friendlyelec
/
rk35xx-android14
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from 'd3321b55a8'
${ noResults }
rk35xx-android14/hardware/rockchip/rknn-toolkit2/rknn-toolkit-lite2/examples/dynamic_shape
History
hmz007 70e34291f6
Rockchip Anroid14_SDK 20241219-rkr6 (2f87fee1) 		1 year ago
..
README.md Rockchip Anroid14_SDK 20241219-rkr6 (2f87fee1) 1 year ago
dog_224x224.jpg Rockchip Anroid14_SDK 20240628-rkr5 (2556df1a) 2 years ago
mobilenet_v2_for_rk3562.rknn Rockchip Anroid14_SDK 20241219-rkr6 (2f87fee1) 1 year ago
mobilenet_v2_for_rk3566_rk3568.rknn Rockchip Anroid14_SDK 20241219-rkr6 (2f87fee1) 1 year ago
mobilenet_v2_for_rk3576.rknn Rockchip Anroid14_SDK 20241219-rkr6 (2f87fee1) 1 year ago
mobilenet_v2_for_rk3588.rknn Rockchip Anroid14_SDK 20241219-rkr6 (2f87fee1) 1 year ago
synset_label.py Rockchip Anroid14_SDK 20240628-rkr5 (2556df1a) 2 years ago
test.py Rockchip Anroid14_SDK 20240628-rkr5 (2556df1a) 2 years ago

README.md

How to use dynamic shape function

Model Source

The model used in this example come from the following open source projects:
https://github.com/shicai/MobileNet-Caffe

Convert to RKNN model

Please refer to the example in the RKNN Toolkit2 project to generate the RKNN model: https://github.com/rockchip-linux/rknn-toolkit2/tree/master/examples/functions/dynamic_shape

Script Usage

Usage:

python test.py

Expected Results

This example will print the TOP5 labels and corresponding scores of the test image classification results for each different input shape, as follows:

model: mobilenet_v2

input shape: 1,3,224,224
W The input[0] need NHWC data format, but NCHW set, the data format and data buffer will be changed to NHWC.
-----TOP 5-----
[155] score:0.992188 class:"Shih-Tzu"
[154] score:0.002636 class:"Pekinese, Pekingese, Peke"
[204] score:0.002636 class:"Lhasa, Lhasa apso"
[283] score:0.001698 class:"Persian cat"
[896] score:0.000273 class:"washbasin, handbasin, washbowl, lavabo, wash-hand basin"

input shape: 1,3,160,160
W The input[0] need NHWC data format, but NCHW set, the data format and data buffer will be changed to NHWC.
-----TOP 5-----
[155] score:0.558594 class:"Shih-Tzu"
[154] score:0.408447 class:"Pekinese, Pekingese, Peke"
[204] score:0.031036 class:"Lhasa, Lhasa apso"
[194] score:0.000956 class:"Dandie Dinmont, Dandie Dinmont terrier"
[219] score:0.000256 class:"cocker spaniel, English cocker spaniel, cocker"

input shape: 1,3,256,256
W The input[0] need NHWC data format, but NCHW set, the data format and data buffer will be changed to NHWC.
-----TOP 5-----
[155] score:0.980957 class:"Shih-Tzu"
[154] score:0.008835 class:"Pekinese, Pekingese, Peke"
[204] score:0.004883 class:"Lhasa, Lhasa apso"
[193] score:0.000929 class:"Australian terrier"
[200] score:0.000509 class:"Tibetan terrier, chrysanthemum dog"
  • Note: Different platforms, different versions of tools and drivers may have slightly different results.