Skip to content

Python sample for referencing object detection model with TensorRT

Notifications You must be signed in to change notification settings

AastaNV/TRT_object_detection

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

TensorRT Python Sample for Object Detection

Performance includes memcpy and inference.

Model Input Size TRT Nano
ssd_inception_v2_coco(2017) 300x300 49ms
ssd_mobilenet_v1_coco 300x300 36ms
ssd_mobilenet_v2_coco 300x300 46ms

Since the optimization of preprocessing is not ready yet, we don't include image read/write time here.

Install dependencies

$ sudo apt-get install python3-pip libhdf5-serial-dev hdf5-tools
$ pip3 install --extra-index-url https://developer.download.nvidia.com/compute/redist/jp/v42 tensorflow-gpu==1.13.1+nv19.5 --user
$ pip3 install numpy pycuda --user


Download model

Please download the object detection model from TensorFlow model zoo.

$ git clone https://github.com/AastaNV/TRT_object_detection.git
$ cd TRT_object_detection
$ mkdir model
$ cp [model].tar.gz model/
$ tar zxvf model/[model].tar.gz -C model/
Supported models:
  • ssd_inception_v2_coco_2017_11_17
  • ssd_mobilenet_v1_coco
  • ssd_mobilenet_v2_coco

We will keep adding new model into our supported list.



Update graphsurgeon converter

Edit /usr/lib/python3.6/dist-packages/graphsurgeon/node_manipulation.py

diff --git a/node_manipulation.py b/node_manipulation.py
index d2d012a..1ef30a0 100644
--- a/node_manipulation.py
+++ b/node_manipulation.py
@@ -30,6 +30,7 @@ def create_node(name, op=None, _do_suffix=False, **kwargs):
     node = NodeDef()
     node.name = name
     node.op = op if op else name
+    node.attr["dtype"].type = 1
     for key, val in kwargs.items():
         if key == "dtype":
             node.attr["dtype"].type = val.as_datatype_enum


RUN

1. Maximize the Nano performance

$ sudo nvpmodel -m 0
$ sudo jetson_clocks

2. Update main.py based on the model you used

from config import model_ssd_inception_v2_coco_2017_11_17 as model
from config import model_ssd_mobilenet_v1_coco_2018_01_28 as model
from config import model_ssd_mobilenet_v2_coco_2018_03_29 as model

3. Execute

$ python3 main.py [image]

It takes some time to compile a TensorRT model when the first launching.
After that, TensorRT engine can be created directly with the serialized .bin file

@ To get more memory, it's recommended to turn-off X-server.




About

Python sample for referencing object detection model with TensorRT

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages