15ad234a7a
* [Fix] Fix example standalone build for msvc (#1626) * fix example build for msvc * move /Zc:__cplusplus to core * [FIX] Fix csharp net48 and batch inference (#1370) * fix csharp net48 * add missing file * update * fix batch inference * update demo * update * update version * update nuget package version & fix project name * build monolithic SDK by default (#1577) * Fix debug build for PoseTracker (#1601) * [Fix] Fix aligned allocations on Android (#1612) * fix android alignment * fix typo * fix size * Fix build error on windows-cuda platform (#1598) * [Fix] Relax module adapter template constraints (#1366) * relax module adapter constraint * remove forwarding `operator()` * fix YOLOV5Head naming Co-authored-by: Li Zhang <lzhang329@gmail.com> |
||
|---|---|---|
| .. | ||
| csharp | ||
| csrc | ||
| java | ||
| python | ||
| resources | ||
| tutorials | ||
| README.md | ||
| 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 |
|---|---|
 |
 |