mirror of
https://github.com/open-mmlab/mmdeploy.git
synced 2025-01-14 08:09:43 +08:00
* rename mmdeploy_python -> mmdeploy_runtime * remove incompatible build config * Revert "remove incompatible build config" This reverts commit cdc780cde52c0417e6a5408001fb5ddef1a9498d. * fix builder * update package_tools docs * fix linux set_env script * fix gcc 7.3 aligned_alloc * fix link * comment temporarily as text_det_recog can't be built with prebuild package built under manylinux
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 |
---|---|
![]() |
![]() |