Merge branch 'PaddlePaddle:release/2.4' into release/2.4

configs/datasets/coco_detection.yml

@@ -17,3 +17,4 @@ EvalDataset:
 TestDataset:
   !ImageFolder
     anno_path: annotations/instances_val2017.json
+    dataset_dir: dataset/coco

configs/datasets/coco_instance.yml

@@ -17,3 +17,4 @@ EvalDataset:
 TestDataset:
   !ImageFolder
     anno_path: annotations/instances_val2017.json
+    dataset_dir: dataset/coco

configs/datasets/dota.yml

@@ -17,3 +17,4 @@ EvalDataset:
 TestDataset:
   !ImageFolder
     anno_path: trainval_split/s2anet_trainval_paddle_coco.json
+    dataset_dir: dataset/DOTA_1024_s2anet/

configs/mot/bytetrack/_base_/mot17.yml

@@ -17,6 +17,7 @@ EvalDataset:
 
 TestDataset:
   !ImageFolder
+    dataset_dir: dataset/mot/MOT17
     anno_path: annotations/val_half.json
 
 

configs/mot/deepsort/_base_/mot17.yml

@@ -17,6 +17,7 @@ EvalDataset:
 
 TestDataset:
   !ImageFolder
+    dataset_dir: dataset/mot/MOT17
     anno_path: annotations/val_half.json
 
 

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:

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])
 

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)
 

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:

ppdet/data/source/category.py

@@ -39,6 +39,11 @@ def get_categories(metric_type, anno_file=None, arch=None):
     if arch == 'keypoint_arch':
         return (None, {'id': 'keypoint'})
 
+    if anno_file == None or (not os.path.isfile(anno_file)):
+        logger.warning("anno_file '{}' is None or not set or not exist, "
+            "please recheck TrainDataset/EvalDataset/TestDataset.anno_path, "
+            "otherwise the default categories will be used by metric_type.".format(anno_file))
+
     if metric_type.lower() == 'coco' or metric_type.lower(
     ) == 'rbox' or metric_type.lower() == 'snipercoco':
         if anno_file and os.path.isfile(anno_file):
@@ -55,8 +60,9 @@ def get_categories(metric_type, anno_file=None, arch=None):
         # anno file not exist, load default categories of COCO17
         else:
             if metric_type.lower() == 'rbox':
+                logger.warning("metric_type: {}, load default categories of DOTA.".format(metric_type))
                 return _dota_category()
-
+            logger.warning("metric_type: {}, load default categories of COCO.".format(metric_type))
             return _coco17_category()
 
     elif metric_type.lower() == 'voc':
@@ -77,6 +83,7 @@ def get_categories(metric_type, anno_file=None, arch=None):
         # anno file not exist, load default categories of
         # VOC all 20 categories
         else:
+            logger.warning("metric_type: {}, load default categories of VOC.".format(metric_type))
             return _vocall_category()
 
     elif metric_type.lower() == 'oid':
@@ -104,6 +111,7 @@ def get_categories(metric_type, anno_file=None, arch=None):
             return clsid2catid, catid2name
         # anno file not exist, load default category 'pedestrian'.
         else:
+            logger.warning("metric_type: {}, load default categories of pedestrian MOT.".format(metric_type))
             return _mot_category(category='pedestrian')
 
     elif metric_type.lower() in ['kitti', 'bdd100kmot']:
@@ -122,6 +130,7 @@ def get_categories(metric_type, anno_file=None, arch=None):
             return clsid2catid, catid2name
         # anno file not exist, load default categories of visdrone all 10 categories
         else:
+            logger.warning("metric_type: {}, load default categories of VisDrone.".format(metric_type))
             return _visdrone_category()
 
     else:

ppdet/metrics/mcmot_metrics.py

@@ -26,8 +26,6 @@ from motmetrics.math_util import quiet_divide
 import numpy as np
 import pandas as pd
 
-import paddle
-import paddle.nn.functional as F
 from .metrics import Metric
 import motmetrics as mm
 import openpyxl
@@ -311,6 +309,8 @@ class MCMOTEvaluator(object):
         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.")
 
     def reset_accumulator(self):
         import motmetrics as mm

ppdet/metrics/mot_metrics.py

@@ -22,8 +22,7 @@ import sys
 import math
 from collections import defaultdict
 import numpy as np
-import paddle
-import paddle.nn.functional as F
+
 from ppdet.modeling.bbox_utils import bbox_iou_np_expand
 from .map_utils import ap_per_class
 from .metrics import Metric
@@ -36,8 +35,10 @@ __all__ = ['MOTEvaluator', 'MOTMetric', 'JDEDetMetric', 'KITTIMOTMetric']
 
 
 def read_mot_results(filename, is_gt=False, is_ignore=False):
-    valid_labels = {1}
-    ignore_labels = {2, 7, 8, 12}  # only in motchallenge datasets like 'MOT16'
+    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]))
     results_dict = dict()
     if os.path.isfile(filename):
         with open(filename, 'r') as f:
@@ -50,12 +51,10 @@ def read_mot_results(filename, is_gt=False, is_ignore=False):
                     continue
                 results_dict.setdefault(fid, list())
 
-                box_size = float(linelist[4]) * float(linelist[5])
-
                 if is_gt:
                     label = int(float(linelist[7]))
                     mark = int(float(linelist[6]))
-                    if mark == 0 or label not in valid_labels:
+                    if mark == 0 or label not in valid_label:
                         continue
                     score = 1
                 elif is_ignore:
@@ -118,6 +117,8 @@ class MOTEvaluator(object):
         assert self.data_type == 'mot'
         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.")
         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)

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], ]))