tensorflow / tensorflow/models
fps of the quantized model
@pkulzc is already working on this.
Since Nov 22, 2021.
- 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
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Assessment
This issue has not been assessed yet.