E.g. ```shell root@linuxkit-025000000001:/Users/test/work/PocketFlow/learners# grep cifar_10 * -r nonuniform_quantization/bit_optimizer.py: if self.dataset_name == 'cifar_10': nonuniform_quantization/learner.py: if dataset_name == 'cifar_10': nonuniform_quantization/learner.py: if self.dataset_name == 'cifar_10': nonuniform_quantization/learner.py: if self.dataset_name == 'cifar_10': uniform_quantization/bit_optimizer.py: if self.dataset_name...
How many operations are supported under the framework of PocketFlow? I didn't find any docs listing the ops available. By the way, the acceleration ratio according to the performance of...
Hi, thanks for the awesome work and for implementing channel pruning. I'm the first author of the channel pruning paper (Channel Pruning for Accelerating Very Deep Neural Networks) As my...
``` In PocketFlow, we adopt multi-GPU training to speed-up this time-consuming training process. Our implementation is compatible with: Horovod: a distributed training framework for TensorFlow, Keras, and PyTorch. TF-Plus: an...
