mirrors
/
mmdeploy
mirror of https://github.com/open-mmlab/mmdeploy.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity
mmdeploy/demo
History
RunningLeon c73756366e
bump version to v0.14.0 (#1943) 
* update

* bump version

* Update README.md

* fix conflicts

* fix ci

* fix circleci

* upgrade to ubuntu20.04 for github ci

* update

* install glibc

* try to fix cuda build

* try to fix cuda build

* fix build-cu102 && build_cpu_sdk

* revert to setup-python@v2

* try to fix pplnn

* fix protobuf

---------

Co-authored-by: Xin Chen <irexyc@gmail.com>
 		2023-04-05 14:28:00 +08:00
..
csharp bump version to v0.14.0 (#1943) 2023-04-05 14:28:00 +08:00
csrc [Refactor] Rename mmdeploy_python to mmdeploy_runtime (#1911) 2023-03-29 19:02:37 +08:00
java [Sync] Sync Java API to master (#1856) 2023-03-13 11:31:39 +08:00
python [Refactor] Rename mmdeploy_python to mmdeploy_runtime (#1911) 2023-03-29 19:02:37 +08:00
resources add more images for demos and user guides (#1339) 2022-11-09 21:06:32 +08:00
tutorials
…
README.md [Docs] Replace markdownlint with mdformat and configure myst-parser (#610) 2022-06-17 09:19:10 +08:00
demo_rewrite.py
…

README.md

Demo

We provide a demo showing what our mmdeploy can do for general model deployment.

In demo_rewrite.py, a resnet18 model from torchvision is rewritten through mmdeploy tool. In our rewritten model, the forward function of resnet gets modified to only down sample the original input to 4x. Original onnx model of resnet18 and its rewritten are visualized through netron.

Prerequisite

Before we run demp_rewrite.py, we need to install pyppeteer through:

pip install pyppeteer

Demo results

The original resnet18 model and its modified one are visualized as follows. The left model is the original resnet18 while the right model is exported after rewritten.

Original resnet18 Rewritten model