Which .pb file should I use? The one in serving model or the one in frozen model?

bendangnuksung / mrcnn_serving_ready

🛠 Mask R-CNN Keras to Tensorflow and TFX models + Serving models using TFX GRPC & RESTAPI

https://github.com/matterport/Mask_RCNN

MIT License

103 stars 35 forks source link

Which .pb file should I use? The one in serving model or the one in frozen model? #18

Closed boycao closed 5 years ago

boycao commented 5 years ago

Hi there,

There are two different .pb file in both tensorflow_serving_model and the frozen_pb. If I want to inference the model, which .pb file should I use? Thanks.

bendangnuksung commented 5 years ago

If you are inferencing using Tensorflow Model Server go for saved_model.pb otherwise you can frozen_model.pb for normal Tensorflow inference

boycao commented 5 years ago

Thanks!