tensorflow / tensorflow/models

fps of the quantized model

Open
#10,377 0 comments 0 reactions 3 assignees View on GitHub

@pkulzc is already working on this.

Since Nov 22, 2021.

models:research:odapi type:bug
Dominant language
Python
Stars
77.7k
Forks
44.8k
PR merge metrics
No merged PRs in 30d

Description

Prerequisites

Please answer the following questions for yourself before submitting an issue.

  • I am using the latest and TensorFlow 2.5

hey
i trained a model with ssd_mobilenet_v2_fpnlite_320x320_coco17_tpu-8 and then exported with export_tflite_graph_tf2.pytflite_convert --output_file=./tflite/detectquantt.tflite
--graph_def_file=/home/dell/Desktop/TF1/models/research/object_detection/train_head/inf_graph/ssdlite/tflite_graph.pb
--input_arrays=normalized_input_image_tensor
--output_arrays='TFLite_Detection_PostProcess','TFLite_Detection_PostProcess:1','TFLite_Detection_PostProcess:2','TFLite_Detection_PostProcess:3'
--input_shape=1,300,300,3 --allow_custom_ops

.I am quantized the my model.But there is no fps difference between model and quantized model on raspberry

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.