Add model file collector, fix some bugs and add some features (#123)

add model path searcher and remove hardwritten file paths from benchmark configs; pack ppresnet, mobilenet & crnn with labels; fix palm det data; add flags to enable models of different precision separately (#123)

benchmark/README.md

 # OpenCV Zoo Benchmark
 
-Benchmarking different models in the zoo.
+Benchmarking the speed of OpenCV DNN inferring different models in the zoo. Result of each model includes the time of its preprocessing, inference and postprocessing stages.
 
 Data for benchmarking will be downloaded and loaded in [data](./data) based on given config.
 
-Time is measured from data preprocess (resize is excluded), to a forward pass of a network, and postprocess to get final results. The final time data presented is averaged from a 100-time run.
-
 ## Preparation
 
 1. Install `python >= 3.6`.
@@ -13,29 +11,29 @@ Time is measured from data preprocess (resize is excluded), to a forward pass of
 3. Download data for benchmarking.
     1. Download all data: `python download_data.py`
     2. Download one or more specified data: `python download_data.py face text`. Available names can be found in `download_data.py`.
-    3. If download fails, you can download all data from https://pan.baidu.com/s/18sV8D4vXUb2xC9EG45k7bg (code: pvrw). Please place and extract data packages under [./data](./data).
+    3. You can also download all data from https://pan.baidu.com/s/18sV8D4vXUb2xC9EG45k7bg (code: pvrw). Please place and extract data packages under [./data](./data).
 
 ## Benchmarking
 
-Run the following command to benchmark on a given config:
+**Linux**:
 
 ```shell
 export PYTHONPATH=$PYTHONPATH:.. 
 python benchmark.py --cfg ./config/face_detection_yunet.yaml
 ```
 
-If you are a Windows user and wants to run in CMD/PowerShell, use this command instead:
+**Windows**:
 - CMD
-```shell
-set PYTHONPATH=%PYTHONPATH%;..
-python benchmark.py --cfg ./config/face_detection_yunet.yaml
-```
+    ```shell
+    set PYTHONPATH=%PYTHONPATH%;..
+    python benchmark.py --cfg ./config/face_detection_yunet.yaml
+    ```
 
 - PowerShell
-```shell
-$env:PYTHONPATH=$env:PYTHONPATH+";.."
-python benchmark.py --cfg ./config/face_detection_yunet.yaml
-```
+    ```shell
+    $env:PYTHONPATH=$env:PYTHONPATH+";.."
+    python benchmark.py --cfg ./config/face_detection_yunet.yaml
+    ```
 <!--
 Omit `--cfg` if you want to benchmark all included models:
 ```shell

benchmark/benchmark.py

@@ -11,6 +11,9 @@ from utils import METRICS, DATALOADERS
 parser = argparse.ArgumentParser("Benchmarks for OpenCV Zoo.")
 parser.add_argument('--cfg', '-c', type=str,
                     help='Benchmarking on the given config.')
+parser.add_argument("--fp32", action="store_true", help="Runs models of float32 precision only.")
+parser.add_argument("--fp16", action="store_true", help="Runs models of float16 precision only.")
+parser.add_argument("--int8", action="store_true", help="Runs models of int8 precision only.")
 args = parser.parse_args()
 
 def build_from_cfg(cfg, registery, key=None, name=None):
@@ -24,14 +27,6 @@ def build_from_cfg(cfg, registery, key=None, name=None):
     else:
         raise NotImplementedError()
 
-def prepend_pythonpath(cfg):
-    for k, v in cfg.items():
-        if isinstance(v, dict):
-            prepend_pythonpath(v)
-        else:
-            if 'path' in k.lower():
-                cfg[k] = os.path.join(os.environ['PYTHONPATH'].split(os.pathsep)[-1], v)
-
 class Benchmark:
     def __init__(self, **kwargs):
         self._type = kwargs.pop('type', None)
@@ -115,16 +110,30 @@ if __name__ == '__main__':
     with open(args.cfg, 'r') as f:
         cfg = yaml.safe_load(f)
 
-    # prepend PYTHONPATH to each path
-    prepend_pythonpath(cfg)
-
-    # Instantiate benchmarking
+    # Instantiate benchmark
     benchmark = Benchmark(**cfg['Benchmark'])
 
     # Instantiate model
-    model = build_from_cfg(cfg=cfg['Model'], registery=MODELS, key='name')
-
-    # Run benchmarking
-    print('Benchmarking {}:'.format(model.name))
-    benchmark.run(model)
-    benchmark.printResults()
+    model_config = cfg['Model']
+    model_handler, model_paths = MODELS.get(model_config.pop('name'))
+
+    _model_paths = []
+    if args.fp32 or args.fp16 or args.int8:
+        if args.fp32:
+            _model_paths += model_paths['fp32']
+        if args.fp16:
+            _model_paths += model_paths['fp16']
+        if args.int8:
+            _model_paths += model_paths['int8']
+    else:
+        _model_paths = model_paths['fp32'] + model_paths['fp16'] + model_paths['int8']
+
+    for model_path in _model_paths:
+        model = model_handler(*model_path, **model_config)
+        # Format model_path
+        for i in range(len(model_path)):
+            model_path[i] = model_path[i].split('/')[-1]
+        print('Benchmarking {} with {}'.format(model.name, model_path))
+        # Run benchmark
+        benchmark.run(model)
+        benchmark.printResults()

benchmark/config/face_detection_yunet.yaml

@@ -2,7 +2,7 @@ Benchmark:
   name: "Face Detection Benchmark"
   type: "Detection"
   data:
-    path: "benchmark/data/face_detection"
+    path: "data/face_detection"
     files: ["group.jpg", "concerts.jpg", "dance.jpg"]
     sizes: # [[w1, h1], ...], Omit to run at original scale
       - [160, 120]
@@ -16,8 +16,6 @@ Benchmark:
 
 Model:
   name: "YuNet"
-  modelPath: "models/face_detection_yunet/face_detection_yunet_2022mar.onnx"
   confThreshold: 0.6
   nmsThreshold: 0.3
   topK: 5000
-

benchmark/config/face_recognition_sface.yaml

@@ -2,7 +2,7 @@ Benchmark:
   name: "Face Recognition Benchmark"
   type: "Recognition"
   data:
-    path: "benchmark/data/face_recognition"
+    path: "data/face_recognition"
     files: ["Aaron_Tippin_0001.jpg", "Alvaro_Uribe_0028.jpg", "Alvaro_Uribe_0029.jpg", "Jose_Luis_Rodriguez_Zapatero_0001.jpg"]
   metric: # 'sizes' is omitted since this model requires input of fixed size
     warmup: 30
@@ -13,4 +13,3 @@ Benchmark:
 
 Model:
   name: "SFace"
-  modelPath: "models/face_recognition_sface/face_recognition_sface_2021dec.onnx"
\ No newline at end of file

benchmark/config/facial_expression_recognition.yaml

@@ -2,7 +2,7 @@ Benchmark:
   name: "Facial Expression Recognition Benchmark"
   type: "Recognition"
   data:
-    path: "benchmark/data/facial_expression_recognition/fer_evaluation"
+    path: "data/facial_expression_recognition/fer_evaluation"
     files: ["RAF_test_0_61.jpg", "RAF_test_0_30.jpg", "RAF_test_6_25.jpg"]
   metric: # 'sizes' is omitted since this model requires input of fixed size
     warmup: 30
@@ -13,4 +13,3 @@ Benchmark:
 
 Model:
   name: "FacialExpressionRecog"
-  modelPath: "models/facial_expression_recognition/facial_expression_recognition_mobilefacenet_2022july.onnx"

benchmark/config/handpose_estimation_mediapipe.yaml

@@ -2,7 +2,7 @@ Benchmark:
   name: "Hand Pose Estimation Benchmark"
   type: "Recognition"
   data:
-    path: "benchmark/data/palm_detection"
+    path: "data/palm_detection_20230125"
     files: ["palm1.jpg", "palm2.jpg", "palm3.jpg"]
     sizes: # [[w1, h1], ...], Omit to run at original scale
       - [256, 256]
@@ -15,5 +15,4 @@ Benchmark:
 
 Model:
   name: "MPHandPose"
-  modelPath: "models/handpose_estimation_mediapipe/handpose_estimation_mediapipe_2022may.onnx"
   confThreshold: 0.9

benchmark/config/human_segmentation_pphumanseg.yaml

@@ -2,7 +2,7 @@ Benchmark:
   name: "Human Segmentation Benchmark"
   type: "Base"
   data:
-    path: "benchmark/data/human_segmentation"
+    path: "data/human_segmentation"
     files: ["messi5.jpg", "100040721_1.jpg", "detect.jpg"]
     sizes: [[192, 192]]
     toRGB: True
@@ -15,4 +15,3 @@ Benchmark:
 
 Model:
   name: "PPHumanSeg"
-  modelPath: "models/human_segmentation_pphumanseg/human_segmentation_pphumanseg_2021oct.onnx"
\ No newline at end of file

benchmark/config/image_classification_mobilenetv1.yaml → benchmark/config/image_classification_mobilenet.yaml

@@ -2,7 +2,7 @@ Benchmark:
   name: "Image Classification Benchmark"
   type: "Classification"
   data:
-    path: "benchmark/data/image_classification"
+    path: "data/image_classification"
     files: ["coffee_mug.jpg", "umbrella.jpg", "wall_clock.jpg"]
     sizes: [[256, 256]]
     toRGB: True
@@ -15,6 +15,4 @@ Benchmark:
   target: "cpu"
 
 Model:
-  name: "MobileNetV1"
-  modelPath: "models/image_classification_mobilenet/image_classification_mobilenetv1_2022apr.onnx"
-
+  name: "MobileNet"

benchmark/config/image_classification_mobilenetv2.yaml

-Benchmark:
-  name: "Image Classification Benchmark"
-  type: "Classification"
-  data:
-    path: "benchmark/data/image_classification"
-    files: ["coffee_mug.jpg", "umbrella.jpg", "wall_clock.jpg"]
-    sizes: [[256, 256]]
-    toRGB: True
-    centerCrop: 224
-  metric:
-    warmup: 30
-    repeat: 10
-    reduction: "median"
-  backend: "default"
-  target: "cpu"
-
-Model:
-  name: "MobileNetV2"
-  modelPath: "models/image_classification_mobilenet/image_classification_mobilenetv2_2022apr.onnx"
-

benchmark/config/image_classification_ppresnet.yaml

@@ -2,7 +2,7 @@ Benchmark:
   name: "Image Classification Benchmark"
   type: "Classification"
   data:
-    path: "benchmark/data/image_classification"
+    path: "data/image_classification"
     files: ["coffee_mug.jpg", "umbrella.jpg", "wall_clock.jpg"]
     sizes: [[256, 256]]
     toRGB: True
@@ -16,5 +16,3 @@ Benchmark:
 
 Model:
   name: "PPResNet"
-  modelPath: "models/image_classification_ppresnet/image_classification_ppresnet50_2022jan.onnx"
-

benchmark/config/license_plate_detection_yunet.yaml

@@ -2,7 +2,7 @@ Benchmark:
   name: "License Plate Detection Benchmark"
   type: "Detection"
   data:
-    path: "benchmark/data/license_plate_detection"
+    path: "data/license_plate_detection"
     files: ["1.jpg", "2.jpg", "3.jpg", "4.jpg"]
     sizes: # [[w1, h1], ...], Omit to run at original scale
       - [320, 240]
@@ -15,7 +15,6 @@ Benchmark:
 
 Model:
   name: "LPD_YuNet"
-  modelPath: "models/license_plate_detection_yunet/license_plate_detection_lpd_yunet_2022may.onnx"
   confThreshold: 0.8
   nmsThreshold: 0.3
   topK: 5000

benchmark/config/object_detection_nanodet.yaml

@@ -2,7 +2,7 @@ Benchmark:
   name: "Object Detection Benchmark"
   type: "Detection"
   data:
-    path: "benchmark/data/object_detection"
+    path: "data/object_detection"
     files: ["1.png", "2.png", "3.png"]
     sizes:
       - [416, 416]
@@ -15,7 +15,5 @@ Benchmark:
 
 Model:
   name: "NanoDet"
-  modelPath: "models/object_detection_nanodet/object_detection_nanodet_2022nov.onnx"
   prob_threshold: 0.35
   iou_threshold: 0.6
-

benchmark/config/object_detection_yolox.yaml

@@ -2,7 +2,7 @@ Benchmark:
   name: "Object Detection Benchmark"
   type: "Detection"
   data:
-    path: "benchmark/data/object_detection"
+    path: "data/object_detection"
     files: ["1.png", "2.png", "3.png"]
     sizes:
       - [640, 640]
@@ -15,8 +15,6 @@ Benchmark:
 
 Model:
   name: "YoloX"
-  modelPath: "models/object_detection_yolox/object_detection_yolox_2022nov.onnx"
   confThreshold: 0.35
   nmsThreshold: 0.5
   objThreshold: 0.5
-

benchmark/config/object_tracking_dasiamrpn.yaml

@@ -3,7 +3,7 @@ Benchmark:
   type: "Tracking"
   data:
     type: "TrackingVideoLoader"
-    path: "benchmark/data/object_tracking"
+    path: "data/object_tracking"
     files: ["throw_cup.mp4"]
   metric:
     type: "Tracking"
@@ -13,6 +13,3 @@ Benchmark:
 
 Model:
   name: "DaSiamRPN"
-  model_path: "models/object_tracking_dasiamrpn/object_tracking_dasiamrpn_model_2021nov.onnx"
-  kernel_cls1_path: "models/object_tracking_dasiamrpn/object_tracking_dasiamrpn_kernel_cls1_2021nov.onnx"
-  kernel_r1_path: "models/object_tracking_dasiamrpn/object_tracking_dasiamrpn_kernel_r1_2021nov.onnx"
\ No newline at end of file

benchmark/config/palm_detection_mediapipe.yaml

@@ -2,7 +2,7 @@ Benchmark:
   name: "Palm Detection Benchmark"
   type: "Detection"
   data:
-    path: "benchmark/data/palm_detection"
+    path: "data/palm_detection_20230125"
     files: ["palm1.jpg", "palm2.jpg", "palm3.jpg"]
     sizes: # [[w1, h1], ...], Omit to run at original scale
       - [256, 256]
@@ -15,8 +15,6 @@ Benchmark:
 
 Model:
   name: "MPPalmDet"
-  modelPath: "models/palm_detection_mediapipe/palm_detection_mediapipe_2022may.onnx"
   scoreThreshold: 0.5
   nmsThreshold: 0.3
   topK: 1
-

benchmark/config/person_reid_youtureid.yaml

@@ -2,7 +2,7 @@ Benchmark:
   name: "Person ReID Benchmark"
   type: "Base"
   data:
-    path: "benchmark/data/person_reid"
+    path: "data/person_reid"
     files: ["0030_c1_f0056923.jpg", "0042_c5_f0068994.jpg", "0056_c8_f0017063.jpg"]
     sizes: [[128, 256]]
   metric:
@@ -14,4 +14,3 @@ Benchmark:
 
 Model:
   name: "YoutuReID"
-  modelPath: "models/person_reid_youtureid/person_reid_youtu_2021nov.onnx"
\ No newline at end of file

benchmark/config/qrcode_wechatqrcode.yaml

@@ -2,7 +2,7 @@ Benchmark:
   name: "QRCode Detection and Decoding Benchmark"
   type: "Detection"
   data:
-    path: "benchmark/data/qrcode"
+    path: "data/qrcode"
     files: ["opencv.png", "opencv_zoo.png"]
     sizes:
       - [100, 100]
@@ -16,7 +16,3 @@ Benchmark:
 
 Model:
   name: "WeChatQRCode"
-  detect_prototxt_path: "models/qrcode_wechatqrcode/detect_2021nov.prototxt"
-  detect_model_path: "models/qrcode_wechatqrcode/detect_2021nov.caffemodel"
-  sr_prototxt_path: "models/qrcode_wechatqrcode/sr_2021nov.prototxt"
-  sr_model_path: "models/qrcode_wechatqrcode/sr_2021nov.caffemodel"
\ No newline at end of file

benchmark/config/text_detection_db.yaml

@@ -2,7 +2,7 @@ Benchmark:
   name: "Text Detection Benchmark"
   type: "Detection"
   data:
-    path: "benchmark/data/text"
+    path: "data/text"
     files: ["1.jpg", "2.jpg", "3.jpg"]
     sizes: # [[w1, h1], ...], Omit to run at original scale
       - [640, 480]
@@ -15,8 +15,7 @@ Benchmark:
 
 Model:
   name: "DB"
-  modelPath: "models/text_detection_db/text_detection_DB_TD500_resnet18_2021sep.onnx"
   binaryThreshold: 0.3
   polygonThreshold: 0.5
   maxCandidates: 200
-  unclipRatio: 2.0
\ No newline at end of file
+  unclipRatio: 2.0

benchmark/config/text_recognition_crnn_en.yaml → benchmark/config/text_recognition_crnn.yaml

@@ -2,7 +2,7 @@ Benchmark:
   name: "Text Recognition Benchmark"
   type: "Recognition"
   data:
-    path: "benchmark/data/text"
+    path: "data/text"
     files: ["1.jpg", "2.jpg", "3.jpg"]
   metric: # 'sizes' is omitted since this model requires input of fixed size
     warmup: 30
@@ -13,5 +13,3 @@ Benchmark:
 
 Model:
   name: "CRNN"
-  modelPath: "models/text_recognition_crnn/text_recognition_CRNN_EN_2021sep.onnx"
-  charsetPath: "models/text_recognition_crnn/charset_36_EN.txt"
\ No newline at end of file

benchmark/config/text_recognition_crnn_cn.yaml

-Benchmark:
-  name: "Text Recognition Benchmark"
-  type: "Recognition"
-  data:
-    path: "benchmark/data/text"
-    files: ["1.jpg", "2.jpg", "3.jpg"]
-  metric: # 'sizes' is omitted since this model requires input of fixed size
-    warmup: 30
-    repeat: 10
-    reduction: "median"
-  backend: "default"
-  target: "cpu"
-
-Model:
-  name: "CRNN"
-  modelPath: "models/text_recognition_crnn/text_recognition_CRNN_CN_2021nov.onnx"
-  charsetPath: "models/text_recognition_crnn/charset_3944_CN.txt"
\ No newline at end of file

benchmark/download_data.py

@@ -202,9 +202,9 @@ data_downloaders = dict(
         sha='5b741fbf34c1fbcf59cad8f2a65327a5899e66f1',
         filename='person_reid.zip'),
     palm_detection=Downloader(name='palm_detection',
-        url='https://drive.google.com/u/0/uc?id=1zYnOsXxYXn-hFIdyIws9louzqjpt8byQ&export=download',
-        sha='78ed095b685a9bacdd643782716127afe936f366',
-        filename='palm_detection_20220826.zip'),
+        url='https://drive.google.com/u/0/uc?id=1Z4KvccTZPeZ0qFLZ6saBt_TvcKYyo9JE&export=download',
+        sha='4b5bb24a51daab8913957e60245a4eb766c8cf2e',
+        filename='palm_detection_20230125.zip'),
     license_plate_detection=Downloader(name='license_plate_detection',
         url='https://drive.google.com/u/0/uc?id=1cf9MEyUqMMy8lLeDGd1any6tM_SsSmny&export=download',
         sha='997acb143ddc4531e6e41365fb7ad4722064564c',

models/__init__.py

+from pathlib import Path
+import glob
+import os
+
 from .face_detection_yunet.yunet import YuNet
 from .text_detection_db.db import DB
 from .text_recognition_crnn.crnn import CRNN
@@ -7,8 +11,7 @@ from .human_segmentation_pphumanseg.pphumanseg import PPHumanSeg
 from .qrcode_wechatqrcode.wechatqrcode import WeChatQRCode
 from .object_tracking_dasiamrpn.dasiamrpn import DaSiamRPN
 from .person_reid_youtureid.youtureid import YoutuReID
-from .image_classification_mobilenet.mobilenet_v1 import MobileNetV1
-from .image_classification_mobilenet.mobilenet_v2 import MobileNetV2
+from .image_classification_mobilenet.mobilenet import MobileNet
 from .palm_detection_mediapipe.mp_palmdet import MPPalmDet
 from .handpose_estimation_mediapipe.mp_handpose import MPHandPose
 from .license_plate_detection_yunet.lpd_yunet import LPD_YuNet
@@ -16,18 +19,61 @@ from .object_detection_nanodet.nanodet import NanoDet
 from .object_detection_yolox.yolox import YoloX
 from .facial_expression_recognition.facial_fer_model import FacialExpressionRecog
 
-class Registery:
+class ModuleRegistery:
     def __init__(self, name):
         self._name = name
         self._dict = dict()
 
+        self._base_path = Path(__file__).parent
+
     def get(self, key):
+        '''
+        Returns a tuple with:
+        - a module handler,
+        - a list of model file paths
+        '''
         return self._dict[key]
 
     def register(self, item):
-        self._dict[item.__name__] = item
+        '''
+        Registers given module handler along with paths of model files
+        '''
+        # search for model files
+        model_dir = str(self._base_path / item.__module__.split(".")[1])
+        fp32_model_paths = []
+        fp16_model_paths = []
+        int8_model_paths = []
+        # onnx
+        ret_onnx = sorted(glob.glob(os.path.join(model_dir, "*.onnx")))
+        if "object_tracking" in item.__module__:
+            # object tracking models usually have multiple parts
+            fp32_model_paths = [ret_onnx]
+        else:
+            for r in ret_onnx:
+                if "int8" in r:
+                    int8_model_paths.append([r])
+                elif "fp16" in r: # exclude fp16 for now
+                    fp16_model_paths.append([r])
+                else:
+                    fp32_model_paths.append([r])
+        # caffe
+        ret_caffemodel = sorted(glob.glob(os.path.join(model_dir, "*.caffemodel")))
+        ret_prototxt = sorted(glob.glob(os.path.join(model_dir, "*.prototxt")))
+        caffe_models = []
+        for caffemodel, prototxt in zip(ret_caffemodel, ret_prototxt):
+            caffe_models += [prototxt, caffemodel]
+        if caffe_models:
+            fp32_model_paths.append(caffe_models)
+
+        all_model_paths = dict(
+            fp32=fp32_model_paths,
+            fp16=fp16_model_paths,
+            int8=int8_model_paths,
+        )
+
+        self._dict[item.__name__] = (item, all_model_paths)
 
-MODELS = Registery('Models')
+MODELS = ModuleRegistery('Models')
 MODELS.register(YuNet)
 MODELS.register(DB)
 MODELS.register(CRNN)
@@ -37,8 +83,7 @@ MODELS.register(PPHumanSeg)
 MODELS.register(WeChatQRCode)
 MODELS.register(DaSiamRPN)
 MODELS.register(YoutuReID)
-MODELS.register(MobileNetV1)
-MODELS.register(MobileNetV2)
+MODELS.register(MobileNet)
 MODELS.register(MPPalmDet)
 MODELS.register(MPHandPose)
 MODELS.register(LPD_YuNet)

models/image_classification_mobilenet/demo.py

@@ -3,8 +3,7 @@ import argparse
 import numpy as np
 import cv2 as cv
 
-from mobilenet_v1 import MobileNetV1
-from mobilenet_v2 import MobileNetV2
+from mobilenet import MobileNet
 
 def str2bool(v):
     if v.lower() in ['on', 'yes', 'true', 'y', 't']:
@@ -26,24 +25,23 @@ try:
 except:
     print('This version of OpenCV does not support TIM-VX and NPU. Visit https://github.com/opencv/opencv/wiki/TIM-VX-Backend-For-Running-OpenCV-On-NPU for more information.')
 
+all_mobilenets = [
+    'image_classification_mobilenetv1_2022apr.onnx',
+    'image_classification_mobilenetv2_2022apr.onnx',
+    'image_classification_mobilenetv1_2022apr-int8-quantized.onnx',
+    'image_classification_mobilenetv2_2022apr-int8-quantized.onnx'
+]
+
 parser = argparse.ArgumentParser(description='Demo for MobileNet V1 & V2.')
 parser.add_argument('--input', '-i', type=str, help='Usage: Set input path to a certain image, omit if using camera.')
-parser.add_argument('--model', '-m', type=str, choices=['v1', 'v2', 'v1-q', 'v2-q'], default='v1', help='Usage: Set model type, defaults to image_classification_mobilenetv1_2022apr.onnx (v1).')
+parser.add_argument('--model', '-m', type=str, choices=all_mobilenets, default=all_mobilenets[0], help='Usage: Set model type, defaults to image_classification_mobilenetv1_2022apr.onnx (v1).')
 parser.add_argument('--backend', '-b', type=int, default=backends[0], help=help_msg_backends.format(*backends))
 parser.add_argument('--target', '-t', type=int, default=targets[0], help=help_msg_targets.format(*targets))
-parser.add_argument('--label', '-l', type=str, default='./imagenet_labels.txt', help='Usage: Set path to the different labels that will be used during the detection. Default list found in imagenet_labels.txt')
 args = parser.parse_args()
 
 if __name__ == '__main__':
-    # Instantiate ResNet
-    models = {
-        'v1': MobileNetV1(modelPath='./image_classification_mobilenetv1_2022apr.onnx', labelPath=args.label, backendId=args.backend, targetId=args.target),
-        'v2': MobileNetV2(modelPath='./image_classification_mobilenetv2_2022apr.onnx', labelPath=args.label, backendId=args.backend, targetId=args.target),
-        'v1-q': MobileNetV1(modelPath='./image_classification_mobilenetv1_2022apr-int8-quantized.onnx', labelPath=args.label, backendId=args.backend, targetId=args.target),
-        'v2-q': MobileNetV2(modelPath='./image_classification_mobilenetv2_2022apr-int8-quantized.onnx', labelPath=args.label, backendId=args.backend, targetId=args.target)
-
-    }
-    model = models[args.model]
+    # Instantiate MobileNet
+    model = MobileNet(modelPath=args.model, backendId=args.backend, targetId=args.target)
 
     # Read image and get a 224x224 crop from a 256x256 resized
     image = cv.imread(args.input)
@@ -56,4 +54,3 @@ if __name__ == '__main__':
 
     # Print result
     print('label: {}'.format(result))
-

models/image_classification_mobilenet/imagenet_labels.txt → models/image_classification_mobilenet/mobilenet.py

-tench
+import numpy as np
+import cv2 as cv
+
+class MobileNet:
+    '''
+    Works with MobileNet V1 & V2.
+    '''
+
+    def __init__(self, modelPath, topK=1, backendId=0, targetId=0):
+        self.model_path = modelPath
+        assert topK >= 1
+        self.top_k = topK
+        self.backend_id = backendId
+        self.target_id = targetId
+
+        self.model = cv.dnn.readNet(self.model_path)
+        self.model.setPreferableBackend(self.backend_id)
+        self.model.setPreferableTarget(self.target_id)
+
+        self.input_names = ''
+        self.output_names = ''
+        self.input_size = [224, 224]
+        self.mean=[0.485, 0.456, 0.406]
+        self.std=[0.229, 0.224, 0.225]
+
+        # load labels
+        self._labels = self._load_labels()
+
+    def _load_labels(self):
+        return self.LABELS_IMAGENET_1K.splitlines()
+
+    @property
+    def name(self):
+        return self.__class__.__name__
+
+    def setBackend(self, backendId):
+        self.backend_id = backendId
+        self.model.setPreferableBackend(self.backend_id)
+
+    def setTarget(self, targetId):
+        self.target_id = targetId
+        self.model.setPreferableTarget(self.target_id)
+
+    def _preprocess(self, image):
+        input_blob = (image / 255.0 - self.mean) / self.std
+        input_blob = input_blob.transpose(2, 0, 1)
+        input_blob = input_blob[np.newaxis, :, :, :]
+        input_blob = input_blob.astype(np.float32)
+        return input_blob
+
+    def infer(self, image):
+        # Preprocess
+        input_blob = self._preprocess(image)
+
+        # Forward
+        self.model.setInput(input_blob, self.input_names)
+        output_blob = self.model.forward(self.output_names)
+
+        # Postprocess
+        results = self._postprocess(output_blob)
+
+        return results
+
+    def _postprocess(self, output_blob):
+        batched_class_id_list = []
+        for o in output_blob:
+            class_id_list = o.argsort()[::-1][:self.top_k]
+            batched_class_id_list.append(class_id_list)
+        if len(self._labels) > 0:
+            batched_predicted_labels = []
+            for class_id_list in batched_class_id_list:
+                predicted_labels = []
+                for class_id in class_id_list:
+                    predicted_labels.append(self._labels[class_id])
+                batched_predicted_labels.append(predicted_labels)
+            return batched_predicted_labels
+        else:
+            return batched_class_id_list
+
+    LABELS_IMAGENET_1K = '''tench
 goldfish
 great white shark
 tiger shark
@@ -997,4 +1076,4 @@ earthstar
 hen-of-the-woods
 bolete
 ear
-toilet tissue
+toilet tissue'''

models/image_classification_mobilenet/mobilenet_v1.py

-import numpy as np
-import cv2 as cv
-
-class MobileNetV1:
-    def __init__(self, modelPath, labelPath=None, topK=1, backendId=0, targetId=0):
-        self.model_path = modelPath
-        self.label_path = labelPath
-        assert topK >= 1
-        self.top_k = topK
-        self.backend_id = backendId
-        self.target_id = targetId
-
-        self.model = cv.dnn.readNet(self.model_path)
-        self.model.setPreferableBackend(self.backend_id)
-        self.model.setPreferableTarget(self.target_id)
-
-        self.input_names = ''
-        self.output_names = ''
-        self.input_size = [224, 224]
-        self.mean=[0.485, 0.456, 0.406]
-        self.std=[0.229, 0.224, 0.225]
-
-        # load labels
-        self._labels = self._load_labels()
-
-    def _load_labels(self):
-        labels = []
-        if self.label_path is not None:
-            with open(self.label_path, 'r') as f:
-                for line in f:
-                    labels.append(line.strip())
-        return labels
-
-    @property
-    def name(self):
-        return self.__class__.__name__
-
-    def setBackend(self, backendId):
-        self.backend_id = backendId
-        self.model.setPreferableBackend(self.backend_id)
-
-    def setTarget(self, targetId):
-        self.target_id = targetId
-        self.model.setPreferableTarget(self.target_id)
-
-    def _preprocess(self, image):
-        input_blob = (image / 255.0 - self.mean) / self.std
-        input_blob = input_blob.transpose(2, 0, 1)
-        input_blob = input_blob[np.newaxis, :, :, :]
-        input_blob = input_blob.astype(np.float32)
-        return input_blob
-
-    def infer(self, image):
-        # Preprocess
-        input_blob = self._preprocess(image)
-
-        # Forward
-        self.model.setInput(input_blob, self.input_names)
-        output_blob = self.model.forward(self.output_names)
-
-        # Postprocess
-        results = self._postprocess(output_blob)
-
-        return results
-
-    def _postprocess(self, output_blob):
-        batched_class_id_list = []
-        for o in output_blob:
-            class_id_list = o.argsort()[::-1][:self.top_k]
-            batched_class_id_list.append(class_id_list)
-        if len(self._labels) > 0:
-            batched_predicted_labels = []
-            for class_id_list in batched_class_id_list:
-                predicted_labels = []
-                for class_id in class_id_list:
-                    predicted_labels.append(self._labels[class_id])
-                batched_predicted_labels.append(predicted_labels)
-            return batched_predicted_labels
-        else:
-            return batched_class_id_list
-

models/image_classification_mobilenet/mobilenet_v2.py

-import numpy as np
-import cv2 as cv
-
-class MobileNetV2:
-    def __init__(self, modelPath, labelPath=None, topK=1, backendId=0, targetId=0):
-        self.model_path = modelPath
-        self.label_path = labelPath
-        assert topK >= 1
-        self.top_k = topK
-        self.backend_id = backendId
-        self.target_id = targetId
-
-        self.model = cv.dnn.readNet(self.model_path)
-        self.model.setPreferableBackend(self.backend_id)
-        self.model.setPreferableTarget(self.target_id)
-
-        self.input_names = ''
-        self.output_names = ''
-        self.input_size = [224, 224]
-        self.mean=[0.485, 0.456, 0.406]
-        self.std=[0.229, 0.224, 0.225]
-
-        # load labels
-        self._labels = self._load_labels()
-
-    def _load_labels(self):
-        labels = []
-        if self.label_path is not None:
-            with open(self.label_path, 'r') as f:
-                for line in f:
-                    labels.append(line.strip())
-        return labels
-
-    @property
-    def name(self):
-        return self.__class__.__name__
-
-    def setBackend(self, backendId):
-        self.backend_id = backendId
-        self.model.setPreferableBackend(self.backend_id)
-
-    def setTarget(self, targetId):
-        self.target_id = targetId
-        self.model.setPreferableTarget(self.target_id)
-
-    def _preprocess(self, image):
-        input_blob = (image / 255.0 - self.mean) / self.std
-        input_blob = input_blob.transpose(2, 0, 1)
-        input_blob = input_blob[np.newaxis, :, :, :]
-        input_blob = input_blob.astype(np.float32)
-        return input_blob
-
-    def infer(self, image):
-        # Preprocess
-        input_blob = self._preprocess(image)
-
-        # Forward
-        self.model.setInput(input_blob, self.input_names)
-        output_blob = self.model.forward(self.output_names)
-
-        # Postprocess
-        results = self._postprocess(output_blob)
-
-        return results
-
-    def _postprocess(self, output_blob):
-        batched_class_id_list = []
-        for o in output_blob:
-            class_id_list = o.argsort()[::-1][:self.top_k]
-            batched_class_id_list.append(class_id_list)
-        if len(self._labels) > 0:
-            batched_predicted_labels = []
-            for class_id_list in batched_class_id_list:
-                predicted_labels = []
-                for class_id in class_id_list:
-                    predicted_labels.append(self._labels[class_id])
-                batched_predicted_labels.append(predicted_labels)
-            return batched_predicted_labels
-        else:
-            return batched_class_id_list
-

models/image_classification_ppresnet/demo.py

@@ -36,12 +36,11 @@ parser.add_argument('--input', '-i', type=str, help='Usage: Set input path to a
 parser.add_argument('--model', '-m', type=str, default='image_classification_ppresnet50_2022jan.onnx', help='Usage: Set model path, defaults to image_classification_ppresnet50_2022jan.onnx.')
 parser.add_argument('--backend', '-b', type=int, default=backends[0], help=help_msg_backends.format(*backends))
 parser.add_argument('--target', '-t', type=int, default=targets[0], help=help_msg_targets.format(*targets))
-parser.add_argument('--label', '-l', type=str, default='./imagenet_labels.txt', help='Usage: Set path to the different labels that will be used during the detection. Default list found in imagenet_labels.txt')
 args = parser.parse_args()
 
 if __name__ == '__main__':
     # Instantiate ResNet
-    model = PPResNet(modelPath=args.model, labelPath=args.label, backendId=args.backend, targetId=args.target)
+    model = PPResNet(modelPath=args.model, backendId=args.backend, targetId=args.target)
 
     # Read image and get a 224x224 crop from a 256x256 resized
     image = cv.imread(args.input)
@@ -54,4 +53,3 @@ if __name__ == '__main__':
 
     # Print result
     print('label: {}'.format(result))
-

models/image_classification_ppresnet/imagenet_labels.txt

-tench
-goldfish
-great white shark
-tiger shark
-hammerhead
-electric ray
-stingray
-cock
-hen
-ostrich
-brambling
-goldfinch
-house finch
-junco
-indigo bunting
-robin
-bulbul
-jay
-magpie
-chickadee
-water ouzel
-kite
-bald eagle
-vulture
-great grey owl
-European fire salamander
-common newt
-eft
-spotted salamander
-axolotl
-bullfrog
-tree frog
-tailed frog
-loggerhead
-leatherback turtle
-mud turtle
-terrapin
-box turtle
-banded gecko
-common iguana
-American chameleon
-whiptail
-agama
-frilled lizard
-alligator lizard
-Gila monster
-green lizard
-African chameleon
-Komodo dragon
-African crocodile
-American alligator
-triceratops
-thunder snake
-ringneck snake
-hognose snake
-green snake
-king snake
-garter snake
-water snake
-vine snake
-night snake
-boa constrictor
-rock python
-Indian cobra
-green mamba
-sea snake
-horned viper
-diamondback
-sidewinder
-trilobite
-harvestman
-scorpion
-black and gold garden spider
-barn spider
-garden spider
-black widow
-tarantula
-wolf spider
-tick
-centipede
-black grouse
-ptarmigan
-ruffed grouse
-prairie chicken
-peacock
-quail
-partridge
-African grey
-macaw
-sulphur-crested cockatoo
-lorikeet
-coucal
-bee eater
-hornbill
-hummingbird
-jacamar
-toucan
-drake
-red-breasted merganser
-goose
-black swan
-tusker
-echidna
-platypus
-wallaby
-koala
-wombat
-jellyfish
-sea anemone
-brain coral
-flatworm
-nematode
-conch
-snail
-slug
-sea slug
-chiton
-chambered nautilus
-Dungeness crab
-rock crab
-fiddler crab
-king crab
-American lobster
-spiny lobster
-crayfish
-hermit crab
-isopod
-white stork
-black stork
-spoonbill
-flamingo
-little blue heron
-American egret
-bittern
-crane
-limpkin
-European gallinule
-American coot
-bustard
-ruddy turnstone
-red-backed sandpiper
-redshank
-dowitcher
-oystercatcher
-pelican
-king penguin
-albatross
-grey whale
-killer whale
-dugong
-sea lion
-Chihuahua
-Japanese spaniel
-Maltese dog
-Pekinese
-Shih-Tzu
-Blenheim spaniel
-papillon
-toy terrier
-Rhodesian ridgeback
-Afghan hound
-basset
-beagle
-bloodhound
-bluetick
-black-and-tan coonhound
-Walker hound
-English foxhound
-redbone
-borzoi
-Irish wolfhound
-Italian greyhound
-whippet
-Ibizan hound
-Norwegian elkhound
-otterhound
-Saluki
-Scottish deerhound
-Weimaraner
-Staffordshire bullterrier
-American Staffordshire terrier
-Bedlington terrier
-Border terrier
-Kerry blue terrier
-Irish terrier
-Norfolk terrier
-Norwich terrier
-Yorkshire terrier
-wire-haired fox terrier
-Lakeland terrier
-Sealyham terrier
-Airedale
-cairn
-Australian terrier
-Dandie Dinmont
-Boston bull
-miniature schnauzer
-giant schnauzer
-standard schnauzer
-Scotch terrier
-Tibetan terrier
-silky terrier
-soft-coated wheaten terrier
-West Highland white terrier
-Lhasa
-flat-coated retriever
-curly-coated retriever
-golden retriever
-Labrador retriever
-Chesapeake Bay retriever
-German short-haired pointer
-vizsla
-English setter
-Irish setter
-Gordon setter
-Brittany spaniel
-clumber
-English springer
-Welsh springer spaniel
-cocker spaniel
-Sussex spaniel
-Irish water spaniel
-kuvasz
-schipperke
-groenendael
-malinois
-briard
-kelpie
-komondor
-Old English sheepdog
-Shetland sheepdog
-collie
-Border collie
-Bouvier des Flandres
-Rottweiler
-German shepherd
-Doberman
-miniature pinscher
-Greater Swiss Mountain dog
-Bernese mountain dog
-Appenzeller
-EntleBucher
-boxer
-bull mastiff
-Tibetan mastiff
-French bulldog
-Great Dane
-Saint Bernard
-Eskimo dog
-malamute
-Siberian husky
-dalmatian
-affenpinscher
-basenji
-pug
-Leonberg
-Newfoundland
-Great Pyrenees
-Samoyed
-Pomeranian
-chow
-keeshond
-Brabancon griffon
-Pembroke
-Cardigan
-toy poodle
-miniature poodle
-standard poodle
-Mexican hairless
-timber wolf
-white wolf
-red wolf
-coyote
-dingo
-dhole
-African hunting dog
-hyena
-red fox
-kit fox
-Arctic fox
-grey fox
-tabby
-tiger cat
-Persian cat
-Siamese cat
-Egyptian cat
-cougar
-lynx
-leopard
-snow leopard
-jaguar
-lion
-tiger
-cheetah
-brown bear
-American black bear
-ice bear
-sloth bear
-mongoose
-meerkat
-tiger beetle
-ladybug
-ground beetle
-long-horned beetle
-leaf beetle
-dung beetle
-rhinoceros beetle
-weevil
-fly
-bee
-ant
-grasshopper
-cricket
-walking stick
-cockroach
-mantis
-cicada
-leafhopper
-lacewing
-dragonfly
-damselfly
-admiral
-ringlet
-monarch
-cabbage butterfly
-sulphur butterfly
-lycaenid
-starfish
-sea urchin
-sea cucumber
-wood rabbit
-hare
-Angora
-hamster
-porcupine
-fox squirrel
-marmot
-beaver
-guinea pig
-sorrel
-zebra
-hog
-wild boar
-warthog
-hippopotamus
-ox
-water buffalo
-bison
-ram
-bighorn
-ibex
-hartebeest
-impala
-gazelle
-Arabian camel
-llama
-weasel
-mink
-polecat
-black-footed ferret
-otter
-skunk
-badger
-armadillo
-three-toed sloth
-orangutan
-gorilla
-chimpanzee
-gibbon
-siamang
-guenon
-patas
-baboon
-macaque
-langur
-colobus
-proboscis monkey
-marmoset
-capuchin
-howler monkey
-titi
-spider monkey
-squirrel monkey
-Madagascar cat
-indri
-Indian elephant
-African elephant
-lesser panda
-giant panda
-barracouta
-eel
-coho
-rock beauty
-anemone fish
-sturgeon
-gar
-lionfish
-puffer
-abacus
-abaya
-academic gown
-accordion
-acoustic guitar
-aircraft carrier
-airliner
-airship
-altar
-ambulance
-amphibian
-analog clock
-apiary
-apron
-ashcan
-assault rifle
-backpack
-bakery
-balance beam
-balloon
-ballpoint
-Band Aid
-banjo
-bannister
-barbell
-barber chair
-barbershop
-barn
-barometer
-barrel
-barrow
-baseball
-basketball
-bassinet
-bassoon
-bathing cap
-bath towel
-bathtub
-beach wagon
-beacon
-beaker
-bearskin
-beer bottle
-beer glass
-bell cote
-bib
-bicycle-built-for-two
-bikini
-binder
-binoculars
-birdhouse
-boathouse
-bobsled
-bolo tie
-bonnet
-bookcase
-bookshop
-bottlecap
-bow
-bow tie
-brass
-brassiere
-breakwater
-breastplate
-broom
-bucket
-buckle
-bulletproof vest
-bullet train
-butcher shop
-cab
-caldron
-candle
-cannon
-canoe
-can opener
-cardigan
-car mirror
-carousel
-carpenters kit
-carton
-car wheel
-cash machine
-cassette
-cassette player
-castle
-catamaran
-CD player
-cello
-cellular telephone
-chain
-chainlink fence
-chain mail
-chain saw
-chest
-chiffonier
-chime
-china cabinet
-Christmas stocking
-church
-cinema
-cleaver
-cliff dwelling
-cloak
-clog
-cocktail shaker
-coffee mug
-coffeepot
-coil
-combination lock
-computer keyboard
-confectionery
-container ship
-convertible
-corkscrew
-cornet
-cowboy boot
-cowboy hat
-cradle
-crane
-crash helmet
-crate
-crib
-Crock Pot
-croquet ball
-crutch
-cuirass
-dam
-desk
-desktop computer
-dial telephone
-diaper
-digital clock
-digital watch
-dining table
-dishrag
-dishwasher
-disk brake
-dock
-dogsled
-dome
-doormat
-drilling platform
-drum
-drumstick
-dumbbell
-Dutch oven
-electric fan
-electric guitar
-electric locomotive
-entertainment center
-envelope
-espresso maker
-face powder
-feather boa
-file
-fireboat
-fire engine
-fire screen
-flagpole
-flute
-folding chair
-football helmet
-forklift
-fountain
-fountain pen
-four-poster
-freight car
-French horn
-frying pan
-fur coat
-garbage truck
-gasmask
-gas pump
-goblet
-go-kart
-golf ball
-golfcart
-gondola
-gong
-gown
-grand piano
-greenhouse
-grille
-grocery store
-guillotine
-hair slide
-hair spray
-half track
-hammer
-hamper
-hand blower
-hand-held computer
-handkerchief
-hard disc
-harmonica
-harp
-harvester
-hatchet
-holster
-home theater
-honeycomb
-hook
-hoopskirt
-horizontal bar
-horse cart
-hourglass
-iPod
-iron
-jack-o-lantern
-jean
-jeep
-jersey
-jigsaw puzzle
-jinrikisha
-joystick
-kimono
-knee pad
-knot
-lab coat
-ladle
-lampshade
-laptop
-lawn mower
-lens cap
-letter opener
-library
-lifeboat
-lighter
-limousine
-liner
-lipstick
-Loafer
-lotion
-loudspeaker
-loupe
-lumbermill
-magnetic compass
-mailbag
-mailbox
-maillot
-maillot
-manhole cover
-maraca
-marimba
-mask
-matchstick
-maypole
-maze
-measuring cup
-medicine chest
-megalith
-microphone
-microwave
-military uniform
-milk can
-minibus
-miniskirt
-minivan
-missile
-mitten
-mixing bowl
-mobile home
-Model T
-modem
-monastery
-monitor
-moped
-mortar
-mortarboard
-mosque
-mosquito net
-motor scooter
-mountain bike
-mountain tent
-mouse
-mousetrap
-moving van
-muzzle
-nail
-neck brace
-necklace
-nipple
-notebook
-obelisk
-oboe
-ocarina
-odometer
-oil filter
-organ
-oscilloscope
-overskirt
-oxcart
-oxygen mask
-packet
-paddle
-paddlewheel
-padlock
-paintbrush
-pajama
-palace
-panpipe
-paper towel
-parachute
-parallel bars
-park bench
-parking meter
-passenger car
-patio
-pay-phone
-pedestal
-pencil box
-pencil sharpener
-perfume
-Petri dish
-photocopier
-pick
-pickelhaube
-picket fence
-pickup
-pier
-piggy bank
-pill bottle
-pillow
-ping-pong ball
-pinwheel
-pirate
-pitcher
-plane
-planetarium
-plastic bag
-plate rack
-plow
-plunger
-Polaroid camera
-pole
-police van
-poncho
-pool table
-pop bottle
-pot
-potters wheel
-power drill
-prayer rug
-printer
-prison
-projectile
-projector
-puck
-punching bag
-purse
-quill
-quilt
-racer
-racket
-radiator
-radio
-radio telescope
-rain barrel
-recreational vehicle
-reel
-reflex camera
-refrigerator
-remote control
-restaurant
-revolver
-rifle
-rocking chair
-rotisserie
-rubber eraser
-rugby ball
-rule
-running shoe
-safe
-safety pin
-saltshaker
-sandal
-sarong
-sax
-scabbard
-scale
-school bus
-schooner
-scoreboard
-screen
-screw
-screwdriver
-seat belt
-sewing machine
-shield
-shoe shop
-shoji
-shopping basket
-shopping cart
-shovel
-shower cap
-shower curtain
-ski
-ski mask
-sleeping bag
-slide rule
-sliding door
-slot
-snorkel
-snowmobile
-snowplow
-soap dispenser
-soccer ball
-sock
-solar dish
-sombrero
-soup bowl
-space bar
-space heater
-space shuttle
-spatula
-speedboat
-spider web
-spindle
-sports car
-spotlight
-stage
-steam locomotive
-steel arch bridge
-steel drum
-stethoscope
-stole
-stone wall
-stopwatch
-stove
-strainer
-streetcar
-stretcher
-studio couch
-stupa
-submarine
-suit
-sundial
-sunglass
-sunglasses
-sunscreen
-suspension bridge
-swab
-sweatshirt
-swimming trunks
-swing
-switch
-syringe
-table lamp
-tank
-tape player
-teapot
-teddy
-television
-tennis ball
-thatch
-theater curtain
-thimble
-thresher
-throne
-tile roof
-toaster
-tobacco shop
-toilet seat
-torch
-totem pole
-tow truck
-toyshop
-tractor
-trailer truck
-tray
-trench coat
-tricycle
-trimaran
-tripod
-triumphal arch
-trolleybus
-trombone
-tub
-turnstile
-typewriter keyboard
-umbrella
-unicycle
-upright
-vacuum
-vase
-vault
-velvet
-vending machine
-vestment
-viaduct
-violin
-volleyball
-waffle iron
-wall clock
-wallet
-wardrobe
-warplane
-washbasin
-washer
-water bottle
-water jug
-water tower
-whiskey jug
-whistle
-wig
-window screen
-window shade
-Windsor tie
-wine bottle
-wing
-wok
-wooden spoon
-wool
-worm fence
-wreck
-yawl
-yurt
-web site
-comic book
-crossword puzzle
-street sign
-traffic light
-book jacket
-menu
-plate
-guacamole
-consomme
-hot pot
-trifle
-ice cream
-ice lolly
-French loaf
-bagel
-pretzel
-cheeseburger
-hotdog
-mashed potato
-head cabbage
-broccoli
-cauliflower
-zucchini
-spaghetti squash
-acorn squash
-butternut squash
-cucumber
-artichoke
-bell pepper
-cardoon
-mushroom
-Granny Smith
-strawberry
-orange
-lemon
-fig
-pineapple
-banana
-jackfruit
-custard apple
-pomegranate
-hay
-carbonara
-chocolate sauce
-dough
-meat loaf
-pizza
-potpie
-burrito
-red wine
-espresso
-cup
-eggnog
-alp
-bubble
-cliff
-coral reef
-geyser
-lakeside
-promontory
-sandbar
-seashore
-valley
-volcano
-ballplayer
-groom
-scuba diver
-rapeseed
-daisy
-yellow ladys slipper
-corn
-acorn
-hip
-buckeye
-coral fungus
-agaric
-gyromitra
-stinkhorn
-earthstar
-hen-of-the-woods
-bolete
-ear
-toilet tissue

models/image_classification_ppresnet/ppresnet.py

@@ -9,9 +9,8 @@ import numpy as np
 import cv2 as cv
 
 class PPResNet:
-    def __init__(self, modelPath, labelPath=None, topK=1, backendId=0, targetId=0):
+    def __init__(self, modelPath, topK=1, backendId=0, targetId=0):
         self._modelPath = modelPath
-        self._labelPath = labelPath
         assert topK >= 1
         self._topK = topK
         self._backendId = backendId
@@ -31,12 +30,7 @@ class PPResNet:
         self._labels = self._load_labels()
 
     def _load_labels(self):
-        labels = []
-        if self._labelPath is not None:
-            with open(self._labelPath, 'r') as f:
-                for line in f:
-                    labels.append(line.strip())
-        return labels
+        return self.LABELS_IMAGENET_1K.splitlines()
 
     @property
     def name(self):
@@ -88,3 +82,1003 @@ class PPResNet:
         else:
             return batched_class_id_list
 
+    LABELS_IMAGENET_1K = '''tench
+goldfish
+great white shark
+tiger shark
+hammerhead
+electric ray
+stingray
+cock
+hen
+ostrich
+brambling
+goldfinch
+house finch
+junco
+indigo bunting
+robin
+bulbul
+jay
+magpie
+chickadee
+water ouzel
+kite
+bald eagle
+vulture
+great grey owl
+European fire salamander
+common newt
+eft
+spotted salamander
+axolotl
+bullfrog
+tree frog
+tailed frog
+loggerhead
+leatherback turtle
+mud turtle
+terrapin
+box turtle
+banded gecko
+common iguana
+American chameleon
+whiptail
+agama
+frilled lizard
+alligator lizard
+Gila monster
+green lizard
+African chameleon
+Komodo dragon
+African crocodile
+American alligator
+triceratops
+thunder snake
+ringneck snake
+hognose snake
+green snake
+king snake
+garter snake
+water snake
+vine snake
+night snake
+boa constrictor
+rock python
+Indian cobra
+green mamba
+sea snake
+horned viper
+diamondback
+sidewinder
+trilobite
+harvestman
+scorpion
+black and gold garden spider
+barn spider
+garden spider
+black widow
+tarantula
+wolf spider
+tick
+centipede
+black grouse
+ptarmigan
+ruffed grouse
+prairie chicken
+peacock
+quail
+partridge
+African grey
+macaw
+sulphur-crested cockatoo
+lorikeet
+coucal
+bee eater
+hornbill
+hummingbird
+jacamar
+toucan
+drake
+red-breasted merganser
+goose
+black swan
+tusker
+echidna
+platypus
+wallaby
+koala
+wombat
+jellyfish
+sea anemone
+brain coral
+flatworm
+nematode
+conch
+snail
+slug
+sea slug
+chiton
+chambered nautilus
+Dungeness crab
+rock crab
+fiddler crab
+king crab
+American lobster
+spiny lobster
+crayfish
+hermit crab
+isopod
+white stork
+black stork
+spoonbill
+flamingo
+little blue heron
+American egret
+bittern
+crane
+limpkin
+European gallinule
+American coot
+bustard
+ruddy turnstone
+red-backed sandpiper
+redshank
+dowitcher
+oystercatcher
+pelican
+king penguin
+albatross
+grey whale
+killer whale
+dugong
+sea lion
+Chihuahua
+Japanese spaniel
+Maltese dog
+Pekinese
+Shih-Tzu
+Blenheim spaniel
+papillon
+toy terrier
+Rhodesian ridgeback
+Afghan hound
+basset
+beagle
+bloodhound
+bluetick
+black-and-tan coonhound
+Walker hound
+English foxhound
+redbone
+borzoi
+Irish wolfhound
+Italian greyhound
+whippet
+Ibizan hound
+Norwegian elkhound
+otterhound
+Saluki
+Scottish deerhound
+Weimaraner
+Staffordshire bullterrier
+American Staffordshire terrier
+Bedlington terrier
+Border terrier
+Kerry blue terrier
+Irish terrier
+Norfolk terrier
+Norwich terrier
+Yorkshire terrier
+wire-haired fox terrier
+Lakeland terrier
+Sealyham terrier
+Airedale
+cairn
+Australian terrier
+Dandie Dinmont
+Boston bull
+miniature schnauzer
+giant schnauzer
+standard schnauzer
+Scotch terrier
+Tibetan terrier
+silky terrier
+soft-coated wheaten terrier
+West Highland white terrier
+Lhasa
+flat-coated retriever
+curly-coated retriever
+golden retriever
+Labrador retriever
+Chesapeake Bay retriever
+German short-haired pointer
+vizsla
+English setter
+Irish setter
+Gordon setter
+Brittany spaniel
+clumber
+English springer
+Welsh springer spaniel
+cocker spaniel
+Sussex spaniel
+Irish water spaniel
+kuvasz
+schipperke
+groenendael
+malinois
+briard
+kelpie
+komondor
+Old English sheepdog
+Shetland sheepdog
+collie
+Border collie
+Bouvier des Flandres
+Rottweiler
+German shepherd
+Doberman
+miniature pinscher
+Greater Swiss Mountain dog
+Bernese mountain dog
+Appenzeller
+EntleBucher
+boxer
+bull mastiff
+Tibetan mastiff
+French bulldog
+Great Dane
+Saint Bernard
+Eskimo dog
+malamute
+Siberian husky
+dalmatian
+affenpinscher
+basenji
+pug
+Leonberg
+Newfoundland
+Great Pyrenees
+Samoyed
+Pomeranian
+chow
+keeshond
+Brabancon griffon
+Pembroke
+Cardigan
+toy poodle
+miniature poodle
+standard poodle
+Mexican hairless
+timber wolf
+white wolf
+red wolf
+coyote
+dingo
+dhole
+African hunting dog
+hyena
+red fox
+kit fox
+Arctic fox
+grey fox
+tabby
+tiger cat
+Persian cat
+Siamese cat
+Egyptian cat
+cougar
+lynx
+leopard
+snow leopard
+jaguar
+lion
+tiger
+cheetah
+brown bear
+American black bear
+ice bear
+sloth bear
+mongoose
+meerkat
+tiger beetle
+ladybug
+ground beetle
+long-horned beetle
+leaf beetle
+dung beetle
+rhinoceros beetle
+weevil
+fly
+bee
+ant
+grasshopper
+cricket
+walking stick
+cockroach
+mantis
+cicada
+leafhopper
+lacewing
+dragonfly
+damselfly
+admiral
+ringlet
+monarch
+cabbage butterfly
+sulphur butterfly
+lycaenid
+starfish
+sea urchin
+sea cucumber
+wood rabbit
+hare
+Angora
+hamster
+porcupine
+fox squirrel
+marmot
+beaver
+guinea pig
+sorrel
+zebra
+hog
+wild boar
+warthog
+hippopotamus
+ox
+water buffalo
+bison
+ram
+bighorn
+ibex
+hartebeest
+impala
+gazelle
+Arabian camel
+llama
+weasel
+mink
+polecat
+black-footed ferret
+otter
+skunk
+badger
+armadillo
+three-toed sloth
+orangutan
+gorilla
+chimpanzee
+gibbon
+siamang
+guenon
+patas
+baboon
+macaque
+langur
+colobus
+proboscis monkey
+marmoset
+capuchin
+howler monkey
+titi
+spider monkey
+squirrel monkey
+Madagascar cat
+indri
+Indian elephant
+African elephant
+lesser panda
+giant panda
+barracouta
+eel
+coho
+rock beauty
+anemone fish
+sturgeon
+gar
+lionfish
+puffer
+abacus
+abaya
+academic gown
+accordion
+acoustic guitar
+aircraft carrier
+airliner
+airship
+altar
+ambulance
+amphibian
+analog clock
+apiary
+apron
+ashcan
+assault rifle
+backpack
+bakery
+balance beam
+balloon
+ballpoint
+Band Aid
+banjo
+bannister
+barbell
+barber chair
+barbershop
+barn
+barometer
+barrel
+barrow
+baseball
+basketball
+bassinet
+bassoon
+bathing cap
+bath towel
+bathtub
+beach wagon
+beacon
+beaker
+bearskin
+beer bottle
+beer glass
+bell cote
+bib
+bicycle-built-for-two
+bikini
+binder
+binoculars
+birdhouse
+boathouse
+bobsled
+bolo tie
+bonnet
+bookcase
+bookshop
+bottlecap
+bow
+bow tie
+brass
+brassiere
+breakwater
+breastplate
+broom
+bucket
+buckle
+bulletproof vest
+bullet train
+butcher shop
+cab
+caldron
+candle
+cannon
+canoe
+can opener
+cardigan
+car mirror
+carousel
+carpenters kit
+carton
+car wheel
+cash machine
+cassette
+cassette player
+castle
+catamaran
+CD player
+cello
+cellular telephone
+chain
+chainlink fence
+chain mail
+chain saw
+chest
+chiffonier
+chime
+china cabinet
+Christmas stocking
+church
+cinema
+cleaver
+cliff dwelling
+cloak
+clog
+cocktail shaker
+coffee mug
+coffeepot
+coil
+combination lock
+computer keyboard
+confectionery
+container ship
+convertible
+corkscrew
+cornet
+cowboy boot
+cowboy hat
+cradle
+crane
+crash helmet
+crate
+crib
+Crock Pot
+croquet ball
+crutch
+cuirass
+dam
+desk
+desktop computer
+dial telephone
+diaper
+digital clock
+digital watch
+dining table
+dishrag
+dishwasher
+disk brake
+dock
+dogsled
+dome
+doormat
+drilling platform
+drum
+drumstick
+dumbbell
+Dutch oven
+electric fan
+electric guitar
+electric locomotive
+entertainment center
+envelope
+espresso maker
+face powder
+feather boa
+file
+fireboat
+fire engine
+fire screen
+flagpole
+flute
+folding chair
+football helmet
+forklift
+fountain
+fountain pen
+four-poster
+freight car
+French horn
+frying pan
+fur coat
+garbage truck
+gasmask
+gas pump
+goblet
+go-kart
+golf ball
+golfcart
+gondola
+gong
+gown
+grand piano
+greenhouse
+grille
+grocery store
+guillotine
+hair slide
+hair spray
+half track
+hammer
+hamper
+hand blower
+hand-held computer
+handkerchief
+hard disc
+harmonica
+harp
+harvester
+hatchet
+holster
+home theater
+honeycomb
+hook
+hoopskirt
+horizontal bar
+horse cart
+hourglass
+iPod
+iron
+jack-o-lantern
+jean
+jeep
+jersey
+jigsaw puzzle
+jinrikisha
+joystick
+kimono
+knee pad
+knot
+lab coat
+ladle
+lampshade
+laptop
+lawn mower
+lens cap
+letter opener
+library
+lifeboat
+lighter
+limousine
+liner
+lipstick
+Loafer
+lotion
+loudspeaker
+loupe
+lumbermill
+magnetic compass
+mailbag
+mailbox
+maillot
+maillot
+manhole cover
+maraca
+marimba
+mask
+matchstick
+maypole
+maze
+measuring cup
+medicine chest
+megalith
+microphone
+microwave
+military uniform
+milk can
+minibus
+miniskirt
+minivan
+missile
+mitten
+mixing bowl
+mobile home
+Model T
+modem
+monastery
+monitor
+moped
+mortar
+mortarboard
+mosque
+mosquito net
+motor scooter
+mountain bike
+mountain tent
+mouse
+mousetrap
+moving van
+muzzle
+nail
+neck brace
+necklace
+nipple
+notebook
+obelisk
+oboe
+ocarina
+odometer
+oil filter
+organ
+oscilloscope
+overskirt
+oxcart
+oxygen mask
+packet
+paddle
+paddlewheel
+padlock
+paintbrush
+pajama
+palace
+panpipe
+paper towel
+parachute
+parallel bars
+park bench
+parking meter
+passenger car
+patio
+pay-phone
+pedestal
+pencil box
+pencil sharpener
+perfume
+Petri dish
+photocopier
+pick
+pickelhaube
+picket fence
+pickup
+pier
+piggy bank
+pill bottle
+pillow
+ping-pong ball
+pinwheel
+pirate
+pitcher
+plane
+planetarium
+plastic bag
+plate rack
+plow
+plunger
+Polaroid camera
+pole
+police van
+poncho
+pool table
+pop bottle
+pot
+potters wheel
+power drill
+prayer rug
+printer
+prison
+projectile
+projector
+puck
+punching bag
+purse
+quill
+quilt
+racer
+racket
+radiator
+radio
+radio telescope
+rain barrel
+recreational vehicle
+reel
+reflex camera
+refrigerator
+remote control
+restaurant
+revolver
+rifle
+rocking chair
+rotisserie
+rubber eraser
+rugby ball
+rule
+running shoe
+safe
+safety pin
+saltshaker
+sandal
+sarong
+sax
+scabbard
+scale
+school bus
+schooner
+scoreboard
+screen
+screw
+screwdriver
+seat belt
+sewing machine
+shield
+shoe shop
+shoji
+shopping basket
+shopping cart
+shovel
+shower cap
+shower curtain
+ski
+ski mask
+sleeping bag
+slide rule
+sliding door
+slot
+snorkel
+snowmobile
+snowplow
+soap dispenser
+soccer ball
+sock
+solar dish
+sombrero
+soup bowl
+space bar
+space heater
+space shuttle
+spatula
+speedboat
+spider web
+spindle
+sports car
+spotlight
+stage
+steam locomotive
+steel arch bridge
+steel drum
+stethoscope
+stole
+stone wall
+stopwatch
+stove
+strainer
+streetcar
+stretcher
+studio couch
+stupa
+submarine
+suit
+sundial
+sunglass
+sunglasses
+sunscreen
+suspension bridge
+swab
+sweatshirt
+swimming trunks
+swing
+switch
+syringe
+table lamp
+tank
+tape player
+teapot
+teddy
+television
+tennis ball
+thatch
+theater curtain
+thimble
+thresher
+throne
+tile roof
+toaster
+tobacco shop
+toilet seat
+torch
+totem pole
+tow truck
+toyshop
+tractor
+trailer truck
+tray
+trench coat
+tricycle
+trimaran
+tripod
+triumphal arch
+trolleybus
+trombone
+tub
+turnstile
+typewriter keyboard
+umbrella
+unicycle
+upright
+vacuum
+vase
+vault
+velvet
+vending machine
+vestment
+viaduct
+violin
+volleyball
+waffle iron
+wall clock
+wallet
+wardrobe
+warplane
+washbasin
+washer
+water bottle
+water jug
+water tower
+whiskey jug
+whistle
+wig
+window screen
+window shade
+Windsor tie
+wine bottle
+wing
+wok
+wooden spoon
+wool
+worm fence
+wreck
+yawl
+yurt
+web site
+comic book
+crossword puzzle
+street sign
+traffic light
+book jacket
+menu
+plate
+guacamole
+consomme
+hot pot
+trifle
+ice cream
+ice lolly
+French loaf
+bagel
+pretzel
+cheeseburger
+hotdog
+mashed potato
+head cabbage
+broccoli
+cauliflower
+zucchini
+spaghetti squash
+acorn squash
+butternut squash
+cucumber
+artichoke
+bell pepper
+cardoon
+mushroom
+Granny Smith
+strawberry
+orange
+lemon
+fig
+pineapple
+banana
+jackfruit
+custard apple
+pomegranate
+hay
+carbonara
+chocolate sauce
+dough
+meat loaf
+pizza
+potpie
+burrito
+red wine
+espresso
+cup
+eggnog
+alp
+bubble
+cliff
+coral reef
+geyser
+lakeside
+promontory
+sandbar
+seashore
+valley
+volcano
+ballplayer
+groom
+scuba diver
+rapeseed
+daisy
+yellow ladys slipper
+corn
+acorn
+hip
+buckeye
+coral fungus
+agaric
+gyromitra
+stinkhorn
+earthstar
+hen-of-the-woods
+bolete
+ear
+toilet tissue'''

models/object_tracking_dasiamrpn/dasiamrpn.py

@@ -8,7 +8,7 @@ import numpy as np
 import cv2 as cv
 
 class DaSiamRPN:
-    def __init__(self, model_path, kernel_cls1_path, kernel_r1_path, backend_id=0, target_id=0):
+    def __init__(self, kernel_cls1_path, kernel_r1_path, model_path, backend_id=0, target_id=0):
         self._model_path = model_path
         self._kernel_cls1_path = kernel_cls1_path
         self._kernel_r1_path = kernel_r1_path

models/object_tracking_dasiamrpn/demo.py

@@ -52,9 +52,9 @@ def visualize(image, bbox, score, isLocated, fps=None, box_color=(0, 255, 0),tex
 if __name__ == '__main__':
     # Instantiate DaSiamRPN
     model = DaSiamRPN(
-        model_path=args.model_path,
         kernel_cls1_path=args.kernel_cls1_path,
-        kernel_r1_path=args.kernel_r1_path
+        kernel_r1_path=args.kernel_r1_path,
+        model_path=args.model_path,
     )
 
     # Read from args.input
@@ -92,4 +92,4 @@ if __name__ == '__main__':
         # Visualize
         frame = visualize(frame, bbox, score, isLocated, fps=tm.getFPS())
         cv.imshow('DaSiamRPN Demo', frame)
-        tm.reset()
\ No newline at end of file
+        tm.reset()

models/text_recognition_crnn/charset_36_EN.txt

-0
-1
-2
-3
-4
-5
-6
-7
-8
-9
-a
-b
-c
-d
-e
-f
-g
-h
-i
-j
-k
-l
-m
-n
-o
-p
-q
-r
-s
-t
-u
-v
-w
-x
-y
-z

models/text_recognition_crnn/charset_94_CH.txt

-0
-1
-2
-3
-4
-5
-6
-7
-8
-9
-a
-b
-c
-d
-e
-f
-g
-h
-i
-j
-k
-l
-m
-n
-o
-p
-q
-r
-s
-t
-u
-v
-w
-x
-y
-z
-A
-B
-C
-D
-E
-F
-G
-H
-I
-J
-K
-L
-M
-N
-O
-P
-Q
-R
-S
-T
-U
-V
-W
-X
-Y
-Z
-!
-"
-#
-$
-%
-&
-'
-(
-)
-*
-+
-,
--
-.
-/
-:
-;
-<
-=
->
-?
-@
-[
-\
-]
-^
-_
-`
-{
-|
-}
-~

models/text_recognition_crnn/demo.py

@@ -41,7 +41,6 @@ parser.add_argument('--input', '-i', type=str, help='Usage: Set path to the inpu
 parser.add_argument('--model', '-m', type=str, default='text_recognition_CRNN_EN_2021sep.onnx', help='Usage: Set model path, defaults to text_recognition_CRNN_EN_2021sep.onnx.')
 parser.add_argument('--backend', '-b', type=int, default=backends[0], help=help_msg_backends.format(*backends))
 parser.add_argument('--target', '-t', type=int, default=targets[0], help=help_msg_targets.format(*targets))
-parser.add_argument('--charset', '-c', type=str, default='charset_36_EN.txt', help='Usage: Set the path to the charset file corresponding to the selected model.')
 parser.add_argument('--save', '-s', type=str, default=False, help='Usage: Set “True” to save a file with results. Invalid in case of camera input. Default will be set to “False”.')
 parser.add_argument('--vis', '-v', type=str2bool, default=True, help='Usage: Default will be set to “True” and will open a new window to show results. Set to “False” to stop visualizations from being shown. Invalid in case of camera input.')
 parser.add_argument('--width', type=int, default=736,
@@ -61,7 +60,7 @@ def visualize(image, boxes, texts, color=(0, 255, 0), isClosed=True, thickness=2
 
 if __name__ == '__main__':
     # Instantiate CRNN for text recognition
-    recognizer = CRNN(modelPath=args.model, charsetPath=args.charset)
+    recognizer = CRNN(modelPath=args.model)
     # Instantiate DB for text detection
     detector = DB(modelPath='../text_detection_db/text_detection_DB_IC15_resnet18_2021sep.onnx',
                   inputSize=[args.width, args.height],

tools/eval/eval.py

@@ -21,63 +21,63 @@ parser.add_argument("--dataset_root", "-dr", type=str, required=True, help="Root
 args = parser.parse_args()
 
 models = dict(
-        mobilenetv1=dict(
-            name="MobileNetV1",
-            topic="image_classification",
-            modelPath=os.path.join(root_dir, "models/image_classification_mobilenet/image_classification_mobilenetv1_2022apr.onnx"),
-            topK=5),
-        mobilenetv1_q=dict(
-            name="MobileNetV1",
-            topic="image_classification",
-            modelPath=os.path.join(root_dir, "models/image_classification_mobilenet/image_classification_mobilenetv1_2022apr-int8-quantized.onnx"),
-            topK=5),
-        mobilenetv2=dict(
-            name="MobileNetV2",
-            topic="image_classification",
-            modelPath=os.path.join(root_dir, "models/image_classification_mobilenet/image_classification_mobilenetv2_2022apr.onnx"),
-            topK=5),
-        mobilenetv2_q=dict(
-            name="MobileNetV2",
-            topic="image_classification",
-            modelPath=os.path.join(root_dir, "models/image_classification_mobilenet/image_classification_mobilenetv2_2022apr-int8-quantized.onnx"),
-            topK=5),
-        ppresnet=dict(
-            name="PPResNet",
-            topic="image_classification",
-            modelPath=os.path.join(root_dir, "models/image_classification_ppresnet/image_classification_ppresnet50_2022jan.onnx"),
-            topK=5),
-        ppresnet_q=dict(
-            name="PPResNet",
-            topic="image_classification",
-            modelPath=os.path.join(root_dir, "models/image_classification_ppresnet/image_classification_ppresnet50_2022jan-act_int8-wt_int8-quantized.onnx"),
-            topK=5),
-        yunet=dict(
-            name="YuNet",
-            topic="face_detection",
-            modelPath=os.path.join(root_dir, "models/face_detection_yunet/face_detection_yunet_2022mar.onnx"),
-            topK=5000,
-            confThreshold=0.3,
-            nmsThreshold=0.45),
-        yunet_q=dict(
-            name="YuNet",
-            topic="face_detection",
-            modelPath=os.path.join(root_dir, "models/face_detection_yunet/face_detection_yunet_2022mar-act_int8-wt_int8-quantized.onnx"),
-            topK=5000,
-            confThreshold=0.3,
-            nmsThreshold=0.45),
-        sface=dict(
-            name="SFace",
-            topic="face_recognition",
-            modelPath=os.path.join(root_dir, "models/face_recognition_sface/face_recognition_sface_2021dec.onnx")),
-        sface_q=dict(
-            name="SFace",
-            topic="face_recognition",
-            modelPath=os.path.join(root_dir, "models/face_recognition_sface/face_recognition_sface_2021dec-act_int8-wt_int8-quantized.onnx")),
-        crnn=dict(
-            name="CRNN",
-            topic="text_recognition",
-            modelPath=os.path.join(root_dir, "models/text_recognition_crnn/text_recognition_CRNN_EN_2021sep.onnx"),
-            charsetPath=os.path.join(root_dir, "models/text_recognition_crnn/charset_36_EN.txt")),
+    mobilenetv1=dict(
+        name="MobileNetV1",
+        topic="image_classification",
+        modelPath=os.path.join(root_dir, "models/image_classification_mobilenet/image_classification_mobilenetv1_2022apr.onnx"),
+        topK=5),
+    mobilenetv1_q=dict(
+        name="MobileNetV1",
+        topic="image_classification",
+        modelPath=os.path.join(root_dir, "models/image_classification_mobilenet/image_classification_mobilenetv1_2022apr-int8-quantized.onnx"),
+        topK=5),
+    mobilenetv2=dict(
+        name="MobileNetV2",
+        topic="image_classification",
+        modelPath=os.path.join(root_dir, "models/image_classification_mobilenet/image_classification_mobilenetv2_2022apr.onnx"),
+        topK=5),
+    mobilenetv2_q=dict(
+        name="MobileNetV2",
+        topic="image_classification",
+        modelPath=os.path.join(root_dir, "models/image_classification_mobilenet/image_classification_mobilenetv2_2022apr-int8-quantized.onnx"),
+        topK=5),
+    ppresnet=dict(
+        name="PPResNet",
+        topic="image_classification",
+        modelPath=os.path.join(root_dir, "models/image_classification_ppresnet/image_classification_ppresnet50_2022jan.onnx"),
+        topK=5),
+    ppresnet_q=dict(
+        name="PPResNet",
+        topic="image_classification",
+        modelPath=os.path.join(root_dir, "models/image_classification_ppresnet/image_classification_ppresnet50_2022jan-act_int8-wt_int8-quantized.onnx"),
+        topK=5),
+    yunet=dict(
+        name="YuNet",
+        topic="face_detection",
+        modelPath=os.path.join(root_dir, "models/face_detection_yunet/face_detection_yunet_2022mar.onnx"),
+        topK=5000,
+        confThreshold=0.3,
+        nmsThreshold=0.45),
+    yunet_q=dict(
+        name="YuNet",
+        topic="face_detection",
+        modelPath=os.path.join(root_dir, "models/face_detection_yunet/face_detection_yunet_2022mar-act_int8-wt_int8-quantized.onnx"),
+        topK=5000,
+        confThreshold=0.3,
+        nmsThreshold=0.45),
+    sface=dict(
+        name="SFace",
+        topic="face_recognition",
+        modelPath=os.path.join(root_dir, "models/face_recognition_sface/face_recognition_sface_2021dec.onnx")),
+    sface_q=dict(
+        name="SFace",
+        topic="face_recognition",
+        modelPath=os.path.join(root_dir, "models/face_recognition_sface/face_recognition_sface_2021dec-act_int8-wt_int8-quantized.onnx")),
+    crnn=dict(
+        name="CRNN",
+        topic="text_recognition",
+        modelPath=os.path.join(root_dir, "models/text_recognition_crnn/text_recognition_CRNN_EN_2021sep.onnx"),
+        charsetPath=os.path.join(root_dir, "models/text_recognition_crnn/charset_36_EN.txt")),
 )
 
 datasets = dict(
@@ -107,7 +107,8 @@ def main(args):
 
     model_name = models[model_key].pop("name")
     model_topic = models[model_key].pop("topic")
-    model = MODELS.get(model_name)(**models[model_key])
+    model_handler, _ = MODELS.get(model_name)
+    model = model_handler(**models[model_key])
 
     # Instantiate dataset
     dataset_key = args.dataset.lower()
@@ -124,6 +125,5 @@ def main(args):
     dataset.eval(model)
     dataset.print_result()
 
-
 if __name__ == "__main__":
     main(args)