From b89abbc3da73bfca377eb7a1ad284a3b6f81a2e5 Mon Sep 17 00:00:00 2001 From: Feng Ni Date: Tue, 23 Nov 2021 20:56:43 +0800 Subject: [PATCH] [MOT]update pptracking modelzoo readme (#4678) --- configs/mot/fairmot/README.md | 5 +- configs/mot/fairmot/README_cn.md | 4 +- ...fairmot_enhance_hardnet85_30e_1088x608.yml | 56 +++++++++++++++++++ configs/mot/headtracking21/README_cn.md | 4 ++ configs/mot/mcfairmot/README.md | 7 ++- configs/mot/mcfairmot/README_cn.md | 7 ++- ppdet/modeling/necks/centernet_fpn.py | 24 ++++---- 7 files changed, 86 insertions(+), 21 deletions(-) create mode 100644 configs/mot/fairmot/fairmot_enhance_hardnet85_30e_1088x608.yml diff --git a/configs/mot/fairmot/README.md b/configs/mot/fairmot/README.md index b28563fef..f3a9aa8b7 100644 --- a/configs/mot/fairmot/README.md +++ b/configs/mot/fairmot/README.md @@ -42,15 +42,16 @@ English | [简体中文](README_cn.md) | backbone | input shape | MOTA | IDF1 | IDS | FP | FN | FPS | download | config | | :--------------| :------- | :----: | :----: | :----: | :----: | :----: | :------: | :----: |:-----: | | DLA-34 | 1088x608 | 75.9 | 74.7 | 1021 | 11425 | 31475 | - |[model](https://paddledet.bj.bcebos.com/models/mot/fairmot_enhance_dla34_60e_1088x608.pdparams) | [config](./fairmot_enhance_dla34_60e_1088x608.yml) | +| HarDNet-85 | 1088x608 | 75.0 | 70.0 | 1050 | 11837 | 32774 | - |[model](https://paddledet.bj.bcebos.com/models/mot/fairmot_enhance_hardnet85_30e_1088x608.pdparams) | [config](./fairmot_enhance_hardnet85_30e_1088x608.yml) | ### Results on MOT-17 Test Set | backbone | input shape | MOTA | IDF1 | IDS | FP | FN | FPS | download | config | | :--------------| :------- | :----: | :----: | :----: | :----: | :----: | :------: | :----: |:-----: | | DLA-34 | 1088x608 | 75.3 | 74.2 | 3270 | 29112 | 106749 | - |[model](https://paddledet.bj.bcebos.com/models/mot/fairmot_enhance_dla34_60e_1088x608.pdparams) | [config](./fairmot_enhance_dla34_60e_1088x608.yml) | +| HarDNet-85 | 1088x608 | 74.7 | 70.7 | 3210 | 29790 | 109914 | - |[model](https://paddledet.bj.bcebos.com/models/mot/fairmot_enhance_hardnet85_30e_1088x608.pdparams) | [config](./fairmot_enhance_hardnet85_30e_1088x608.yml) | **Notes:** - FairMOT enhance DLA-34 used 8 GPUs for training and mini-batch size as 16 on each GPU，and trained for 60 epoches. The crowdhuman dataset is added to the train-set during training. - + FairMOT enhance used 8 GPUs for training, and the crowdhuman dataset is added to the train-set during training. For FairMOT enhance DLA-34 the batch size is 16 on each GPU，and trained for 60 epoches. For FairMOT enhance HarDNet-85 the batch size is 10 on each GPU，and trained for 30 epoches. ### FairMOT light model ### Results on MOT-16 Test Set diff --git a/configs/mot/fairmot/README_cn.md b/configs/mot/fairmot/README_cn.md index e411256de..956109b76 100644 --- a/configs/mot/fairmot/README_cn.md +++ b/configs/mot/fairmot/README_cn.md @@ -41,14 +41,16 @@ | 骨干网络 | 输入尺寸 | MOTA | IDF1 | IDS | FP | FN | FPS | 下载链接 | 配置文件 | | :--------------| :------- | :----: | :----: | :----: | :----: | :----: | :------: | :----: |:-----: | | DLA-34 | 1088x608 | 75.9 | 74.7 | 1021 | 11425 | 31475 | - |[下载链接](https://paddledet.bj.bcebos.com/models/mot/fairmot_enhance_dla34_60e_1088x608.pdparams) | [配置文件](./fairmot_enhance_dla34_60e_1088x608.yml) | +| HarDNet-85 | 1088x608 | 75.0 | 70.0 | 1050 | 11837 | 32774 | - |[下载链接](https://paddledet.bj.bcebos.com/models/mot/fairmot_enhance_hardnet85_30e_1088x608.pdparams) | [配置文件](./fairmot_enhance_hardnet85_30e_1088x608.yml) | ### 在MOT-17 Test Set上结果 | 骨干网络 | 输入尺寸 | MOTA | IDF1 | IDS | FP | FN | FPS | 下载链接 | 配置文件 | | :--------------| :------- | :----: | :----: | :----: | :----: | :----: | :------: | :----: |:-----: | | DLA-34 | 1088x608 | 75.3 | 74.2 | 3270 | 29112 | 106749 | - |[下载链接](https://paddledet.bj.bcebos.com/models/mot/fairmot_enhance_dla34_60e_1088x608.pdparams) | [配置文件](./fairmot_enhance_dla34_60e_1088x608.yml) | +| HarDNet-85 | 1088x608 | 74.7 | 70.7 | 3210 | 29790 | 109914 | - |[下载链接](https://paddledet.bj.bcebos.com/models/mot/fairmot_enhance_hardnet85_30e_1088x608.pdparams) | [配置文件](./fairmot_enhance_hardnet85_30e_1088x608.yml) | **注意:** - FairMOT enhance DLA-34使用8个GPU进行训练，每个GPU上batch size为16，训练60个epoch，并且训练集中加入了crowdhuman数据集一起参与训练。 + FairMOT enhance模型均使用8个GPU进行训练，训练集中加入了crowdhuman数据集一起参与训练。DLA-34骨干网络的每个GPU上batch size为16，训练60个epoch。HarDNet-85骨干网络的每个GPU上batch size为10，训练30个epoch。 ### FairMOT轻量级模型 diff --git a/configs/mot/fairmot/fairmot_enhance_hardnet85_30e_1088x608.yml b/configs/mot/fairmot/fairmot_enhance_hardnet85_30e_1088x608.yml new file mode 100644 index 000000000..c03976510 --- /dev/null +++ b/configs/mot/fairmot/fairmot_enhance_hardnet85_30e_1088x608.yml @@ -0,0 +1,56 @@ +_BASE_: [ + '../../datasets/mot.yml', + '../../runtime.yml', + '_base_/optimizer_30e.yml', + '_base_/fairmot_enhance_hardnet85.yml', + '_base_/fairmot_reader_1088x608.yml', +] +norm_type: sync_bn +use_ema: true +ema_decay: 0.9998 + +# add crowdhuman +TrainDataset: + !MOTDataSet + dataset_dir: dataset/mot + image_lists: ['mot17.train', 'caltech.all', 'cuhksysu.train', 'prw.train', 'citypersons.train', 'eth.train', 'crowdhuman.train', 'crowdhuman.val'] + data_fields: ['image', 'gt_bbox', 'gt_class', 'gt_ide'] + +worker_num: 4 +TrainReader: + inputs_def: + image_shape: [3, 608, 1088] + sample_transforms: + - Decode: {} + - RGBReverse: {} + - AugmentHSV: {} + - LetterBoxResize: {target_size: [608, 1088]} + - MOTRandomAffine: {reject_outside: False} + - RandomFlip: {} + - BboxXYXY2XYWH: {} + - NormalizeBox: {} + - NormalizeImage: {mean: [0, 0, 0], std: [1, 1, 1]} + - RGBReverse: {} + - Permute: {} + batch_transforms: + - Gt2FairMOTTarget: {} + batch_size: 10 + shuffle: True + drop_last: True + use_shared_memory: True + +epoch: 30 +LearningRate: + base_lr: 0.0001 + schedulers: + - !PiecewiseDecay + gamma: 0.1 + milestones: [20,] + use_warmup: False + +OptimizerBuilder: + optimizer: + type: Adam + regularizer: NULL + +weights: output/fairmot_enhance_hardnet85_30e_1088x608/model_final diff --git a/configs/mot/headtracking21/README_cn.md b/configs/mot/headtracking21/README_cn.md index 78cdc833f..550afa0e6 100644 --- a/configs/mot/headtracking21/README_cn.md +++ b/configs/mot/headtracking21/README_cn.md @@ -14,14 +14,18 @@ | 骨干网络 | 输入尺寸 | MOTA | IDF1 | IDS | FP | FN | FPS | 下载链接 | 配置文件 | | :--------------| :------- | :----: | :----: | :---: | :----: | :---: | :------: | :----: |:----: | | DLA-34 | 1088x608 | 64.7 | 69.0 | 8533 | 148817 | 234970 | - | [下载链接](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_1088x608_headtracking21.pdparams) | [配置文件](./fairmot_dla34_30e_1088x608_headtracking21.yml) | +| HRNetv2-W18 | 1088x608 | 57.2 | 58.4 | 30950 | 188260 | 256580 | - | [下载链接](https://paddledet.bj.bcebos.com/models/mot/fairmot_hrnetv2_w18_dlafpn_30e_1088x608_headtracking21.pdparams) | [配置文件](./fairmot_hrnetv2_w18_dlafpn_30e_1088x608_headtracking21.yml) | + ### FairMOT在HT-21 Test Set上结果 | 骨干网络 | 输入尺寸 | MOTA | IDF1 | IDS | FP | FN | FPS | 下载链接 | 配置文件 | | :--------------| :------- | :----: | :----: | :----: | :----: | :----: |:-------: | :----: | :----: | | DLA-34 | 1088x608 | 60.8 | 62.8 | 12781 | 118109 | 198896 | - | [下载链接](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_1088x608_headtracking21.pdparams) | [配置文件](./fairmot_dla34_30e_1088x608_headtracking21.yml) | +| HRNetv2-W18 | 1088x608 | 41.2 | 47.1 | 48809 | 241683 | 204346 | - | [下载链接](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_1088x608_headtracking21.pdparams) | [配置文件](./fairmot_dla34_30e_1088x608_headtracking21.yml) | **注意:** FairMOT DLA-34使用2个GPU进行训练，每个GPU上batch size为6，训练30个epoch。目前MOTA精度位于MOT官网[Head Tracking 21](https://motchallenge.net/results/Head_Tracking_21)榜单榜首。 + FairMOT HRNetv2-W18使用4个GPU进行训练，每个GPU上batch size为8，训练30个epoch。 ## 快速开始 diff --git a/configs/mot/mcfairmot/README.md b/configs/mot/mcfairmot/README.md index 453620b39..97727df04 100644 --- a/configs/mot/mcfairmot/README.md +++ b/configs/mot/mcfairmot/README.md @@ -13,7 +13,7 @@ English | [简体中文](README_cn.md) MCFairMOT is the Multi-class extended version of [FairMOT](https://arxiv.org/abs/2004.01888). ## Model Zoo -### MCFairMOT DLA-34 Results on VisDrone2019 Val Set +### MCFairMOT Results on VisDrone2019 Val Set | backbone | input shape | MOTA | IDF1 | IDS | FPS | download | config | | :--------------| :------- | :----: | :----: | :---: | :------: | :----: |:----: | | DLA-34 | 1088x608 | 24.3 | 41.6 | 2314 | - |[model](https://paddledet.bj.bcebos.com/models/mot/mcfairmot_dla34_30e_1088x608_visdrone.pdparams) | [config](./mcfairmot_dla34_30e_1088x608_visdrone.yml) | @@ -23,14 +23,15 @@ MCFairMOT is the Multi-class extended version of [FairMOT](https://arxiv.org/abs **Notes:** MOTA is the average MOTA of 10 catecories in the VisDrone2019 MOT dataset, and its value is also equal to the average MOTA of all the evaluated video sequences. + MCFairMOT used 4 GPUs for training 30 epoches. The batch size is 6 on each GPU for MCFairMOT DLA-34, and 4 for MCFairMOT HRNetV2-W18. ## Getting Start ### 1. Training -Training MCFairMOT on 8 GPUs with following command +Training MCFairMOT on 4 GPUs with following command ```bash -python -m paddle.distributed.launch --log_dir=./mcfairmot_dla34_30e_1088x608_visdrone/ --gpus 0,1,2,3,4,5,6,7 tools/train.py -c configs/mot/mcfairmot/mcfairmot_dla34_30e_1088x608_visdrone.yml +python -m paddle.distributed.launch --log_dir=./mcfairmot_dla34_30e_1088x608_visdrone/ --gpus 0,1,2,3 tools/train.py -c configs/mot/mcfairmot/mcfairmot_dla34_30e_1088x608_visdrone.yml ``` ### 2. Evaluation diff --git a/configs/mot/mcfairmot/README_cn.md b/configs/mot/mcfairmot/README_cn.md index d157cd332..55a6bff70 100644 --- a/configs/mot/mcfairmot/README_cn.md +++ b/configs/mot/mcfairmot/README_cn.md @@ -14,7 +14,7 @@ MCFairMOT是[FairMOT](https://arxiv.org/abs/2004.01888)的多类别扩展版本 ## 模型库 -### MCFairMOT DLA-34 在VisDrone2019 MOT val-set上结果 +### MCFairMOT 在VisDrone2019 MOT val-set上结果 | 骨干网络 | 输入尺寸 | MOTA | IDF1 | IDS | FPS | 下载链接 | 配置文件 | | :--------------| :------- | :----: | :----: | :---: | :------: | :----: |:----: | | DLA-34 | 1088x608 | 24.3 | 41.6 | 2314 | - |[下载链接](https://paddledet.bj.bcebos.com/models/mot/mcfairmot_dla34_30e_1088x608_visdrone.pdparams) | [配置文件](./mcfairmot_dla34_30e_1088x608_visdrone.yml) | @@ -24,13 +24,14 @@ MCFairMOT是[FairMOT](https://arxiv.org/abs/2004.01888)的多类别扩展版本 **注意:** MOTA是VisDrone2019 MOT数据集10类目标的平均MOTA, 其值也等于所有评估的视频序列的平均MOTA。 + MCFairMOT enhance模型均使用4个GPU进行训练，训练30个epoch。DLA-34骨干网络的每个GPU上batch size为6，HRNetV2-W18骨干网络的每个GPU上batch size为4。 ## 快速开始 ### 1. 训练 -使用8个GPU通过如下命令一键式启动训练 +使用4个GPU通过如下命令一键式启动训练 ```bash -python -m paddle.distributed.launch --log_dir=./mcfairmot_dla34_30e_1088x608_visdrone/ --gpus 0,1,2,3,4,5,6,7 tools/train.py -c configs/mot/mcfairmot/mcfairmot_dla34_30e_1088x608_visdrone.yml +python -m paddle.distributed.launch --log_dir=./mcfairmot_dla34_30e_1088x608_visdrone/ --gpus 0,1,2,3 tools/train.py -c configs/mot/mcfairmot/mcfairmot_dla34_30e_1088x608_visdrone.yml ``` ### 2. 评估 diff --git a/ppdet/modeling/necks/centernet_fpn.py b/ppdet/modeling/necks/centernet_fpn.py index 9f2bb04b8..df5ced2e7 100755 --- a/ppdet/modeling/necks/centernet_fpn.py +++ b/ppdet/modeling/necks/centernet_fpn.py @@ -283,11 +283,10 @@ class TransitionUp(nn.Layer): def __init__(self, in_channels, out_channels): super().__init__() - def forward(self, x, skip, concat=True): + def forward(self, x, skip): w, h = skip.shape[2], skip.shape[3] out = F.interpolate(x, size=(w, h), mode="bilinear", align_corners=True) - if concat: - out = paddle.concat([out, skip], 1) + out = paddle.concat([out, skip], 1) return out @@ -391,16 +390,17 @@ class CenterNetHarDNetFPN(nn.Layer): for i in range(3): skip_x = body_feats[3 - i] - x = self.transUpBlocks[i](x, skip_x, (i < self.skip_lv)) - x = self.conv1x1_up[i](x) + x_up = self.transUpBlocks[i](x, skip_x) + x_ch = self.conv1x1_up[i](x_up) if self.SC[i] > 0: - end = x.shape[1] - x_sc.append(x[:, end - self.SC[i]:, :, :]) - x = x[:, :end - self.SC[i], :, :] - x2 = self.avg9x9(x) - x3 = x / (x.sum((2, 3), keepdim=True) + 0.1) - x = paddle.concat([x, x2, x3], 1) - x = self.denseBlocksUp[i](x) + end = x_ch.shape[1] + new_st = end - self.SC[i] + x_sc.append(x_ch[:, new_st:, :, :]) + x_ch = x_ch[:, :new_st, :, :] + x2 = self.avg9x9(x_ch) + x3 = x_ch / (x_ch.sum((2, 3), keepdim=True) + 0.1) + x_new = paddle.concat([x_ch, x2, x3], 1) + x = self.denseBlocksUp[i](x_new) scs = [x] for i in range(3): -- GitLab