mirrors/fast-reid
1
0
Fork 0
mirror of https://github.com/JDAI-CV/fast-reid.git synced 2025-06-03 14:50:47 +08:00
Code Issues Projects Releases Wiki Activity

update deploy docs

Browse Source
This commit is contained in:
liaoxingyu 2020-07-29 17:47:35 +08:00
parent 16655448c2
commit a8c7e07df6
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
tools/deploy/README.md
View File

@ -82,7 +82,7 @@ This is a tiny example for converting fastreid-baseline in `meta_arch` to Caffe
--input test_data/*.jpg --output caffe_output --input test_data/*.jpg --output caffe_output
``` ```
6. Run `demo/demo.py` to get fastreid model features with the same input images, then verify that Caffe and PyTorch are computing the same value for the network. 5. Run `demo/demo.py` to get fastreid model features with the same input images, then verify that Caffe and PyTorch are computing the same value for the network.
```python ```python
np.testing.assert_allclose(torch_out, ort_out, rtol=1e-3, atol=1e-6) np.testing.assert_allclose(torch_out, ort_out, rtol=1e-3, atol=1e-6)
@ -127,9 +127,9 @@ This is a tiny example for converting fastreid-baseline in `meta_arch` to ONNX m
<details> <details>
<summary>step-to-step pipeline for trt convert</summary> <summary>step-to-step pipeline for trt convert</summary>
This is a tiny example for converting fastreid-baseline in `meta_arch` to TRT model. We use [tiny-tensorrt](https://github.com/zerollzeng/tiny-tensorrt) which is a simple and easy-to-use nvidia TensorRt warpper, to get the model converted to tensorRT. This is a tiny example for converting fastreid-baseline in `meta_arch` to TRT model. We use [tiny-tensorrt](https://github.com/zerollzeng/tiny-tensorrt), which is a simple and easy-to-use nvidia TensorRT warpper, to get the model converted to tensorRT.
First you need to convert the pytorch model to ONNX format following [ONNX Convert](https://github.com/JDAI-CV/fast-reid#fastreid), and you need to remember your `output` name. Then you can convert ONNX model to TensorRT following instructions below. First you need to convert the pytorch model to ONNX format following [ONNX Convert](https://github.com/JDAI-CV/fast-reid/tree/master/tools/deploy#onnx-convert), and you need to remember your `output` name. Then you can convert ONNX model to TensorRT following instructions below.
1. Run command line below to get the converted TRT model from ONNX model, 1. Run command line below to get the converted TRT model from ONNX model,