slow segmentation with deeplab

[hakS07]

@toniz Hi, I have trained deep lab on my custom dataset(50*50,3400 images) for iris eyes object with 257 as crop size and during the test, it detects for crop with crop size 257 . i tested the pb model with code python it detects ok

now what I need is to integrate my model on ios application, i was able to successfully convert the model to tflite .but it gives me a slow segmentation tflite_convert ----output_format=TFLITE --inference_type=FLOAT --inference_input_type=FlOAT --input_arrays=sub_2 --input_shapes=1,257,257,3 --output_arrays=ResizeBilinear_2 --output_file=/Users/hak/Downloads/deeplabv3_mnv2_pascal_trainvall/mobilenet.tflite --graph_def=/Users/hak/Downloads/deeplabv3_mnv2_pascal_trainvall/mobilenet.pb --mean_values=128 --std_dev_values=127 --allow_custom_ops --post_training_quantize tflite file size=2,2mo however the original deeplab tflite file works fine on the appliacation i have changed fps to 60 and to 240 but nothing change i use iphone6+

[toniz]

Use this model From model zoo:

mobilenetv2_dm05_coco_voc_trainaug https://github.com/tensorflow/models/blob/master/research/deeplab/g3doc/model_zoo.md

Convert tflite like this: convert2pb.sh:

xwj@master01:/data/xwj/segmentation/train$ cat convert2pb.sh python ../../models/research/deeplab/export_model.py \ --checkpoint_path=log_all/model.ckpt-100000 \ --depth_multiplier=0.5 \ --quantize_delay_step=0 \ --export_path=tflite_all/frozen_inference_graph.pb

conver2tflite.sh:

xwj@master01:/data/xwj/segmentation/train$ cat conver2tflite.sh tflite_convert \ --graph_def_file=tflite_all/frozen_inference_graph.pb \ --output_file=tflite_all/frozen_inference_graph.tflite \ --output_format=TFLITE \ --input_shape=1,513,513,3 \ --input_arrays="MobilenetV2/MobilenetV2/input" \ --change_concat_input_ranges=true \ --output_arrays="ArgMax"