Merge branch 'PaddlePaddle:develop' into develop

f67c9b2e · YixinKristy · GitHub · b9554990 · 2cd40bdd · f67c9b2e
23 changed file
--- a/configs/mot/README.md
+++ b/configs/mot/README.md
@@ -47,12 +47,11 @@ PP-Tracking 提供了简洁的GUI可视化界面，教程请参考[PP-Tracking
 ## 安装依赖
 一键安装MOT相关的依赖：
 ```
-pip install lap sklearn motmetrics openpyxl cython_bbox
+pip install lap sklearn motmetrics openpyxl
 或者
 pip install -r requirements.txt
 ```
 **注意：**
- `cython_bbox`在windows上安装：`pip install -e git+https://github.com/samson-wang/cython_bbox.git#egg=cython-bbox`。可参考这个[教程](https://stackoverflow.com/questions/60349980/is-there-a-way-to-install-cython-bbox-for-windows)。
 - 预测需确保已安装[ffmpeg](https://ffmpeg.org/ffmpeg.html), Linux(Ubuntu)平台可以直接用以下命令安装：`apt-get update && apt-get install -y ffmpeg`。



--- a/configs/mot/README_en.md
+++ b/configs/mot/README_en.md
@@ -49,12 +49,11 @@ PP-Tracking supports GUI predict and deployment. Please refer to this [doc](http
 ## Installation
 Install all the related dependencies for MOT:
 ```
-pip install lap sklearn motmetrics openpyxl cython_bbox
+pip install lap sklearn motmetrics openpyxl
 or
 pip install -r requirements.txt
 ```
 **Notes:**
- Install `cython_bbox` for Windows: `pip install -e git+https://github.com/samson-wang/cython_bbox.git#egg=cython-bbox`. You can refer to this [tutorial](https://stackoverflow.com/questions/60349980/is-there-a-way-to-install-cython-bbox-for-windows).
 - Please make sure that [ffmpeg](https://ffmpeg.org/ffmpeg.html) is installed first, on Linux(Ubuntu) platform you can directly install it by the following command:`apt-get update && apt-get install -y ffmpeg`.



--- a/configs/mot/fairmot/README.md
+++ b/configs/mot/fairmot/README.md
@@ -86,7 +86,7 @@ PP-tracking provides an AI studio public project tutorial. Please refer to this
 ### Results on MOT-17 Half Set
 | backbone       | input shape | MOTA | IDF1 |  IDS  |    FP   |   FN   |    FPS    | download | config |
 | :--------------| :------- | :----: | :----: | :----: | :----: | :----: | :------: | :----: |:-----: |
-| DLA-34         | 1088x608 |  69.1  |  72.8  |  299  |  1957  | 14412 |    -     |[model](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_1088x608_bytetracker.pdparams) | [config](./fairmot_dla34_30e_1088x608.yml) |
+| DLA-34         | 1088x608 |  69.1  |  72.8  |  299  |  1957  | 14412 |    -     |[model](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_1088x608.pdparams) | [config](./fairmot_dla34_30e_1088x608.yml) |
 | DLA-34 + BYTETracker| 1088x608 |  70.3 |  73.2  |  234  |  2176  | 13598 |    -     |[model](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_1088x608_bytetracker.pdparams) | [config](./fairmot_dla34_30e_1088x608_bytetracker.yml) |

 **Notes:**

--- a/configs/mot/fairmot/README_cn.md
+++ b/configs/mot/fairmot/README_cn.md
@@ -82,7 +82,7 @@ PP-Tracking 提供了AI Studio公开项目案例，教程请参考[PP-Tracking
 ### 在MOT-17 Half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 |  69.1  |  72.8  |  299  |  1957  | 14412 |    -     |[下载链接](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_1088x608_bytetracker.pdparams) | [配置文件](./fairmot_dla34_30e_1088x608.yml) |
+| DLA-34         | 1088x608 |  69.1  |  72.8  |  299  |  1957  | 14412 |    -     |[下载链接](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_1088x608.pdparams) | [配置文件](./fairmot_dla34_30e_1088x608.yml) |
 | DLA-34 + BYTETracker| 1088x608 |  70.3 |  73.2  |  234  |  2176  | 13598 |    -     |[下载链接](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_1088x608_bytetracker.pdparams) | [配置文件](./fairmot_dla34_30e_1088x608_bytetracker.yml) |



--- a/configs/mot/fairmot/fairmot_dla34_30e_1088x608_bytetracker.yml
+++ b/configs/mot/fairmot/fairmot_dla34_30e_1088x608_bytetracker.yml
@@ -14,8 +14,18 @@ TrainDataset:
    image_lists: ['mot17.half', 'caltech.all', 'cuhksysu.train', 'prw.train', 'citypersons.train', 'eth.train']
    data_fields: ['image', 'gt_bbox', 'gt_class', 'gt_ide']

+# for MOT evaluation
+# If you want to change the MOT evaluation dataset, please modify 'data_root'
+EvalMOTDataset:
+  !MOTImageFolder
+    dataset_dir: dataset/mot
+    data_root: MOT17/images/half
+    keep_ori_im: False # set True if save visualization images or video, or used in DeepSORT
+
 JDETracker:
  use_byte: True
  match_thres: 0.8
  conf_thres: 0.4
  low_conf_thres: 0.2
+  min_box_area: 200
+  vertical_ratio: 1.6 # for pedestrian
--- a/configs/mot/pedestrian/README_cn.md
+++ b/configs/mot/pedestrian/README_cn.md
@@ -18,7 +18,7 @@
 | :-------------| :-------- | :------- | :----: | :----: | :----: | :-----: |:------: |
 |  PathTrack    |   DLA-34  | 1088x608 |  44.9 |    59.3   |    -   |[下载链接](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_1088x608_pathtrack.pdparams) | [配置文件](./fairmot_dla34_30e_1088x608_pathtrack.yml) |
 |  VisDrone     |   DLA-34  | 1088x608 |  49.2 |   63.1 |    -   | [下载链接](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_1088x608_visdrone_pedestrian.pdparams) | [配置文件](./fairmot_dla34_30e_1088x608_visdrone_pedestrian.yml) |
-|  VisDrone     | HRNetv2-W18| 1088x608 |  40.5 |   54.7 |    -   | [下载链接](https://paddledet.bj.bcebos.com/models/mot/fairmot_hrnetv2_w18_dlafpn_30e_864x480_visdrone_pedestrian.pdparams) | [配置文件](./fairmot_hrnetv2_w18_dlafpn_30e_864x480_visdrone_pedestrian.yml) |
+|  VisDrone     | HRNetv2-W18| 1088x608 |  40.5 |   54.7 |    -   | [下载链接](https://paddledet.bj.bcebos.com/models/mot/fairmot_hrnetv2_w18_dlafpn_30e_1088x608_visdrone_pedestrian.pdparams) | [配置文件](./fairmot_hrnetv2_w18_dlafpn_30e_1088x608_visdrone_pedestrian.yml) |
 |  VisDrone     | HRNetv2-W18| 864x480 |  38.6 |   50.9 |    -   | [下载链接](https://paddledet.bj.bcebos.com/models/mot/fairmot_hrnetv2_w18_dlafpn_30e_864x480_visdrone_pedestrian.pdparams) | [配置文件](./fairmot_hrnetv2_w18_dlafpn_30e_864x480_visdrone_pedestrian.yml) |
 |  VisDrone     | HRNetv2-W18| 576x320 |  30.6 |   47.2 |    -   | [下载链接](https://paddledet.bj.bcebos.com/models/mot/fairmot_hrnetv2_w18_dlafpn_30e_576x320_visdrone_pedestrian.pdparams) | [配置文件](./fairmot_hrnetv2_w18_dlafpn_30e_576x320_visdrone_pedestrian.yml) |

@@ -124,8 +124,8 @@ month={Oct},}

 @ARTICLE{9573394,
  author={Zhu, Pengfei and Wen, Longyin and Du, Dawei and Bian, Xiao and Fan, Heng and Hu, Qinghua and Ling, Haibin},
-  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence}, 
-  title={Detection and Tracking Meet Drones Challenge}, 
+  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
+  title={Detection and Tracking Meet Drones Challenge},
  year={2021},
  volume={},
  number={},

--- a/configs/picodet/README.md
+++ b/configs/picodet/README.md
--- a/configs/picodet/README_cn.md
+++ b/configs/picodet/README_cn.md
--- a/deploy/cpp/src/object_detector.cc
+++ b/deploy/cpp/src/object_detector.cc
@@ -15,16 +15,15 @@
 // for setprecision
 #include <chrono>
 #include <iomanip>
-#include "include/object_detector.h"

-using namespace paddle_infer;
+#include "include/object_detector.h"

 namespace PaddleDetection {

 // Load Model and create model predictor
-void ObjectDetector::LoadModel(const std::string& model_dir,
+void ObjectDetector::LoadModel(const std::string &model_dir,
                               const int batch_size,
-                               const std::string& run_mode) {
+                               const std::string &run_mode) {
  paddle_infer::Config config;
  std::string prog_file = model_dir + OS_PATH_SEP + "model.pdmodel";
  std::string params_file = model_dir + OS_PATH_SEP + "model.pdiparams";
@@ -42,27 +41,22 @@ void ObjectDetector::LoadModel(const std::string& model_dir,
      } else if (run_mode == "trt_int8") {
        precision = paddle_infer::Config::Precision::kInt8;
      } else {
-        printf(
-            "run_mode should be 'paddle', 'trt_fp32', 'trt_fp16' or "
-            "'trt_int8'");
+        printf("run_mode should be 'paddle', 'trt_fp32', 'trt_fp16' or "
+               "'trt_int8'");
      }
      // set tensorrt
-      config.EnableTensorRtEngine(1 << 30,
-                                  batch_size,
-                                  this->min_subgraph_size_,
-                                  precision,
-                                  false,
-                                  this->trt_calib_mode_);
+      config.EnableTensorRtEngine(1 << 30, batch_size, this->min_subgraph_size_,
+                                  precision, false, this->trt_calib_mode_);

      // set use dynamic shape
      if (this->use_dynamic_shape_) {
-        // set DynamicShsape for image tensor
+        // set DynamicShape for image tensor
        const std::vector<int> min_input_shape = {
-            1, 3, this->trt_min_shape_, this->trt_min_shape_};
+            batch_size, 3, this->trt_min_shape_, this->trt_min_shape_};
        const std::vector<int> max_input_shape = {
-            1, 3, this->trt_max_shape_, this->trt_max_shape_};
+            batch_size, 3, this->trt_max_shape_, this->trt_max_shape_};
        const std::vector<int> opt_input_shape = {
-            1, 3, this->trt_opt_shape_, this->trt_opt_shape_};
+            batch_size, 3, this->trt_opt_shape_, this->trt_opt_shape_};
        const std::map<std::string, std::vector<int>> map_min_input_shape = {
            {"image", min_input_shape}};
        const std::map<std::string, std::vector<int>> map_max_input_shape = {
@@ -70,8 +64,8 @@ void ObjectDetector::LoadModel(const std::string& model_dir,
        const std::map<std::string, std::vector<int>> map_opt_input_shape = {
            {"image", opt_input_shape}};

-        config.SetTRTDynamicShapeInfo(
-            map_min_input_shape, map_max_input_shape, map_opt_input_shape);
+        config.SetTRTDynamicShapeInfo(map_min_input_shape, map_max_input_shape,
+                                      map_opt_input_shape);
        std::cout << "TensorRT dynamic shape enabled" << std::endl;
      }
    }
@@ -96,12 +90,11 @@ void ObjectDetector::LoadModel(const std::string& model_dir,
 }

 // Visualiztion MaskDetector results
-cv::Mat VisualizeResult(
-    const cv::Mat& img,
-    const std::vector<PaddleDetection::ObjectResult>& results,
-    const std::vector<std::string>& lables,
-    const std::vector<int>& colormap,
-    const bool is_rbox = false) {
+cv::Mat
+VisualizeResult(const cv::Mat &img,
+                const std::vector<PaddleDetection::ObjectResult> &results,
+                const std::vector<std::string> &lables,
+                const std::vector<int> &colormap, const bool is_rbox = false) {
  cv::Mat vis_img = img.clone();
  for (int i = 0; i < results.size(); ++i) {
    // Configure color and text size
@@ -142,24 +135,18 @@ cv::Mat VisualizeResult(
    origin.y = results[i].rect[1];

    // Configure text background
-    cv::Rect text_back = cv::Rect(results[i].rect[0],
-                                  results[i].rect[1] - text_size.height,
-                                  text_size.width,
-                                  text_size.height);
+    cv::Rect text_back =
+        cv::Rect(results[i].rect[0], results[i].rect[1] - text_size.height,
+                 text_size.width, text_size.height);
    // Draw text, and background
    cv::rectangle(vis_img, text_back, roi_color, -1);
-    cv::putText(vis_img,
-                text,
-                origin,
-                font_face,
-                font_scale,
-                cv::Scalar(255, 255, 255),
-                thickness);
+    cv::putText(vis_img, text, origin, font_face, font_scale,
+                cv::Scalar(255, 255, 255), thickness);
  }
  return vis_img;
 }

-void ObjectDetector::Preprocess(const cv::Mat& ori_im) {
+void ObjectDetector::Preprocess(const cv::Mat &ori_im) {
  // Clone the image : keep the original mat for postprocess
  cv::Mat im = ori_im.clone();
  cv::cvtColor(im, im, cv::COLOR_BGR2RGB);
@@ -168,9 +155,8 @@ void ObjectDetector::Preprocess(const cv::Mat& ori_im) {

 void ObjectDetector::Postprocess(
    const std::vector<cv::Mat> mats,
-    std::vector<PaddleDetection::ObjectResult>* result,
-    std::vector<int> bbox_num,
-    std::vector<float> output_data_,
+    std::vector<PaddleDetection::ObjectResult> *result,
+    std::vector<int> bbox_num, std::vector<float> output_data_,
    bool is_rbox = false) {
  result->clear();
  int start_idx = 0;
@@ -226,12 +212,11 @@ void ObjectDetector::Postprocess(
 }

 void ObjectDetector::Predict(const std::vector<cv::Mat> imgs,
-                             const double threshold,
-                             const int warmup,
+                             const double threshold, const int warmup,
                             const int repeats,
-                             std::vector<PaddleDetection::ObjectResult>* result,
-                             std::vector<int>* bbox_num,
-                             std::vector<double>* times) {
+                             std::vector<PaddleDetection::ObjectResult> *result,
+                             std::vector<int> *bbox_num,
+                             std::vector<double> *times) {
  auto preprocess_start = std::chrono::steady_clock::now();
  int batch_size = imgs.size();

@@ -239,7 +224,7 @@ void ObjectDetector::Predict(const std::vector<cv::Mat> imgs,
  std::vector<float> in_data_all;
  std::vector<float> im_shape_all(batch_size * 2);
  std::vector<float> scale_factor_all(batch_size * 2);
-  std::vector<const float*> output_data_list_;
+  std::vector<const float *> output_data_list_;
  std::vector<int> out_bbox_num_data_;

  // in_net img for each batch
@@ -255,9 +240,8 @@ void ObjectDetector::Predict(const std::vector<cv::Mat> imgs,
    scale_factor_all[bs_idx * 2] = inputs_.scale_factor_[0];
    scale_factor_all[bs_idx * 2 + 1] = inputs_.scale_factor_[1];

-    // TODO: reduce cost time
-    in_data_all.insert(
-        in_data_all.end(), inputs_.im_data_.begin(), inputs_.im_data_.end());
+    in_data_all.insert(in_data_all.end(), inputs_.im_data_.begin(),
+                       inputs_.im_data_.end());

    // collect in_net img
    in_net_img_all[bs_idx] = inputs_.in_net_im_;
@@ -276,10 +260,10 @@ void ObjectDetector::Predict(const std::vector<cv::Mat> imgs,
      pad_img.convertTo(pad_img, CV_32FC3);
      std::vector<float> pad_data;
      pad_data.resize(rc * rh * rw);
-      float* base = pad_data.data();
+      float *base = pad_data.data();
      for (int i = 0; i < rc; ++i) {
-        cv::extractChannel(
-            pad_img, cv::Mat(rh, rw, CV_32FC1, base + i * rh * rw), i);
+        cv::extractChannel(pad_img,
+                           cv::Mat(rh, rw, CV_32FC1, base + i * rh * rw), i);
      }
      in_data_all.insert(in_data_all.end(), pad_data.begin(), pad_data.end());
    }
@@ -290,7 +274,7 @@ void ObjectDetector::Predict(const std::vector<cv::Mat> imgs,
  auto preprocess_end = std::chrono::steady_clock::now();
  // Prepare input tensor
  auto input_names = predictor_->GetInputNames();
-  for (const auto& tensor_name : input_names) {
+  for (const auto &tensor_name : input_names) {
    auto in_tensor = predictor_->GetInputHandle(tensor_name);
    if (tensor_name == "image") {
      int rh = inputs_.in_net_shape_[0];
@@ -320,8 +304,8 @@ void ObjectDetector::Predict(const std::vector<cv::Mat> imgs,
    for (int j = 0; j < output_names.size(); j++) {
      auto output_tensor = predictor_->GetOutputHandle(output_names[j]);
      std::vector<int> output_shape = output_tensor->shape();
-      int out_num = std::accumulate(
-          output_shape.begin(), output_shape.end(), 1, std::multiplies<int>());
+      int out_num = std::accumulate(output_shape.begin(), output_shape.end(), 1,
+                                    std::multiplies<int>());
      if (output_tensor->type() == paddle_infer::DataType::INT32) {
        out_bbox_num_data_.resize(out_num);
        output_tensor->CopyToCpu(out_bbox_num_data_.data());
@@ -344,8 +328,8 @@ void ObjectDetector::Predict(const std::vector<cv::Mat> imgs,
    for (int j = 0; j < output_names.size(); j++) {
      auto output_tensor = predictor_->GetOutputHandle(output_names[j]);
      std::vector<int> output_shape = output_tensor->shape();
-      int out_num = std::accumulate(
-          output_shape.begin(), output_shape.end(), 1, std::multiplies<int>());
+      int out_num = std::accumulate(output_shape.begin(), output_shape.end(), 1,
+                                    std::multiplies<int>());
      output_shape_list.push_back(output_shape);
      if (output_tensor->type() == paddle_infer::DataType::INT32) {
        out_bbox_num_data_.resize(out_num);
@@ -371,22 +355,15 @@ void ObjectDetector::Predict(const std::vector<cv::Mat> imgs,
      if (i == config_.fpn_stride_.size()) {
        reg_max = output_shape_list[i][2] / 4 - 1;
      }
-      float* buffer = new float[out_tensor_list[i].size()];
-      memcpy(buffer,
-             &out_tensor_list[i][0],
+      float *buffer = new float[out_tensor_list[i].size()];
+      memcpy(buffer, &out_tensor_list[i][0],
             out_tensor_list[i].size() * sizeof(float));
      output_data_list_.push_back(buffer);
    }
    PaddleDetection::PicoDetPostProcess(
-        result,
-        output_data_list_,
-        config_.fpn_stride_,
-        inputs_.im_shape_,
-        inputs_.scale_factor_,
-        config_.nms_info_["score_threshold"].as<float>(),
-        config_.nms_info_["nms_threshold"].as<float>(),
-        num_class,
-        reg_max);
+        result, output_data_list_, config_.fpn_stride_, inputs_.im_shape_,
+        inputs_.scale_factor_, config_.nms_info_["score_threshold"].as<float>(),
+        config_.nms_info_["nms_threshold"].as<float>(), num_class, reg_max);
    bbox_num->push_back(result->size());
  } else {
    is_rbox = output_shape_list[0][output_shape_list[0].size() - 1] % 10 == 0;

--- a/deploy/pphuman/datacollector.py
+++ b/deploy/pphuman/datacollector.py
@@ -35,6 +35,9 @@ class Result(object):
            return self.res_dict[name]
        return None

+    def clear(self, name):
+        self.res_dict[name].clear()
+

 class DataCollector(object):
    """
@@ -80,7 +83,6 @@ class DataCollector(object):
            ids = int(mot_item[0])
            if ids not in self.collector:
                self.collector[ids] = copy.deepcopy(self.mots)
-
            self.collector[ids]["frames"].append(frameid)
            self.collector[ids]["rects"].append([mot_item[2:]])
            if attr_res:

--- a/deploy/pphuman/mtmct.py
+++ b/deploy/pphuman/mtmct.py
@@ -297,10 +297,9 @@ def distill_idfeat(mot_res):
        feature_new = feature_list

    #if available frames number is more than 200, take one frame data per 20 frames
-    if len(qualities_new) > 200:
-        skipf = 20
-    else:
-        skipf = max(10, len(qualities_new) // 10)
+    skipf = 1
+    if len(qualities_new) > 20:
+        skipf = 2
    quality_skip = np.array(qualities_new[::skipf])
    feature_skip = np.array(feature_new[::skipf])


--- a/deploy/pphuman/pipeline.py
+++ b/deploy/pphuman/pipeline.py
@@ -587,7 +587,7 @@ class PipePredictor(object):
                if self.cfg['visual']:
                    self.action_visual_helper.update(action_res)

-            if self.with_mtmct:
+            if self.with_mtmct and frame_id % 10 == 0:
                crop_input, img_qualities, rects = self.reid_predictor.crop_image_with_mot(
                    frame, mot_res)
                if frame_id > self.warmup_frame:
@@ -603,6 +603,8 @@ class PipePredictor(object):
                    "rects": rects
                }
                self.pipeline_res.update(reid_res_dict, 'reid')
+            else:
+                self.pipeline_res.clear('reid')

            self.collector.append(frame_id, self.pipeline_res)


--- a/deploy/pptracking/python/mot/matching/jde_matching.py
+++ b/deploy/pptracking/python/mot/matching/jde_matching.py
@@ -26,7 +26,7 @@ warnings.filterwarnings("ignore")
 __all__ = [
    'merge_matches',
    'linear_assignment',
-    'cython_bbox_ious',
+    'bbox_ious',
    'iou_distance',
    'embedding_distance',
    'fuse_motion',
@@ -68,22 +68,28 @@ def linear_assignment(cost_matrix, thresh):
    return matches, unmatched_a, unmatched_b


-def cython_bbox_ious(atlbrs, btlbrs):
-    ious = np.zeros((len(atlbrs), len(btlbrs)), dtype=np.float)
-    if ious.size == 0:
+def bbox_ious(atlbrs, btlbrs):
+    boxes = np.ascontiguousarray(atlbrs, dtype=np.float)
+    query_boxes = np.ascontiguousarray(btlbrs, dtype=np.float)
+    N = boxes.shape[0]
+    K = query_boxes.shape[0]
+    ious = np.zeros((N, K), dtype=boxes.dtype)
+    if N * K == 0:
        return ious
-    try:
-        import cython_bbox
-    except Exception as e:
-        print('cython_bbox not found, please install cython_bbox.'
-              'for example: `pip install cython_bbox`.')
-        exit()
-
-    ious = cython_bbox.bbox_overlaps(
-        np.ascontiguousarray(
-            atlbrs, dtype=np.float),
-        np.ascontiguousarray(
-            btlbrs, dtype=np.float))
+
+    for k in range(K):
+        box_area = ((query_boxes[k, 2] - query_boxes[k, 0] + 1) *
+                    (query_boxes[k, 3] - query_boxes[k, 1] + 1))
+        for n in range(N):
+            iw = (min(boxes[n, 2], query_boxes[k, 2]) - max(
+                boxes[n, 0], query_boxes[k, 0]) + 1)
+            if iw > 0:
+                ih = (min(boxes[n, 3], query_boxes[k, 3]) - max(
+                    boxes[n, 1], query_boxes[k, 1]) + 1)
+                if ih > 0:
+                    ua = float((boxes[n, 2] - boxes[n, 0] + 1) * (boxes[
+                        n, 3] - boxes[n, 1] + 1) + box_area - iw * ih)
+                    ious[n, k] = iw * ih / ua
    return ious


@@ -98,7 +104,7 @@ def iou_distance(atracks, btracks):
    else:
        atlbrs = [track.tlbr for track in atracks]
        btlbrs = [track.tlbr for track in btracks]
-    _ious = cython_bbox_ious(atlbrs, btlbrs)
+    _ious = bbox_ious(atlbrs, btlbrs)
    cost_matrix = 1 - _ious

    return cost_matrix

--- a/deploy/python/infer.py
+++ b/deploy/python/infer.py
@@ -231,7 +231,7 @@ class Detector(object):
                self.det_times.preprocess_time_s.end()

                # model prediction
-                result = self.predict(repeats=repeats)  # warmup
+                result = self.predict(repeats=50)  # warmup
                self.det_times.inference_time_s.start()
                result = self.predict(repeats=repeats)
                self.det_times.inference_time_s.end(repeats=repeats)
@@ -296,7 +296,7 @@ class Detector(object):
        if not os.path.exists(self.output_dir):
            os.makedirs(self.output_dir)
        out_path = os.path.join(self.output_dir, video_out_name)
-        fourcc = cv2.VideoWriter_fourcc(* 'mp4v')
+        fourcc = cv2.VideoWriter_fourcc(*'mp4v')
        writer = cv2.VideoWriter(out_path, fourcc, fps, (width, height))
        index = 1
        while (1):
@@ -790,7 +790,7 @@ def main():
        if FLAGS.image_dir is None and FLAGS.image_file is not None:
            assert FLAGS.batch_size == 1, "batch_size should be 1, when image_file is not None"
        img_list = get_test_images(FLAGS.image_dir, FLAGS.image_file)
-        detector.predict_image(img_list, FLAGS.run_benchmark, repeats=10)
+        detector.predict_image(img_list, FLAGS.run_benchmark, repeats=100)
        if not FLAGS.run_benchmark:
            detector.det_times.info(average=True)
        else:

--- a/ppdet/metrics/mcmot_metrics.py
+++ b/ppdet/metrics/mcmot_metrics.py
@@ -306,11 +306,12 @@ class MCMOTEvaluator(object):

    def load_annotations(self):
        assert self.data_type == 'mcmot'
-        self.gt_filename = os.path.join(self.data_root, '../',
-                                        'sequences',
+        self.gt_filename = os.path.join(self.data_root, '../', 'sequences',
                                        '{}.txt'.format(self.seq_name))
        if not os.path.exists(self.gt_filename):
-            logger.warning("gt_filename '{}' of MCMOTEvaluator is not exist, so the MOTA will be -inf.")
+            logger.warning(
+                "gt_filename '{}' of MCMOTEvaluator is not exist, so the MOTA will be -INF."
+            )

    def reset_accumulator(self):
        import motmetrics as mm

--- a/ppdet/metrics/mot_metrics.py
+++ b/ppdet/metrics/mot_metrics.py
@@ -37,8 +37,11 @@ __all__ = ['MOTEvaluator', 'MOTMetric', 'JDEDetMetric', 'KITTIMOTMetric']
 def read_mot_results(filename, is_gt=False, is_ignore=False):
    valid_label = [1]
    ignore_labels = [2, 7, 8, 12]  # only in motchallenge datasets like 'MOT16'
-    logger.info("In MOT16/17 dataset the valid_label of ground truth is '{}', "
-        "in other dataset it should be '0' for single classs MOT.".format(valid_label[0]))
+    if is_gt:
+        logger.info(
+            "In MOT16/17 dataset the valid_label of ground truth is '{}', "
+            "in other dataset it should be '0' for single classs MOT.".format(
+                valid_label[0]))
    results_dict = dict()
    if os.path.isfile(filename):
        with open(filename, 'r') as f:
@@ -118,7 +121,9 @@ class MOTEvaluator(object):
        gt_filename = os.path.join(self.data_root, self.seq_name, 'gt',
                                   'gt.txt')
        if not os.path.exists(gt_filename):
-            logger.warning("gt_filename '{}' of MOTEvaluator is not exist, so the MOTA will be -inf.")
+            logger.warning(
+                "gt_filename '{}' of MOTEvaluator is not exist, so the MOTA will be -INF."
+            )
        self.gt_frame_dict = read_mot_results(gt_filename, is_gt=True)
        self.gt_ignore_frame_dict = read_mot_results(
            gt_filename, is_ignore=True)

--- a/ppdet/modeling/architectures/meta_arch.py
+++ b/ppdet/modeling/architectures/meta_arch.py
@@ -22,22 +22,23 @@ class BaseArch(nn.Layer):
        self.fuse_norm = False

    def load_meanstd(self, cfg_transform):
-        self.scale = 1.
-        self.mean = paddle.to_tensor([0.485, 0.456, 0.406]).reshape(
-            (1, 3, 1, 1))
-        self.std = paddle.to_tensor([0.229, 0.224, 0.225]).reshape((1, 3, 1, 1))
+        scale = 1.
+        mean = np.array([0.485, 0.456, 0.406], dtype=np.float32)
+        std = np.array([0.229, 0.224, 0.225], dtype=np.float32)
        for item in cfg_transform:
            if 'NormalizeImage' in item:
-                self.mean = paddle.to_tensor(item['NormalizeImage'][
-                    'mean']).reshape((1, 3, 1, 1))
-                self.std = paddle.to_tensor(item['NormalizeImage'][
-                    'std']).reshape((1, 3, 1, 1))
+                mean = np.array(
+                    item['NormalizeImage']['mean'], dtype=np.float32)
+                std = np.array(item['NormalizeImage']['std'], dtype=np.float32)
                if item['NormalizeImage'].get('is_scale', True):
-                    self.scale = 1. / 255.
+                    scale = 1. / 255.
                break
        if self.data_format == 'NHWC':
-            self.mean = self.mean.reshape(1, 1, 1, 3)
-            self.std = self.std.reshape(1, 1, 1, 3)
+            self.scale = paddle.to_tensor(scale / std).reshape((1, 1, 1, 3))
+            self.bias = paddle.to_tensor(-mean / std).reshape((1, 1, 1, 3))
+        else:
+            self.scale = paddle.to_tensor(scale / std).reshape((1, 3, 1, 1))
+            self.bias = paddle.to_tensor(-mean / std).reshape((1, 3, 1, 1))

    def forward(self, inputs):
        if self.data_format == 'NHWC':
@@ -46,7 +47,7 @@ class BaseArch(nn.Layer):

        if self.fuse_norm:
            image = inputs['image']
-            self.inputs['image'] = (image * self.scale - self.mean) / self.std
+            self.inputs['image'] = image * self.scale + self.bias
            self.inputs['im_shape'] = inputs['im_shape']
            self.inputs['scale_factor'] = inputs['scale_factor']
        else:
@@ -66,8 +67,7 @@ class BaseArch(nn.Layer):
            outs = []
            for inp in inputs_list:
                if self.fuse_norm:
-                    self.inputs['image'] = (
-                        inp['image'] * self.scale - self.mean) / self.std
+                    self.inputs['image'] = inp['image'] * self.scale + self.bias
                    self.inputs['im_shape'] = inp['im_shape']
                    self.inputs['scale_factor'] = inp['scale_factor']
                else:
@@ -75,7 +75,7 @@ class BaseArch(nn.Layer):
                outs.append(self.get_pred())

            # multi-scale test
-            if len(outs)>1:
+            if len(outs) > 1:
                out = self.merge_multi_scale_predictions(outs)
            else:
                out = outs[0]
@@ -92,7 +92,9 @@ class BaseArch(nn.Layer):
            keep_top_k = self.bbox_post_process.nms.keep_top_k
            nms_threshold = self.bbox_post_process.nms.nms_threshold
        else:
-            raise Exception("Multi scale test only supports CascadeRCNN, FasterRCNN and MaskRCNN for now")
+            raise Exception(
+                "Multi scale test only supports CascadeRCNN, FasterRCNN and MaskRCNN for now"
+            )

        final_boxes = []
        all_scale_outs = paddle.concat([o['bbox'] for o in outs]).numpy()
@@ -101,9 +103,11 @@ class BaseArch(nn.Layer):
            if np.count_nonzero(idxs) == 0:
                continue
            r = nms(all_scale_outs[idxs, 1:], nms_threshold)
-            final_boxes.append(np.concatenate([np.full((r.shape[0], 1), c), r], 1))
+            final_boxes.append(
+                np.concatenate([np.full((r.shape[0], 1), c), r], 1))
        out = np.concatenate(final_boxes)
-        out = np.concatenate(sorted(out, key=lambda e: e[1])[-keep_top_k:]).reshape((-1, 6))
+        out = np.concatenate(sorted(
+            out, key=lambda e: e[1])[-keep_top_k:]).reshape((-1, 6))
        out = {
            'bbox': paddle.to_tensor(out),
            'bbox_num': paddle.to_tensor(np.array([out.shape[0], ]))

--- a/ppdet/modeling/assigners/atss_assigner.py
+++ b/ppdet/modeling/assigners/atss_assigner.py
@@ -199,7 +199,11 @@ class ATSSAssigner(nn.Layer):
            gt_bboxes.reshape([-1, 4]), assigned_gt_index.flatten(), axis=0)
        assigned_bboxes = assigned_bboxes.reshape([batch_size, num_anchors, 4])

-        assigned_scores = F.one_hot(assigned_labels, self.num_classes)
+        assigned_scores = F.one_hot(assigned_labels, self.num_classes + 1)
+        ind = list(range(self.num_classes + 1))
+        ind.remove(bg_index)
+        assigned_scores = paddle.index_select(
+            assigned_scores, paddle.to_tensor(ind), axis=-1)
        if pred_bboxes is not None:
            # assigned iou
            ious = batch_iou_similarity(gt_bboxes, pred_bboxes) * mask_positive

--- a/ppdet/modeling/assigners/task_aligned_assigner.py
+++ b/ppdet/modeling/assigners/task_aligned_assigner.py
@@ -143,7 +143,11 @@ class TaskAlignedAssigner(nn.Layer):
            gt_bboxes.reshape([-1, 4]), assigned_gt_index.flatten(), axis=0)
        assigned_bboxes = assigned_bboxes.reshape([batch_size, num_anchors, 4])

-        assigned_scores = F.one_hot(assigned_labels, num_classes)
+        assigned_scores = F.one_hot(assigned_labels, num_classes + 1)
+        ind = list(range(num_classes + 1))
+        ind.remove(bg_index)
+        assigned_scores = paddle.index_select(
+            assigned_scores, paddle.to_tensor(ind), axis=-1)
        # rescale alignment metrics
        alignment_metrics *= mask_positive
        max_metrics_per_instance = alignment_metrics.max(axis=-1, keepdim=True)

--- a/ppdet/modeling/heads/ppyoloe_head.py
+++ b/ppdet/modeling/heads/ppyoloe_head.py
@@ -331,7 +331,8 @@ class PPYOLOEHead(nn.Layer):
        assigned_bboxes /= stride_tensor
        # cls loss
        if self.use_varifocal_loss:
-            one_hot_label = F.one_hot(assigned_labels, self.num_classes)
+            one_hot_label = F.one_hot(assigned_labels,
+                                      self.num_classes + 1)[..., :-1]
            loss_cls = self._varifocal_loss(pred_scores, assigned_scores,
                                            one_hot_label)
        else:

--- a/ppdet/modeling/losses/detr_loss.py
+++ b/ppdet/modeling/losses/detr_loss.py
@@ -80,7 +80,7 @@ class DETRLoss(nn.Layer):
            target_label = target_label.reshape([bs, num_query_objects])
        if self.use_focal_loss:
            target_label = F.one_hot(target_label,
-                                     self.num_classes + 1)[:, :, :-1]
+                                     self.num_classes + 1)[..., :-1]
        return {
            'loss_class': self.loss_coeff['class'] * sigmoid_focal_loss(
                logits, target_label, num_gts / num_query_objects)

--- a/ppdet/modeling/mot/matching/jde_matching.py
+++ b/ppdet/modeling/mot/matching/jde_matching.py
@@ -26,7 +26,7 @@ warnings.filterwarnings("ignore")
 __all__ = [
    'merge_matches',
    'linear_assignment',
-    'cython_bbox_ious',
+    'bbox_ious',
    'iou_distance',
    'embedding_distance',
    'fuse_motion',
@@ -68,22 +68,28 @@ def linear_assignment(cost_matrix, thresh):
    return matches, unmatched_a, unmatched_b


-def cython_bbox_ious(atlbrs, btlbrs):
-    ious = np.zeros((len(atlbrs), len(btlbrs)), dtype=np.float)
-    if ious.size == 0:
+def bbox_ious(atlbrs, btlbrs):
+    boxes = np.ascontiguousarray(atlbrs, dtype=np.float)
+    query_boxes = np.ascontiguousarray(btlbrs, dtype=np.float)
+    N = boxes.shape[0]
+    K = query_boxes.shape[0]
+    ious = np.zeros((N, K), dtype=boxes.dtype)
+    if N * K == 0:
        return ious
-    try:
-        import cython_bbox
-    except Exception as e:
-        print('cython_bbox not found, please install cython_bbox.'
-                     'for example: `pip install cython_bbox`.')
-        raise e
-
-    ious = cython_bbox.bbox_overlaps(
-        np.ascontiguousarray(
-            atlbrs, dtype=np.float),
-        np.ascontiguousarray(
-            btlbrs, dtype=np.float))
+
+    for k in range(K):
+        box_area = ((query_boxes[k, 2] - query_boxes[k, 0] + 1) *
+                    (query_boxes[k, 3] - query_boxes[k, 1] + 1))
+        for n in range(N):
+            iw = (min(boxes[n, 2], query_boxes[k, 2]) - max(
+                boxes[n, 0], query_boxes[k, 0]) + 1)
+            if iw > 0:
+                ih = (min(boxes[n, 3], query_boxes[k, 3]) - max(
+                    boxes[n, 1], query_boxes[k, 1]) + 1)
+                if ih > 0:
+                    ua = float((boxes[n, 2] - boxes[n, 0] + 1) * (boxes[
+                        n, 3] - boxes[n, 1] + 1) + box_area - iw * ih)
+                    ious[n, k] = iw * ih / ua
    return ious


@@ -98,7 +104,7 @@ def iou_distance(atracks, btracks):
    else:
        atlbrs = [track.tlbr for track in atracks]
        btlbrs = [track.tlbr for track in btracks]
-    _ious = cython_bbox_ious(atlbrs, btlbrs)
+    _ious = bbox_ious(atlbrs, btlbrs)
    cost_matrix = 1 - _ious

    return cost_matrix

--- a/requirements.txt
+++ b/requirements.txt
@@ -14,4 +14,3 @@ lap
 sklearn
 motmetrics
 openpyxl
-cython_bbox