更换文档检测模型
This commit is contained in:
190
paddle_detection/configs/yolox/README.md
Normal file
190
paddle_detection/configs/yolox/README.md
Normal file
@@ -0,0 +1,190 @@
|
||||
# YOLOX (YOLOX: Exceeding YOLO Series in 2021)
|
||||
|
||||
## 内容
|
||||
- [模型库](#模型库)
|
||||
- [使用说明](#使用说明)
|
||||
- [速度测试](#速度测试)
|
||||
- [引用](#引用)
|
||||
|
||||
|
||||
## 模型库
|
||||
### YOLOX on COCO
|
||||
|
||||
| 网络网络 | 输入尺寸 | 图片数/GPU | 学习率策略 | 模型推理耗时(ms) | mAP<sup>val<br>0.5:0.95 | mAP<sup>val<br>0.5 | Params(M) | FLOPs(G) | 下载链接 | 配置文件 |
|
||||
| :------------- | :------- | :-------: | :------: | :------------: | :---------------------: | :----------------: |:---------: | :------: |:---------------: |:-----: |
|
||||
| YOLOX-nano | 416 | 8 | 300e | 2.3 | 26.1 | 42.0 | 0.91 | 1.08 | [下载链接](https://paddledet.bj.bcebos.com/models/yolox_nano_300e_coco.pdparams) | [配置文件](./yolox_nano_300e_coco.yml) |
|
||||
| YOLOX-tiny | 416 | 8 | 300e | 2.8 | 32.9 | 50.4 | 5.06 | 6.45 | [下载链接](https://paddledet.bj.bcebos.com/models/yolox_tiny_300e_coco.pdparams) | [配置文件](./yolox_tiny_300e_coco.yml) |
|
||||
| YOLOX-s | 640 | 8 | 300e | 3.0 | 40.4 | 59.6 | 9.0 | 26.8 | [下载链接](https://paddledet.bj.bcebos.com/models/yolox_s_300e_coco.pdparams) | [配置文件](./yolox_s_300e_coco.yml) |
|
||||
| YOLOX-m | 640 | 8 | 300e | 5.8 | 46.9 | 65.7 | 25.3 | 73.8 | [下载链接](https://paddledet.bj.bcebos.com/models/yolox_m_300e_coco.pdparams) | [配置文件](./yolox_m_300e_coco.yml) |
|
||||
| YOLOX-l | 640 | 8 | 300e | 9.3 | 50.1 | 68.8 | 54.2 | 155.6 | [下载链接](https://paddledet.bj.bcebos.com/models/yolox_l_300e_coco.pdparams) | [配置文件](./yolox_l_300e_coco.yml) |
|
||||
| YOLOX-x | 640 | 8 | 300e | 16.6 | **51.8** | **70.6** | 99.1 | 281.9 | [下载链接](https://paddledet.bj.bcebos.com/models/yolox_x_300e_coco.pdparams) | [配置文件](./yolox_x_300e_coco.yml) |
|
||||
|
||||
|
||||
| 网络网络 | 输入尺寸 | 图片数/GPU | 学习率策略 | 模型推理耗时(ms) | mAP<sup>val<br>0.5:0.95 | mAP<sup>val<br>0.5 | Params(M) | FLOPs(G) | 下载链接 | 配置文件 |
|
||||
| :------------- | :------- | :-------: | :------: | :------------: | :---------------------: | :----------------: |:---------: | :------: |:---------------: |:-----: |
|
||||
| YOLOX-cdn-tiny | 416 | 8 | 300e | 1.9 | 32.4 | 50.2 | 5.03 | 6.33 | [下载链接](https://paddledet.bj.bcebos.com/models/yolox_cdn_tiny_300e_coco.pdparams) | [配置文件](./yolox_cdn_tiny_300e_coco.yml) |
|
||||
| YOLOX-crn-s | 640 | 8 | 300e | 3.0 | 40.4 | 59.6 | 7.7 | 24.69 | [下载链接](https://paddledet.bj.bcebos.com/models/yolox_crn_s_300e_coco.pdparams) | [配置文件](./yolox_crn_s_300e_coco.yml) |
|
||||
| YOLOX-ConvNeXt-s| 640 | 8 | 36e | - | **44.6** | **65.3** | 36.2 | 27.52 | [下载链接](https://paddledet.bj.bcebos.com/models/yolox_convnext_s_36e_coco.pdparams) | [配置文件](../convnext/yolox_convnext_s_36e_coco.yml) |
|
||||
|
||||
|
||||
**注意:**
|
||||
- YOLOX模型训练使用COCO train2017作为训练集,YOLOX-cdn表示使用与YOLOv5 releases v6.0之后版本相同的主干网络,YOLOX-crn表示使用与PPYOLOE相同的主干网络CSPResNet,YOLOX-ConvNeXt表示使用ConvNeXt作为主干网络;
|
||||
- YOLOX模型训练过程中默认使用8 GPUs进行混合精度训练,默认每卡batch_size为8,默认lr为0.01为8卡总batch_size=64的设置,如果**GPU卡数**或者每卡**batch size**发生了改变,你需要按照公式 **lr<sub>new</sub> = lr<sub>default</sub> * (batch_size<sub>new</sub> * GPU_number<sub>new</sub>) / (batch_size<sub>default</sub> * GPU_number<sub>default</sub>)** 调整学习率;
|
||||
- 为保持高mAP的同时提高推理速度,可以将[yolox_cspdarknet.yml](_base_/yolox_cspdarknet.yml)中的`nms_top_k`修改为`1000`,将`keep_top_k`修改为`100`,将`score_threshold`修改为`0.01`,mAP会下降约0.1~0.2%;
|
||||
- 为快速的demo演示效果,可以将[yolox_cspdarknet.yml](_base_/yolox_cspdarknet.yml)中的`score_threshold`修改为`0.25`,将`nms_threshold`修改为`0.45`,但mAP会下降较多;
|
||||
- YOLOX模型推理速度测试采用单卡V100,batch size=1进行测试,使用**CUDA 10.2**, **CUDNN 7.6.5**,TensorRT推理速度测试使用**TensorRT 6.0.1.8**。
|
||||
- 参考[速度测试](#速度测试)以复现YOLOX推理速度测试结果,速度为**tensorRT-FP16**测速后的最快速度,**不包含数据预处理和模型输出后处理(NMS)**的耗时。
|
||||
- 如果你设置了`--run_benchmark=True`, 你首先需要安装以下依赖`pip install pynvml psutil GPUtil`。
|
||||
|
||||
## 使用教程
|
||||
|
||||
### 1.训练
|
||||
执行以下指令使用混合精度训练YOLOX
|
||||
```bash
|
||||
python -m paddle.distributed.launch --gpus 0,1,2,3,4,5,6,7 tools/train.py -c configs/yolox/yolox_s_300e_coco.yml --amp --eval
|
||||
```
|
||||
**注意:**
|
||||
- `--amp`表示开启混合精度训练以避免显存溢出,`--eval`表示边训边验证。
|
||||
|
||||
### 2.评估
|
||||
执行以下命令在单个GPU上评估COCO val2017数据集
|
||||
```bash
|
||||
CUDA_VISIBLE_DEVICES=0 python tools/eval.py -c configs/yolox/yolox_s_300e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/yolox_s_300e_coco.pdparams
|
||||
```
|
||||
|
||||
### 3.推理
|
||||
使用以下命令在单张GPU上预测图片,使用`--infer_img`推理单张图片以及使用`--infer_dir`推理文件中的所有图片。
|
||||
```bash
|
||||
# 推理单张图片
|
||||
CUDA_VISIBLE_DEVICES=0 python tools/infer.py -c configs/yolox/yolox_s_300e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/yolox_s_300e_coco.pdparams --infer_img=demo/000000014439_640x640.jpg
|
||||
|
||||
# 推理文件中的所有图片
|
||||
CUDA_VISIBLE_DEVICES=0 python tools/infer.py -c configs/yolox/yolox_s_300e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/yolox_s_300e_coco.pdparams --infer_dir=demo
|
||||
```
|
||||
|
||||
### 4.导出模型
|
||||
YOLOX在GPU上推理部署或benchmark测速等需要通过`tools/export_model.py`导出模型。
|
||||
|
||||
当你**使用Paddle Inference但不使用TensorRT**时,运行以下的命令导出模型
|
||||
|
||||
```bash
|
||||
python tools/export_model.py -c configs/yolox/yolox_s_300e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/yolox_s_300e_coco.pdparams
|
||||
```
|
||||
|
||||
当你**使用Paddle Inference且使用TensorRT**时,需要指定`-o trt=True`来导出模型。
|
||||
|
||||
```bash
|
||||
python tools/export_model.py -c configs/yolox/yolox_s_300e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/yolox_s_300e_coco.pdparams trt=True
|
||||
```
|
||||
|
||||
如果你想将YOLOX模型导出为**ONNX格式**,参考
|
||||
[PaddleDetection模型导出为ONNX格式教程](../../deploy/EXPORT_ONNX_MODEL.md),运行以下命令:
|
||||
|
||||
```bash
|
||||
|
||||
# 导出推理模型
|
||||
python tools/export_model.py -c configs/yolox/yolox_s_300e_coco.yml --output_dir=output_inference -o weights=https://paddledet.bj.bcebos.com/models/yolox_s_300e_coco.pdparams
|
||||
|
||||
# 安装paddle2onnx
|
||||
pip install paddle2onnx
|
||||
|
||||
# 转换成onnx格式
|
||||
paddle2onnx --model_dir output_inference/yolox_s_300e_coco --model_filename model.pdmodel --params_filename model.pdiparams --opset_version 11 --save_file yolox_s_300e_coco.onnx
|
||||
```
|
||||
|
||||
**注意:** ONNX模型目前只支持batch_size=1
|
||||
|
||||
|
||||
### 5.推理部署
|
||||
YOLOX可以使用以下方式进行部署:
|
||||
- Paddle Inference [Python](../../deploy/python) & [C++](../../deploy/cpp)
|
||||
- [Paddle-TensorRT](../../deploy/TENSOR_RT.md)
|
||||
- [PaddleServing](https://github.com/PaddlePaddle/Serving)
|
||||
- [PaddleSlim模型量化](../slim)
|
||||
|
||||
运行以下命令导出模型
|
||||
|
||||
```bash
|
||||
python tools/export_model.py -c configs/yolox/yolox_s_300e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/yolox_s_300e_coco.pdparams trt=True
|
||||
```
|
||||
|
||||
**注意:**
|
||||
- trt=True表示**使用Paddle Inference且使用TensorRT**进行测速,速度会更快,默认不加即为False,表示**使用Paddle Inference但不使用TensorRT**进行测速。
|
||||
- 如果是使用Paddle Inference在TensorRT FP16模式下部署,需要参考[Paddle Inference文档](https://www.paddlepaddle.org.cn/inference/master/user_guides/download_lib.html#python),下载并安装与你的CUDA, CUDNN和TensorRT相应的wheel包。
|
||||
|
||||
#### 5.1.Python部署
|
||||
`deploy/python/infer.py`使用上述导出后的Paddle Inference模型用于推理和benchnark测速,如果设置了`--run_benchmark=True`, 首先需要安装以下依赖`pip install pynvml psutil GPUtil`。
|
||||
|
||||
```bash
|
||||
# Python部署推理单张图片
|
||||
python deploy/python/infer.py --model_dir=output_inference/yolox_s_300e_coco --image_file=demo/000000014439_640x640.jpg --device=gpu
|
||||
|
||||
# 推理文件夹下的所有图片
|
||||
python deploy/python/infer.py --model_dir=output_inference/yolox_s_300e_coco --image_dir=demo/ --device=gpu
|
||||
```
|
||||
|
||||
#### 5.2. C++部署
|
||||
`deploy/cpp/build/main`使用上述导出后的Paddle Inference模型用于C++推理部署, 首先按照[docs](../../deploy/cpp/docs)编译安装环境。
|
||||
```bash
|
||||
# C++部署推理单张图片
|
||||
./deploy/cpp/build/main --model_dir=output_inference/yolox_s_300e_coco/ --image_file=demo/000000014439_640x640.jpg --run_mode=paddle --device=GPU --threshold=0.5 --output_dir=cpp_infer_output/yolox_s_300e_coco
|
||||
```
|
||||
|
||||
|
||||
## 速度测试
|
||||
|
||||
为了公平起见,在[模型库](#模型库)中的速度测试结果均为不包含数据预处理和模型输出后处理(NMS)的数据(与[YOLOv4(AlexyAB)](https://github.com/AlexeyAB/darknet)测试方法一致),需要在导出模型时指定`-o exclude_nms=True`。测速需设置`--run_benchmark=True`, 首先需要安装以下依赖`pip install pynvml psutil GPUtil`。
|
||||
|
||||
**使用Paddle Inference但不使用TensorRT**进行测速,执行以下命令:
|
||||
|
||||
```bash
|
||||
# 导出模型
|
||||
python tools/export_model.py -c configs/yolox/yolox_s_300e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/yolox_s_300e_coco.pdparams exclude_nms=True
|
||||
|
||||
# 速度测试,使用run_benchmark=True
|
||||
python deploy/python/infer.py --model_dir=output_inference/yolox_s_300e_coco --image_file=demo/000000014439_640x640.jpg --run_mode=paddle --device=gpu --run_benchmark=True
|
||||
```
|
||||
|
||||
**使用Paddle Inference且使用TensorRT**进行测速,执行以下命令:
|
||||
|
||||
```bash
|
||||
# 导出模型,使用trt=True
|
||||
python tools/export_model.py -c configs/yolox/yolox_s_300e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/yolox_s_300e_coco.pdparams exclude_nms=True trt=True
|
||||
|
||||
# 速度测试,使用run_benchmark=True
|
||||
python deploy/python/infer.py --model_dir=output_inference/yolox_s_300e_coco --image_file=demo/000000014439_640x640.jpg --device=gpu --run_benchmark=True
|
||||
|
||||
# tensorRT-FP32测速
|
||||
python deploy/python/infer.py --model_dir=output_inference/yolox_s_300e_coco --image_file=demo/000000014439_640x640.jpg --device=gpu --run_benchmark=True --run_mode=trt_fp32
|
||||
|
||||
# tensorRT-FP16测速
|
||||
python deploy/python/infer.py --model_dir=output_inference/yolox_s_300e_coco --image_file=demo/000000014439_640x640.jpg --device=gpu --run_benchmark=True --run_mode=trt_fp16
|
||||
```
|
||||
**注意:**
|
||||
- 导出模型时指定`-o exclude_nms=True`仅作为测速时用,这样导出的模型其推理部署预测的结果不是最终检出框的结果。
|
||||
- [模型库](#模型库)中的速度测试结果为**tensorRT-FP16**测速后的最快速度,为**不包含数据预处理和模型输出后处理(NMS)**的耗时。
|
||||
|
||||
## FAQ
|
||||
|
||||
<details>
|
||||
<summary>如何计算模型参数量</summary>
|
||||
可以将以下代码插入:[trainer.py](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/ppdet/engine/trainer.py#L154) 来计算参数量。
|
||||
```python
|
||||
params = sum([
|
||||
p.numel() for n, p in self.model.named_parameters()
|
||||
if all([x not in n for x in ['_mean', '_variance']])
|
||||
]) # exclude BatchNorm running status
|
||||
print('Params: ', params)
|
||||
```
|
||||
</details>
|
||||
|
||||
|
||||
## Citations
|
||||
```
|
||||
@article{yolox2021,
|
||||
title={YOLOX: Exceeding YOLO Series in 2021},
|
||||
author={Ge, Zheng and Liu, Songtao and Wang, Feng and Li, Zeming and Sun, Jian},
|
||||
journal={arXiv preprint arXiv:2107.08430},
|
||||
year={2021}
|
||||
}
|
||||
```
|
||||
20
paddle_detection/configs/yolox/_base_/optimizer_300e.yml
Normal file
20
paddle_detection/configs/yolox/_base_/optimizer_300e.yml
Normal file
@@ -0,0 +1,20 @@
|
||||
epoch: 300
|
||||
|
||||
LearningRate:
|
||||
base_lr: 0.01
|
||||
schedulers:
|
||||
- !CosineDecay
|
||||
max_epochs: 300
|
||||
min_lr_ratio: 0.05
|
||||
last_plateau_epochs: 15
|
||||
- !ExpWarmup
|
||||
epochs: 5
|
||||
|
||||
OptimizerBuilder:
|
||||
optimizer:
|
||||
type: Momentum
|
||||
momentum: 0.9
|
||||
use_nesterov: True
|
||||
regularizer:
|
||||
factor: 0.0005
|
||||
type: L2
|
||||
42
paddle_detection/configs/yolox/_base_/yolox_cspdarknet.yml
Normal file
42
paddle_detection/configs/yolox/_base_/yolox_cspdarknet.yml
Normal file
@@ -0,0 +1,42 @@
|
||||
architecture: YOLOX
|
||||
norm_type: sync_bn
|
||||
use_ema: True
|
||||
ema_decay: 0.9999
|
||||
ema_decay_type: "exponential"
|
||||
act: silu
|
||||
find_unused_parameters: True
|
||||
|
||||
depth_mult: 1.0
|
||||
width_mult: 1.0
|
||||
|
||||
YOLOX:
|
||||
backbone: CSPDarkNet
|
||||
neck: YOLOCSPPAN
|
||||
head: YOLOXHead
|
||||
size_stride: 32
|
||||
size_range: [15, 25] # multi-scale range [480*480 ~ 800*800]
|
||||
|
||||
CSPDarkNet:
|
||||
arch: "X"
|
||||
return_idx: [2, 3, 4]
|
||||
depthwise: False
|
||||
|
||||
YOLOCSPPAN:
|
||||
depthwise: False
|
||||
|
||||
YOLOXHead:
|
||||
l1_epoch: 285
|
||||
depthwise: False
|
||||
loss_weight: {cls: 1.0, obj: 1.0, iou: 5.0, l1: 1.0}
|
||||
assigner:
|
||||
name: SimOTAAssigner
|
||||
candidate_topk: 10
|
||||
use_vfl: False
|
||||
nms:
|
||||
name: MultiClassNMS
|
||||
nms_top_k: 10000
|
||||
keep_top_k: 1000
|
||||
score_threshold: 0.001
|
||||
nms_threshold: 0.65
|
||||
# For speed while keep high mAP, you can modify 'nms_top_k' to 1000 and 'keep_top_k' to 100, the mAP will drop about 0.1%.
|
||||
# For high speed demo, you can modify 'score_threshold' to 0.25 and 'nms_threshold' to 0.45, but the mAP will drop a lot.
|
||||
44
paddle_detection/configs/yolox/_base_/yolox_reader.yml
Normal file
44
paddle_detection/configs/yolox/_base_/yolox_reader.yml
Normal file
@@ -0,0 +1,44 @@
|
||||
worker_num: 4
|
||||
TrainReader:
|
||||
sample_transforms:
|
||||
- Decode: {}
|
||||
- Mosaic:
|
||||
prob: 1.0
|
||||
input_dim: [640, 640]
|
||||
degrees: [-10, 10]
|
||||
scale: [0.1, 2.0]
|
||||
shear: [-2, 2]
|
||||
translate: [-0.1, 0.1]
|
||||
enable_mixup: True
|
||||
mixup_prob: 1.0
|
||||
mixup_scale: [0.5, 1.5]
|
||||
- AugmentHSV: {is_bgr: False, hgain: 5, sgain: 30, vgain: 30}
|
||||
- PadResize: {target_size: 640}
|
||||
- RandomFlip: {}
|
||||
batch_transforms:
|
||||
- Permute: {}
|
||||
batch_size: 8
|
||||
shuffle: True
|
||||
drop_last: True
|
||||
collate_batch: False
|
||||
mosaic_epoch: 285
|
||||
|
||||
|
||||
EvalReader:
|
||||
sample_transforms:
|
||||
- Decode: {}
|
||||
- Resize: {target_size: [640, 640], keep_ratio: True, interp: 1}
|
||||
- Pad: {size: [640, 640], fill_value: [114., 114., 114.]}
|
||||
- Permute: {}
|
||||
batch_size: 4
|
||||
|
||||
|
||||
TestReader:
|
||||
inputs_def:
|
||||
image_shape: [3, 640, 640]
|
||||
sample_transforms:
|
||||
- Decode: {}
|
||||
- Resize: {target_size: [640, 640], keep_ratio: True, interp: 1}
|
||||
- Pad: {size: [640, 640], fill_value: [114., 114., 114.]}
|
||||
- Permute: {}
|
||||
batch_size: 1
|
||||
14
paddle_detection/configs/yolox/yolox_cdn_tiny_300e_coco.yml
Normal file
14
paddle_detection/configs/yolox/yolox_cdn_tiny_300e_coco.yml
Normal file
@@ -0,0 +1,14 @@
|
||||
_BASE_: [
|
||||
'yolox_tiny_300e_coco.yml'
|
||||
]
|
||||
depth_mult: 0.33
|
||||
width_mult: 0.375
|
||||
|
||||
log_iter: 100
|
||||
snapshot_epoch: 10
|
||||
weights: output/yolox_cdn_tiny_300e_coco/model_final
|
||||
|
||||
CSPDarkNet:
|
||||
arch: "P5" # using the same backbone of YOLOv5 releases v6.0 and later version
|
||||
return_idx: [2, 3, 4]
|
||||
depthwise: False
|
||||
28
paddle_detection/configs/yolox/yolox_crn_s_300e_coco.yml
Normal file
28
paddle_detection/configs/yolox/yolox_crn_s_300e_coco.yml
Normal file
@@ -0,0 +1,28 @@
|
||||
_BASE_: [
|
||||
'../datasets/coco_detection.yml',
|
||||
'../runtime.yml',
|
||||
'./_base_/optimizer_300e.yml',
|
||||
'./_base_/yolox_cspdarknet.yml',
|
||||
'./_base_/yolox_reader.yml'
|
||||
]
|
||||
depth_mult: 0.33
|
||||
width_mult: 0.50
|
||||
|
||||
log_iter: 100
|
||||
snapshot_epoch: 10
|
||||
weights: output/yolox_crn_s_300e_coco/model_final
|
||||
pretrain_weights: https://paddledet.bj.bcebos.com/models/pretrained/CSPResNetb_s_pretrained.pdparams
|
||||
|
||||
|
||||
YOLOX:
|
||||
backbone: CSPResNet
|
||||
neck: YOLOCSPPAN
|
||||
head: YOLOXHead
|
||||
size_stride: 32
|
||||
size_range: [15, 25] # multi-scale range [480*480 ~ 800*800]
|
||||
|
||||
CSPResNet:
|
||||
layers: [3, 6, 6, 3]
|
||||
channels: [64, 128, 256, 512, 1024]
|
||||
return_idx: [1, 2, 3]
|
||||
use_large_stem: True
|
||||
13
paddle_detection/configs/yolox/yolox_l_300e_coco.yml
Normal file
13
paddle_detection/configs/yolox/yolox_l_300e_coco.yml
Normal file
@@ -0,0 +1,13 @@
|
||||
_BASE_: [
|
||||
'../datasets/coco_detection.yml',
|
||||
'../runtime.yml',
|
||||
'./_base_/optimizer_300e.yml',
|
||||
'./_base_/yolox_cspdarknet.yml',
|
||||
'./_base_/yolox_reader.yml'
|
||||
]
|
||||
depth_mult: 1.0
|
||||
width_mult: 1.0
|
||||
|
||||
log_iter: 100
|
||||
snapshot_epoch: 10
|
||||
weights: output/yolox_l_300e_coco/model_final
|
||||
13
paddle_detection/configs/yolox/yolox_m_300e_coco.yml
Normal file
13
paddle_detection/configs/yolox/yolox_m_300e_coco.yml
Normal file
@@ -0,0 +1,13 @@
|
||||
_BASE_: [
|
||||
'../datasets/coco_detection.yml',
|
||||
'../runtime.yml',
|
||||
'./_base_/optimizer_300e.yml',
|
||||
'./_base_/yolox_cspdarknet.yml',
|
||||
'./_base_/yolox_reader.yml'
|
||||
]
|
||||
depth_mult: 0.67
|
||||
width_mult: 0.75
|
||||
|
||||
log_iter: 100
|
||||
snapshot_epoch: 10
|
||||
weights: output/yolox_m_300e_coco/model_final
|
||||
81
paddle_detection/configs/yolox/yolox_nano_300e_coco.yml
Normal file
81
paddle_detection/configs/yolox/yolox_nano_300e_coco.yml
Normal file
@@ -0,0 +1,81 @@
|
||||
_BASE_: [
|
||||
'../datasets/coco_detection.yml',
|
||||
'../runtime.yml',
|
||||
'./_base_/optimizer_300e.yml',
|
||||
'./_base_/yolox_cspdarknet.yml',
|
||||
'./_base_/yolox_reader.yml'
|
||||
]
|
||||
depth_mult: 0.33
|
||||
width_mult: 0.25
|
||||
|
||||
log_iter: 100
|
||||
snapshot_epoch: 10
|
||||
weights: output/yolox_nano_300e_coco/model_final
|
||||
|
||||
|
||||
### model config:
|
||||
# Note: YOLOX-nano use depthwise conv in backbone, neck and head.
|
||||
YOLOX:
|
||||
backbone: CSPDarkNet
|
||||
neck: YOLOCSPPAN
|
||||
head: YOLOXHead
|
||||
size_stride: 32
|
||||
size_range: [10, 20] # multi-scale range [320*320 ~ 640*640]
|
||||
|
||||
CSPDarkNet:
|
||||
arch: "X"
|
||||
return_idx: [2, 3, 4]
|
||||
depthwise: True
|
||||
|
||||
YOLOCSPPAN:
|
||||
depthwise: True
|
||||
|
||||
YOLOXHead:
|
||||
depthwise: True
|
||||
|
||||
|
||||
### reader config:
|
||||
# Note: YOLOX-tiny/nano uses 416*416 for evaluation and inference.
|
||||
# And multi-scale training setting is in model config, TrainReader's operators use 640*640 as default.
|
||||
worker_num: 4
|
||||
TrainReader:
|
||||
sample_transforms:
|
||||
- Decode: {}
|
||||
- Mosaic:
|
||||
prob: 0.5 # 1.0 in YOLOX-tiny/s/m/l/x
|
||||
input_dim: [640, 640]
|
||||
degrees: [-10, 10]
|
||||
scale: [0.5, 1.5] # [0.1, 2.0] in YOLOX-s/m/l/x
|
||||
shear: [-2, 2]
|
||||
translate: [-0.1, 0.1]
|
||||
enable_mixup: False # True in YOLOX-s/m/l/x
|
||||
- AugmentHSV: {is_bgr: False, hgain: 5, sgain: 30, vgain: 30}
|
||||
- PadResize: {target_size: 640}
|
||||
- RandomFlip: {}
|
||||
batch_transforms:
|
||||
- Permute: {}
|
||||
batch_size: 8
|
||||
shuffle: True
|
||||
drop_last: True
|
||||
collate_batch: False
|
||||
mosaic_epoch: 285
|
||||
|
||||
|
||||
EvalReader:
|
||||
sample_transforms:
|
||||
- Decode: {}
|
||||
- Resize: {target_size: [416, 416], keep_ratio: True, interp: 1}
|
||||
- Pad: {size: [416, 416], fill_value: [114., 114., 114.]}
|
||||
- Permute: {}
|
||||
batch_size: 8
|
||||
|
||||
|
||||
TestReader:
|
||||
inputs_def:
|
||||
image_shape: [3, 416, 416]
|
||||
sample_transforms:
|
||||
- Decode: {}
|
||||
- Resize: {target_size: [416, 416], keep_ratio: True, interp: 1}
|
||||
- Pad: {size: [416, 416], fill_value: [114., 114., 114.]}
|
||||
- Permute: {}
|
||||
batch_size: 1
|
||||
13
paddle_detection/configs/yolox/yolox_s_300e_coco.yml
Normal file
13
paddle_detection/configs/yolox/yolox_s_300e_coco.yml
Normal file
@@ -0,0 +1,13 @@
|
||||
_BASE_: [
|
||||
'../datasets/coco_detection.yml',
|
||||
'../runtime.yml',
|
||||
'./_base_/optimizer_300e.yml',
|
||||
'./_base_/yolox_cspdarknet.yml',
|
||||
'./_base_/yolox_reader.yml'
|
||||
]
|
||||
depth_mult: 0.33
|
||||
width_mult: 0.50
|
||||
|
||||
log_iter: 100
|
||||
snapshot_epoch: 10
|
||||
weights: output/yolox_s_300e_coco/model_final
|
||||
69
paddle_detection/configs/yolox/yolox_tiny_300e_coco.yml
Normal file
69
paddle_detection/configs/yolox/yolox_tiny_300e_coco.yml
Normal file
@@ -0,0 +1,69 @@
|
||||
_BASE_: [
|
||||
'../datasets/coco_detection.yml',
|
||||
'../runtime.yml',
|
||||
'./_base_/optimizer_300e.yml',
|
||||
'./_base_/yolox_cspdarknet.yml',
|
||||
'./_base_/yolox_reader.yml'
|
||||
]
|
||||
depth_mult: 0.33
|
||||
width_mult: 0.375
|
||||
|
||||
log_iter: 100
|
||||
snapshot_epoch: 10
|
||||
weights: output/yolox_tiny_300e_coco/model_final
|
||||
|
||||
|
||||
### model config:
|
||||
YOLOX:
|
||||
backbone: CSPDarkNet
|
||||
neck: YOLOCSPPAN
|
||||
head: YOLOXHead
|
||||
size_stride: 32
|
||||
size_range: [10, 20] # multi-scale ragne [320*320 ~ 640*640]
|
||||
|
||||
|
||||
### reader config:
|
||||
# Note: YOLOX-tiny/nano uses 416*416 for evaluation and inference.
|
||||
# And multi-scale training setting is in model config, TrainReader's operators use 640*640 as default.
|
||||
worker_num: 4
|
||||
TrainReader:
|
||||
sample_transforms:
|
||||
- Decode: {}
|
||||
- Mosaic:
|
||||
prob: 1.0
|
||||
input_dim: [640, 640]
|
||||
degrees: [-10, 10]
|
||||
scale: [0.5, 1.5] # [0.1, 2.0] in YOLOX-s/m/l/x
|
||||
shear: [-2, 2]
|
||||
translate: [-0.1, 0.1]
|
||||
enable_mixup: False # True in YOLOX-s/m/l/x
|
||||
- AugmentHSV: {is_bgr: False, hgain: 5, sgain: 30, vgain: 30}
|
||||
- PadResize: {target_size: 640}
|
||||
- RandomFlip: {}
|
||||
batch_transforms:
|
||||
- Permute: {}
|
||||
batch_size: 8
|
||||
shuffle: True
|
||||
drop_last: True
|
||||
collate_batch: False
|
||||
mosaic_epoch: 285
|
||||
|
||||
|
||||
EvalReader:
|
||||
sample_transforms:
|
||||
- Decode: {}
|
||||
- Resize: {target_size: [416, 416], keep_ratio: True, interp: 1}
|
||||
- Pad: {size: [416, 416], fill_value: [114., 114., 114.]}
|
||||
- Permute: {}
|
||||
batch_size: 8
|
||||
|
||||
|
||||
TestReader:
|
||||
inputs_def:
|
||||
image_shape: [3, 416, 416]
|
||||
sample_transforms:
|
||||
- Decode: {}
|
||||
- Resize: {target_size: [416, 416], keep_ratio: True, interp: 1}
|
||||
- Pad: {size: [416, 416], fill_value: [114., 114., 114.]}
|
||||
- Permute: {}
|
||||
batch_size: 1
|
||||
13
paddle_detection/configs/yolox/yolox_x_300e_coco.yml
Normal file
13
paddle_detection/configs/yolox/yolox_x_300e_coco.yml
Normal file
@@ -0,0 +1,13 @@
|
||||
_BASE_: [
|
||||
'../datasets/coco_detection.yml',
|
||||
'../runtime.yml',
|
||||
'./_base_/optimizer_300e.yml',
|
||||
'./_base_/yolox_cspdarknet.yml',
|
||||
'./_base_/yolox_reader.yml'
|
||||
]
|
||||
depth_mult: 1.33
|
||||
width_mult: 1.25
|
||||
|
||||
log_iter: 100
|
||||
snapshot_epoch: 10
|
||||
weights: output/yolox_x_300e_coco/model_final
|
||||
Reference in New Issue
Block a user