diff --git a/deploy/pipeline/config/infer_cfg_pphuman.yml b/deploy/pipeline/config/infer_cfg_pphuman.yml index 6317c26724b2b005145f9727dd9a56d209faa752..2e91a4bff9453fed3943b9d1728028c55dadf642 100644 --- a/deploy/pipeline/config/infer_cfg_pphuman.yml +++ b/deploy/pipeline/config/infer_cfg_pphuman.yml @@ -20,7 +20,7 @@ KPT: batch_size: 8 ATTR: - model_dir: output_inference/strongbaseline_r50_30e_pa100k/ + model_dir: output_inference/PPLCNet_x1_0_person_attribute_945_infer/ batch_size: 8 basemode: "idbased" enable: False diff --git a/deploy/pipeline/docs/tutorials/attribute.md b/deploy/pipeline/docs/tutorials/attribute.md index 067a017e7dbdf65ae21eba83dbe4918daef94a0a..299cdf42f5a2993107e6a3b5e684da56cb585c7a 100644 --- a/deploy/pipeline/docs/tutorials/attribute.md +++ b/deploy/pipeline/docs/tutorials/attribute.md @@ -6,21 +6,40 @@ | 任务 | 算法 | 精度 | 预测速度(ms) |下载链接 | |:---------------------|:---------:|:------:|:------:| :---------------------------------------------------------------------------------: | -| 行人属性高精度模型 | PP-HGNet_small | mA: 95.4 | 单人 1.54ms | [下载链接](https://bj.bcebos.com/v1/paddledet/models/pipeline/PPLCNet_x1_0_person_attribute_945_infer.tar) | -| 行人属性快速版模型 | PP-LCNet_x1_0 | mA: 94.5 | 单人 0.54ms | [下载链接](https://bj.bcebos.com/v1/paddledet/models/pipeline/PPLCNet_x1_0_person_attribute_945_infer.tar) | -| 行人属性平衡模型 | PP-HGNet_tiny | mA: 95.2 | 单人 1.14ms | [下载链接](https://bj.bcebos.com/v1/paddledet/models/pipeline/PPHGNet_tiny_person_attribute_952_infer.tar) | +| 行人属性高精度模型 | PP-HGNet_small | mA: 95.4 | 单人 1.54ms | [下载链接](https://bj.bcebos.com/v1/paddledet/models/pipeline/PPHGNet_small_person_attribute_954_infer.tar) | +| 行人属性轻量级模型 | PP-LCNet_x1_0 | mA: 94.5 | 单人 0.54ms | [下载链接](https://bj.bcebos.com/v1/paddledet/models/pipeline/PPLCNet_x1_0_person_attribute_945_infer.tar) | +| 行人属性精度与速度均衡模型 | PP-HGNet_tiny | mA: 95.2 | 单人 1.14ms | [下载链接](https://bj.bcebos.com/v1/paddledet/models/pipeline/PPHGNet_tiny_person_attribute_952_infer.tar) | 1. 行人属性分析精度为[PA100k](https://github.com/xh-liu/HydraPlus-Net#pa-100k-dataset)，[RAPv2](http://www.rapdataset.com/rapv2.html)，[PETA](http://mmlab.ie.cuhk.edu.hk/projects/PETA.html)和部分业务数据融合训练测试得到 -2. 预测速度为V100 机器上使用TensorRT FP16时的速度, 速度包含数据预处理、模型预测、后处理全流程 +2. 预测速度为V100 机器上使用TensorRT FP16时的速度, 该处测速速度为模型预测速度 +3. 属性模型应用依赖跟踪模型结果，请在[跟踪模型页面](./mot.md)下载跟踪模型，依自身需求选择高精或轻量级下载。 +4. 模型下载后解压放置在PaddleDetection/output_inference/目录下。 ## 使用方法 -1. 从上表链接中下载模型并解压到```./output_inference```路径下，并且设置infer_cfg_pphuman.yml中`ATTR`的enable: True +1. 从上表链接中下载模型并解压到```PaddleDetection/output_inference```路径下，并且设置```deploy/pipeline/config/infer_cfg_pphuman.yml```中`ATTR`的enable: True + +`infer_cfg_pphuman.yml`中配置项说明： +``` +ATTR: #模块名称 + model_dir: output_inference/PPLCNet_x1_0_person_attribute_945_infer/ #模型路径 + batch_size: 8 #推理最大batchsize + basemode: "idbased" #流程类型，'idbased'表示基于跟踪模型 + enable: False #功能是否开启 +``` + 2. 图片输入时，启动命令如下 ```python +#单张图片 python deploy/pipeline/pipeline.py --config deploy/pipeline/config/infer_cfg_pphuman.yml \ --image_file=test_image.jpg \ --device=gpu \ + +#图片文件夹 +python deploy/pipeline/pipeline.py --config deploy/pipeline/config/infer_cfg_pphuman.yml \ + --image_dir=images/ \ + --device=gpu \ + ``` 3. 视频输入时，启动命令如下 ```python @@ -28,15 +47,16 @@ python deploy/pipeline/pipeline.py --config deploy/pipeline/config/infer_cfg_pph --video_file=test_video.mp4 \ --device=gpu \ ``` + 4. 若修改模型路径，有以下两种方式： - - ```./deploy/pipeline/config/infer_cfg_pphuman.yml```下可以配置不同模型路径，属性识别模型修改ATTR字段下配置 - - **(推荐)**命令行中增加`--model_dir`修改模型路径： + - 方法一：```./deploy/pipeline/config/infer_cfg_pphuman.yml```下可以配置不同模型路径，属性识别模型修改ATTR字段下配置 + - 方法二：命令行中增加`--model_dir`修改模型路径： ```python python deploy/pipeline/pipeline.py --config deploy/pipeline/config/infer_cfg_pphuman.yml \ --video_file=test_video.mp4 \ --device=gpu \ - --model_dir det=ppyoloe/ + --model_dir attr=output_inference/PPLCNet_x1_0_person_attribute_945_infer/ ``` 测试效果如下： diff --git a/deploy/pipeline/docs/tutorials/attribute_en.md b/deploy/pipeline/docs/tutorials/attribute_en.md index 3d8fab989482ffed72f0d510c7ce21bc485506ba..d77bd0e3e882300c0524df432530202fc6a07a78 100644 --- a/deploy/pipeline/docs/tutorials/attribute_en.md +++ b/deploy/pipeline/docs/tutorials/attribute_en.md @@ -6,21 +6,40 @@ Pedestrian attribute recognition has been widely used in the intelligent communi | Task | Algorithm | Precision | Inference Speed(ms) | Download Link | |:---------------------|:---------:|:------:|:------:| :---------------------------------------------------------------------------------: | -| High-Precision Model | PP-HGNet_small | mA: 95.4 | per person 1.54ms | [Download](https://bj.bcebos.com/v1/paddledet/models/pipeline/PPLCNet_x1_0_person_attribute_945_infer.tar) | +| High-Precision Model | PP-HGNet_small | mA: 95.4 | per person 1.54ms | [Download](https://bj.bcebos.com/v1/paddledet/models/pipeline/PPHGNet_small_person_attribute_954_infer.tar) | | Fast Model | PP-LCNet_x1_0 | mA: 94.5 | per person 0.54ms | [Download](https://bj.bcebos.com/v1/paddledet/models/pipeline/PPLCNet_x1_0_person_attribute_945_infer.tar) | | Balanced Model | PP-HGNet_tiny | mA: 95.2 | per person 1.14ms | [Download](https://bj.bcebos.com/v1/paddledet/models/pipeline/PPHGNet_tiny_person_attribute_952_infer.tar) | 1. The precision of pedestiran attribute analysis is obtained by training and testing on the dataset consist of [PA100k](https://github.com/xh-liu/HydraPlus-Net#pa-100k-dataset)，[RAPv2](http://www.rapdataset.com/rapv2.html)，[PETA](http://mmlab.ie.cuhk.edu.hk/projects/PETA.html) and some business data. 2. The inference speed is V100, the speed of using TensorRT FP16. +3. This model of Attribute is based on the result of tracking, please download tracking model in the [Page of Mot](./mot_en.md). The High precision and Faster model are both available. +4. You should place the model unziped in the directory of `PaddleDetection/output_inference/`. ## Instruction 1. Download the model from the link in the above table, and unzip it to```./output_inference```, and set the "enable: True" in ATTR of infer_cfg_pphuman.yml + +The meaning of configs of `infer_cfg_pphuman.yml`： +``` +ATTR: #module name + model_dir: output_inference/PPLCNet_x1_0_person_attribute_945_infer/ #model path + batch_size: 8 #maxmum batchsize when inference + basemode: "idbased" #the routing type of pipeline，'idbased' means this model is based on tracking. + enable: False #whether to enable this model +``` + 2. When inputting the image, run the command as follows: ```python +#single image python deploy/pipeline/pipeline.py --config deploy/pipeline/config/infer_cfg_pphuman.yml \ --image_file=test_image.jpg \ --device=gpu \ + +#image directory +python deploy/pipeline/pipeline.py --config deploy/pipeline/config/infer_cfg_pphuman.yml \ + --image_dir=images/ \ + --device=gpu \ + ``` 3. When inputting the video, run the command as follows: ```python @@ -30,13 +49,13 @@ python deploy/pipeline/pipeline.py --config deploy/pipeline/config/infer_cfg_pph ``` 4. If you want to change the model path, there are two methods： - - In ```./deploy/pipeline/config/infer_cfg_pphuman.yml``` you can configurate different model paths. In attribute recognition models, you can modify the configuration in the field of ATTR. - - Add `--model_dir` in the command line to change the model path： + - The first: In ```./deploy/pipeline/config/infer_cfg_pphuman.yml``` you can configurate different model paths. In attribute recognition models, you can modify the configuration in the field of ATTR. + - The second: Add `--model_dir` in the command line to change the model path： ```python python deploy/pipeline/pipeline.py --config deploy/pipeline/config/infer_cfg_pphuman.yml \ --video_file=test_video.mp4 \ --device=gpu \ - --model_dir det=ppyoloe/ + --model_dir attr=output_inference/PPLCNet_x1_0_person_attribute_945_infer/ ``` The test result is： diff --git a/deploy/pipeline/pipeline.py b/deploy/pipeline/pipeline.py index 70322194929d4d4c40650855eb0fcbbea37efe40..ef56e622da977c9b3e3ea785bef9475de86e081a 100644 --- a/deploy/pipeline/pipeline.py +++ b/deploy/pipeline/pipeline.py @@ -444,6 +444,17 @@ class PipePredictor(object): trt_max_shape, trt_opt_shape, trt_calib_mode, cpu_threads, enable_mkldnn, color_threshold, type_threshold) + if self.with_mtmct: + reid_cfg = self.cfg['REID'] + model_dir = reid_cfg['model_dir'] + batch_size = reid_cfg['batch_size'] + basemode = reid_cfg['basemode'] + self.modebase[basemode] = True + self.reid_predictor = ReID( + model_dir, device, run_mode, batch_size, trt_min_shape, + trt_max_shape, trt_opt_shape, trt_calib_mode, cpu_threads, + enable_mkldnn) + if self.with_mot or self.modebase["idbased"] or self.modebase[ "skeletonbased"]: mot_cfg = self.cfg['MOT'] @@ -493,15 +504,6 @@ class PipePredictor(object): cpu_threads=cpu_threads, enable_mkldnn=enable_mkldnn) - if self.with_mtmct: - reid_cfg = self.cfg['REID'] - model_dir = reid_cfg['model_dir'] - batch_size = reid_cfg['batch_size'] - self.reid_predictor = ReID( - model_dir, device, run_mode, batch_size, trt_min_shape, - trt_max_shape, trt_opt_shape, trt_calib_mode, cpu_threads, - enable_mkldnn) - def set_file_name(self, path): if path is not None: self.file_name = os.path.split(path)[-1] diff --git a/deploy/pipeline/pphuman/mtmct.py b/deploy/pipeline/pphuman/mtmct.py index 721008f638b543c9f276c0e86877ecbe32eb2c46..d873794a7994d13aa4fa347148ad95164051edbe 100644 --- a/deploy/pipeline/pphuman/mtmct.py +++ b/deploy/pipeline/pphuman/mtmct.py @@ -329,6 +329,9 @@ def res2dict(multi_res): def mtmct_process(multi_res, captures, mtmct_vis=True, output_dir="output"): cid_tid_dict = res2dict(multi_res) + if len(cid_tid_dict) == 0: + print("no tracking result found, mtmct will be skiped.") + return map_tid = sub_cluster(cid_tid_dict) if not os.path.exists(output_dir): diff --git a/docs/advanced_tutorials/customization/attribute.md b/docs/advanced_tutorials/customization/attribute.md index 763ee1359d7a3929a82fed6b908973830d9b6818..15dcefb8e53916b8d118852defff54a507ed2716 100644 --- a/docs/advanced_tutorials/customization/attribute.md +++ b/docs/advanced_tutorials/customization/attribute.md @@ -70,36 +70,61 @@ train.txt文件内为所有训练图片名称（相对于根路径的文件路 00001.jpg 0,0,1,0,.... ``` -注意：图片与标注值之间是以Tab[\t]符号隔开, 标注值之间是以逗号[,]隔开。该格式不能错，否则解析失败。 +注意：1)图片与标注值之间是以Tab[\t]符号隔开, 2)标注值之间是以逗号[,]隔开。该格式不能错，否则解析失败。 ### 修改配置开始训练 -该任务的训练功能集成在[PaddleClas](https://github.com/PaddlePaddle/PaddleClas)套件中。 +首先执行以下命令下载训练代码： -需要在配置文件[PPLCNet_x1_0.yaml](https://github.com/PaddlePaddle/PaddleClas/blob/develop/ppcls/configs/PULC/person_attribute/PPLCNet_x1_0.yaml)中，修改的配置项如下： +```shell +git clone https://github.com/PaddlePaddle/PaddleClas +``` + +需要在配置文件`PaddleClas/blob/develop/ppcls/configs/PULC/person_attribute/PPLCNet_x1_0.yaml`中，修改的配置项如下： ``` - image_root: "dataset/attribute/data/" 指定训练图片所在根路径 - cls_label_path: "dataset/attribute/trainval.txt" 指定训练列表文件位置 +DataLoader: + Train: + dataset: + name: MultiLabelDataset + image_root: "dataset/pa100k/" #指定训练图片所在根路径 + cls_label_path: "dataset/pa100k/train_list.txt" #指定训练列表文件位置 + label_ratio: True + transform_ops: + + Eval: + dataset: + name: MultiLabelDataset + image_root: "dataset/pa100k/" #指定评估图片所在根路径 + cls_label_path: "dataset/pa100k/val_list.txt" #指定评估列表文件位置 + label_ratio: True + transform_ops: ``` 注意： - -1. 这里image_root路径+train.txt中图片相对路径，对应图片存放的完整路径。 - -如果有修改属性数量，则还需修改内容配置项： - +1. 这里image_root路径+train.txt中图片相对路径，对应图片的完整路径位置。 +2. 如果有修改属性数量，则还需修改内容配置项中属性种类数量： ``` - class_num: 26 #属性种类数量 +# model architecture +Arch: + name: "PPLCNet_x1_0" + pretrained: True + use_ssld: True + class_num: 26 #属性种类数量 ``` 然后运行以下命令开始训练。 ``` +#多卡训练 export CUDA_VISIBLE_DEVICES=0,1,2,3 python3 -m paddle.distributed.launch \ --gpus="0,1,2,3" \ tools/train.py \ -c ./ppcls/configs/PULC/person_attribute/PPLCNet_x1_0.yaml + +#单卡训练 +python3 tools/train.py \ + -c ./ppcls/configs/PULC/person_attribute/PPLCNet_x1_0.yaml ``` ### 模型导出 @@ -113,23 +138,34 @@ python3 tools/export_model.py \ -o Global.save_inference_dir=deploy/models/PPLCNet_x1_0_person_attribute_infer ``` -导出模型后，然后将PP-Human中提供的部署模型[PPLCNet_x1_0](https://bj.bcebos.com/v1/paddledet/models/pipeline/PPLCNet_x1_0_person_attribute_945_infer.tar)中的infer_cfg.yml文件拷贝到导出的模型文件夹'PPLCNet_x1_0_person_attribute_infer'中。 +导出模型后，将PP-Human中提供的部署模型[PPLCNet_x1_0](https://bj.bcebos.com/v1/paddledet/models/pipeline/PPLCNet_x1_0_person_attribute_945_infer.tar)中的`infer_cfg.yml`文件拷贝到导出的模型文件夹`PPLCNet_x1_0_person_attribute_infer`中。 -使用时在PP-Human中的配置文件infer_cfg_pphuman.yml中修改 +使用时在PP-Human中的配置文件`./deploy/pipeline/config/infer_cfg_pphuman.yml`中修改新的模型路径 ``` ATTR: - model_dir: [YOUR_DEPLOY_MODEL_DIR]/PPLCNet_x1_0_person_attribute_infer/ - enable: True + model_dir: [YOUR_DEPLOY_MODEL_DIR]/PPLCNet_x1_0_person_attribute_infer/ #新导出的模型路径位置 + enable: True #开启功能 ``` -然后可以使用。 +然后可以使用-->至此即完成新增属性类别识别任务。 ## 属性增减 上述是以26个属性为例的标注、训练过程。 -如果需要增加、减少属性数量，则只需修改1)标注、2)训练中train.txt所使用的属性数量和名称。 +如果需要增加、减少属性数量，则需要： +1)标注时需增加新属性类别信息或删减属性类别信息； +2)对应修改训练中train.txt所使用的属性数量和名称； +3)修改训练配置，例如``PaddleClas/blob/develop/ppcls/configs/PULC/person_attribute/PPLCNet_x1_0.yaml``文件中的属性数量,详细见上述`修改配置开始训练`部分。 + +增加属性示例： -删减属性，例如，如果不需要年龄属性，则位置[1,2,3]的数值可以去掉。只需在train.txt中标注的26个数字中全部删除第1-3位数值即可，同时标注数据时也不再需要标注这3位属性值。 +1. 在标注数据时在26位后继续增加新的属性标注数值； +2. 在train.txt文件的标注数值中也增加新的属性数值。 +3. 注意属性类型在train.txt中属性数值列表中的位置的对应关系需要时固定的，例如第1-3位表示年龄，所有图片都要使用1-3位置表示年龄，不再赘述。 -同理进行增加属性，在标注数据时在26位后继续增加新的属性标注数值，在train.txt文件的标注数值中也增加新的属性数值。注意属性类型在train.txt中属性数值列表中的位置的对应关系需要时固定的，例如第1-3位表示年龄，所有图片都要使用1-3位置表示年龄，不再赘述。 +
+ +
+删减属性同理。 +例如，如果不需要年龄属性，则位置[1,2,3]的数值可以去掉。只需在train.txt中标注的26个数字中全部删除第1-3位数值即可，同时标注数据时也不再需要标注这3位属性值。 diff --git a/docs/images/add_attribute.png b/docs/images/add_attribute.png new file mode 100644 index 0000000000000000000000000000000000000000..1d6092c4a3f778f08b0636875bdcb30a51d0655d Binary files /dev/null and b/docs/images/add_attribute.png differ