update mobilenets (#48)

README.md

@@ -23,8 +23,8 @@ Guidelines:
 | [CRNN-EN](./models/text_recognition_crnn)             | 100x32   | 50.21  | 234.32  | 196.15 | 125.30 | ---   |
 | [CRNN-CN](./models/text_recognition_crnn)             | 100x32   | 73.52  | 322.16  | 239.76 | 166.79 | ---   |
 | [PP-ResNet](./models/image_classification_ppresnet)   | 224x224  | 56.05  | 602.58  | 98.64  | 75.45  | ---   |
-| [MobileNet-V1](./models/image_classification_mobilenet)| 224x224 | 7.76   | 85.09   | 20.78  | 45.78  | ---   |
-| [MobileNet-V2](./models/image_classification_mobilenet)| 224x224 | 7.48   | 74.45   | 23.92  | 104.05 | ---   |
+| [MobileNet-V1](./models/image_classification_mobilenet)| 224x224 | 9.04   | 92.25   | 33.18  | 145.66 | ---   |
+| [MobileNet-V2](./models/image_classification_mobilenet)| 224x224 | 8.86   | 74.03   | 31.92  | 146.31 | ---   |
 | [PP-HumanSeg](./models/human_segmentation_pphumanseg) | 192x192  | 19.92  | 105.32  | 67.97  | 74.77  | ---   |
 | [WeChatQRCode](./models/qrcode_wechatqrcode)          | 100x100  | 7.04   | 37.68   | ---    | ---    | ---   |
 | [DaSiamRPN](./models/object_tracking_dasiamrpn)       | 1280x720 | 36.15  | 705.48  | 76.82  | ---    | ---   |

benchmark/benchmark.py

@@ -61,9 +61,7 @@ class Benchmark:
             opencv=cv.dnn.DNN_BACKEND_OPENCV,
             # vkcom=cv.dnn.DNN_BACKEND_VKCOM,
             cuda=cv.dnn.DNN_BACKEND_CUDA,
-            timvx=cv.dnn.DNN_BACKEND_TIMVX
         )
-        self._backend = available_backends[backend_id]
 
         target_id = kwargs.pop('target', 'cpu')
         available_targets = dict(
@@ -76,8 +74,16 @@ class Benchmark:
             cuda=cv.dnn.DNN_TARGET_CUDA,
             cuda_fp16=cv.dnn.DNN_TARGET_CUDA_FP16,
             # hddl=cv.dnn.DNN_TARGET_HDDL,
-            npu=cv.dnn.DNN_TARGET_NPU
         )
+
+        # add extra backends & targets
+        try:
+            available_backends['timvx'] = cv.dnn.DNN_BACKEND_TIMVX
+            available_targets['npu'] = cv.dnn.DNN_TARGET_NPU
+        except:
+            print('OpenCV is not compiled with TIM-VX backend enbaled. See https://github.com/opencv/opencv/wiki/TIM-VX-Backend-For-Running-OpenCV-On-NPU for more details on how to enable TIM-VX backend.')
+
+        self._backend = available_backends[backend_id]
         self._target = available_targets[target_id]
 
         self._benchmark_results = dict()

benchmark/config/image_classification_mobilenetv1.yaml

@@ -16,5 +16,5 @@ Benchmark:
 
 Model:
   name: "MobileNetV1"
-  modelPath: "models/image_classification_mobilenet/mobilenet_v1.onnx"
+  modelPath: "models/image_classification_mobilenet/image_classification_mobilenetv1_2022apr.onnx"
   labelPath: "models/image_classification_mobilenet/imagenet_labels.txt"

benchmark/config/image_classification_mobilenetv2.yaml

@@ -16,5 +16,5 @@ Benchmark:
 
 Model:
   name: "MobileNetV2"
-  modelPath: "models/image_classification_mobilenet/mobilenet_v2.onnx"
+  modelPath: "models/image_classification_mobilenet/image_classification_mobilenetv2_2022apr.onnx"
   labelPath: "models/image_classification_mobilenet/imagenet_labels.txt"

models/image_classification_mobilenet/LICENSE

@@ -1,29 +1,202 @@
-BSD 3-Clause License
-
-Copyright (c) 2017-, Shicai Yang
-All rights reserved.
-
-Redistribution and use in source and binary forms, with or without
-modification, are permitted provided that the following conditions are met:
-
-* Redistributions of source code must retain the above copyright notice, this
-  list of conditions and the following disclaimer.
-
-* Redistributions in binary form must reproduce the above copyright notice,
-  this list of conditions and the following disclaimer in the documentation
-  and/or other materials provided with the distribution.
-
-* Neither the name of the copyright holder nor the names of its
-  contributors may be used to endorse or promote products derived from
-  this software without specific prior written permission.
-
-THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
-AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
-IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
-DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
-FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
-DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
-SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
-CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
-OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
-OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

models/image_classification_mobilenet/README.md

@@ -4,14 +4,6 @@ MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicatio
 
 MobileNetV2: Inverted Residuals and Linear Bottlenecks
 
-Models are taken from https://github.com/shicai/MobileNet-Caffe and converted to ONNX format using [caffe2onnx](https://github.com/asiryan/caffe2onnx):
-```
-python -m caffe2onnx.convert --prototxt mobilenet_deploy.prototxt --caffemodel mobilenet.caffemodel --onnx mobilenet_v1.onnx
-python -m caffe2onnx.convert --prototxt mobilenet_v2_deploy.prototxt --caffemodel mobilenet_v2.caffemodel --onnx mobilenet_v2.onnx
-```
-
-NOTE: Quantized MobileNet V1 & V2 have a great drop in accuracy. We are working on producing higher accuracy MobileNets.
-
 ## Demo
 
 Run the following command to try the demo:
@@ -24,12 +16,11 @@ python demo.py --input /path/to/image --model v2
 
 ## License
 
-Model weights are licensed under [BSD-3-Clause License](./LICENSE).
-Scripts are licensed unser [Apache 2.0 License](../../LICENSE).
+All files in this directory are licensed under [Apache 2.0 License](./LICENSE).
 
 ## Reference
 
 - MobileNet V1: https://arxiv.org/abs/1704.04861
 - MobileNet V2: https://arxiv.org/abs/1801.04381
-- https://github.com/shicai/MobileNet-Caffe
-
+- MobileNet V1 weight and scripts for training: https://github.com/wjc852456/pytorch-mobilenet-v1
+- MobileNet V2 weight: https://github.com/onnx/models/tree/main/vision/classification/mobilenet

models/image_classification_mobilenet/mobilenet_v1.py

@@ -15,8 +15,8 @@ class MobileNetV1:
         self.input_names = ''
         self.output_names = ''
         self.input_size = [224, 224]
-        self.mean = [103.94,116.78,123.68]
-        self.scale = 0.017
+        self.mean=[0.485, 0.456, 0.406]
+        self.std=[0.229, 0.224, 0.225]
 
         # load labels
         self.labels = self._load_labels()
@@ -41,7 +41,11 @@ class MobileNetV1:
         self.model.setPreferableTarget(self.target_id)
 
     def _preprocess(self, image):
-        return cv.dnn.blobFromImage(image, scalefactor=self.scale, size=self.input_size, mean=self.mean)
+        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

models/image_classification_mobilenet/mobilenet_v2.py

@@ -15,8 +15,8 @@ class MobileNetV2:
         self.input_names = ''
         self.output_names = ''
         self.input_size = [224, 224]
-        self.mean = [103.94,116.78,123.68]
-        self.scale = 0.017
+        self.mean=[0.485, 0.456, 0.406]
+        self.std=[0.229, 0.224, 0.225]
 
         # load labels
         self.labels = self._load_labels()
@@ -41,7 +41,11 @@ class MobileNetV2:
         self.model.setPreferableTarget(self.target_id)
 
     def _preprocess(self, image):
-        return cv.dnn.blobFromImage(image, scalefactor=self.scale, size=self.input_size, mean=self.mean)
+        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

tools/quantize/README.md

@@ -1,6 +1,6 @@
-# Quantization with ONNXRUNTIME
+# Quantization with ONNXRUNTIME and Neural Compressor
 
-ONNXRUNTIME is used for quantization in the Zoo.
+[ONNXRUNTIME](https://github.com/microsoft/onnxruntime) and [Neural Compressor](https://github.com/intel/neural-compressor) are used for quantization in the Zoo.
 
 Install dependencies before trying quantization:
 ```shell
@@ -35,4 +35,4 @@ models = dict(
 )
 # quantize the added models
 python quantize.py model1
-```
+```

tools/quantize/inc_configs/mobilenet.yaml

@@ -0,0 +1,98 @@
+#
+# Copyright (c) 2021 Intel Corporation
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+version: 1.0
+
+model:                                               # mandatory. used to specify model specific information.
+  name: mobilenetv2
+  framework: onnxrt_qlinearops                       # mandatory. supported values are tensorflow, pytorch, pytorch_ipex, onnxrt_integer, onnxrt_qlinear or mxnet; allow new framework backend extension.
+
+quantization:                                        # optional. tuning constraints on model-wise for advance user to reduce tuning space.
+  approach: post_training_static_quant               # optional. default value is post_training_static_quant.                          
+  calibration:
+    dataloader:
+      batch_size: 1
+      dataset:
+        ImagenetRaw:
+          data_path: /path/to/imagenet/val
+          image_list: /path/to/imagenet/val.txt      # download from http://dl.caffe.berkeleyvision.org/caffe_ilsvrc12.tar.gz
+      transform:
+        Rescale: {}
+        Resize:
+          size: 256
+        CenterCrop:
+          size: 224
+        Normalize:
+          mean: [0.485, 0.456, 0.406]
+          std: [0.229, 0.224, 0.225]
+        Transpose:
+          perm: [2, 0, 1]
+        Cast:
+          dtype: float32
+evaluation:                                          # optional. required if user doesn't provide eval_func in lpot.Quantization.
+  accuracy:                                          # optional. required if user doesn't provide eval_func in lpot.Quantization.
+    metric:
+      topk: 1                                        # built-in metrics are topk, map, f1, allow user to register new metric.
+    dataloader:
+      batch_size: 1
+      dataset:
+        ImagenetRaw:
+          data_path: /path/to/imagenet/val
+          image_list: /path/to/imagenet/val.txt      # download from http://dl.caffe.berkeleyvision.org/caffe_ilsvrc12.tar.gz
+       transform:
+        Rescale: {}
+        Resize:
+          size: 256
+        CenterCrop:
+          size: 224
+        Normalize:
+          mean: [0.485, 0.456, 0.406]
+          std: [0.229, 0.224, 0.225]
+        Transpose:
+          perm: [2, 0, 1]
+        Cast:
+          dtype: float32
+  performance:                                       # optional. used to benchmark performance of passing model.
+    warmup: 10
+    iteration: 1000
+    configs:
+      cores_per_instance: 4
+      num_of_instance: 1
+    dataloader:
+      batch_size: 1 
+      dataset:
+        ImagenetRaw:
+          data_path: /path/to/imagenet/val
+          image_list: /path/to/imagenet/val.txt      # download from http://dl.caffe.berkeleyvision.org/caffe_ilsvrc12.tar.gz
+      transform:
+        Rescale: {}
+        Resize:
+          size: 256
+        CenterCrop:
+          size: 224
+        Normalize:
+          mean: [0.485, 0.456, 0.406]
+          std: [0.229, 0.224, 0.225]
+        Transpose:
+          perm: [2, 0, 1]
+        Cast:
+          dtype: float32
+
+tuning:
+  accuracy_criterion:
+    relative:  0.02                                  # optional. default value is relative, other value is absolute. this example allows relative accuracy loss: 1%.
+  exit_policy:
+    timeout: 0                                       # optional. tuning timeout (seconds). default value is 0 which means early stop. combine with max_trials field to decide when to exit.
+  random_seed: 9527                                  # optional. random seed for deterministic tuning.

tools/quantize/quantize.py

@@ -10,6 +10,7 @@ import numpy as ny
 import cv2 as cv
 
 import onnx
+from neural_compressor.experimental import Quantization, common as nc_Quantization, nc_common
 from onnx import version_converter
 import onnxruntime
 from onnxruntime.quantization import quantize_static, CalibrationDataReader, QuantType
@@ -31,15 +32,15 @@ class DataReader(CalibrationDataReader):
         blobs = []
         for image_name in os.listdir(image_dir):
             image_name_suffix = image_name.split('.')[-1].lower()
-            if image_name_suffix == 'jpg' or image_name_suffix != 'jpeg':
+            if image_name_suffix != 'jpg' and image_name_suffix != 'jpeg':
                 continue
             img = cv.imread(os.path.join(image_dir, image_name))
             img = self.transforms(img)
             blob = cv.dnn.blobFromImage(img)
             blobs.append(blob)
-        return blobs[:100]
+        return blobs
 
-class Quantize:
+class ORT_Quantize:
     def __init__(self, model_path, calibration_image_dir, transforms=Compose(), per_channel=False, act_type='int8', wt_type='int8'):
         self.type_dict = {"uint8" : QuantType.QUInt8, "int8" : QuantType.QInt8}
 
@@ -77,35 +78,51 @@ class Quantize:
         os.remove('{}-opt.onnx'.format(self.model_path[:-5]))
         print('\tQuantized model saved to {}'.format(output_name))
 
+class INC_Quantize:
+    def __init__(self, model_path, config_path):
+        self.model_path = model_path
+        self.config_path = config_path
+
+    def run(self):
+        print('Quantizing (int8) with Intel\'s Neural Compressor:')
+        print('\tModel: {}'.format(self.model_path))
+        print('\tConfig: {}'.format(self.config_path))
+
+        output_name = '{}-int8-quantized.onnx'.format(self.model_path[:-5])
+
+        model = onnx.load(self.model_path)
+        quantizer = nc_Quantization(self.config_path)
+        quantizer.model = common.Model(model)
+        q_model = quantizer()
+        q_model.save(output_name)
+
 
 models=dict(
-    yunet=Quantize(model_path='../../models/face_detection_yunet/face_detection_yunet_2022mar.onnx',
+    yunet=ORT_Quantize(model_path='../../models/face_detection_yunet/face_detection_yunet_2022mar.onnx',
                    calibration_image_dir='../../benchmark/data/face_detection',
                    transforms=Compose([Resize(size=(160, 120))])),
-    sface=Quantize(model_path='../../models/face_recognition_sface/face_recognition_sface_2021dec.onnx',
+    sface=ORT_Quantize(model_path='../../models/face_recognition_sface/face_recognition_sface_2021dec.onnx',
                    calibration_image_dir='../../benchmark/data/face_recognition',
                    transforms=Compose([Resize(size=(112, 112))])),
-    pphumenseg=Quantize(model_path='../../models/human_segmentation_pphumanseg/human_segmentation_pphumanseg_2021oct.onnx',
+    pphumenseg=ORT_Quantize(model_path='../../models/human_segmentation_pphumanseg/human_segmentation_pphumanseg_2021oct.onnx',
                         calibration_image_dir='../../benchmark/data/human_segmentation',
                         transforms=Compose([Resize(size=(192, 192))])),
-    ppresnet50=Quantize(model_path='../../models/image_classification_ppresnet/image_classification_ppresnet50_2022jan.onnx',
+    ppresnet50=ORT_Quantize(model_path='../../models/image_classification_ppresnet/image_classification_ppresnet50_2022jan.onnx',
                         calibration_image_dir='../../benchmark/data/image_classification',
                         transforms=Compose([Resize(size=(224, 224))])),
-    mobilenetv1=Quantize(model_path='../../models/image_classification_mobilenet/image_classification_mobilenetv1_2022apr.onnx',
-                        calibration_image_dir='../../benchmark/data/image_classification',
-                        transforms=Compose([Resize(size=(256, 256)), CenterCrop(size=(224, 224)), Normalize(mean=[103.94, 116.78, 123.68], std=[0.017, 0.017, 0.017])])),
-    mobilenetv2=Quantize(model_path='../../models/image_classification_mobilenet/image_classification_mobilenetv2_2022apr.onnx',
-                        calibration_image_dir='../../benchmark/data/image_classification',
-                        transforms=Compose([Resize(size=(256, 256)), CenterCrop(size=(224, 224)), Normalize(mean=[103.94, 116.78, 123.68], std=[0.017, 0.017, 0.017])])),
+    mobilenetv1=INC_Quantize(model_path='../../models/image_classification_mobilenet/image_classification_mobilenetv1_2022apr.onnx',
+                             config_path='./inc_configs/mobilenet.yaml'),
+    mobilenetv2=INC_Quantize(model_path='../../models/image_classification_mobilenet/image_classification_mobilenetv2_2022apr.onnx',
+                             config_path='./inc_configs/mobilenet.yaml'),
     # TBD: DaSiamRPN
-    youtureid=Quantize(model_path='../../models/person_reid_youtureid/person_reid_youtu_2021nov.onnx',
+    youtureid=ORT_Quantize(model_path='../../models/person_reid_youtureid/person_reid_youtu_2021nov.onnx',
                        calibration_image_dir='../../benchmark/data/person_reid',
                        transforms=Compose([Resize(size=(128, 256))])),
     # TBD: DB-EN & DB-CN
-    crnn_en=Quantize(model_path='../../models/text_recognition_crnn/text_recognition_CRNN_EN_2021sep.onnx',
+    crnn_en=ORT_Quantize(model_path='../../models/text_recognition_crnn/text_recognition_CRNN_EN_2021sep.onnx',
                      calibration_image_dir='../../benchmark/data/text',
                      transforms=Compose([Resize(size=(100, 32)), ColorConvert(ctype=cv.COLOR_BGR2GRAY)])),
-    crnn_cn=Quantize(model_path='../../models/text_recognition_crnn/text_recognition_CRNN_CN_2021nov.onnx',
+    crnn_cn=ORT_Quantize(model_path='../../models/text_recognition_crnn/text_recognition_CRNN_CN_2021nov.onnx',
                      calibration_image_dir='../../benchmark/data/text',
                      transforms=Compose([Resize(size=(100, 32))]))
 )

tools/quantize/requirements.txt

@@ -1,3 +1,5 @@
 opencv-python>=4.5.4.58
 onnx
-onnxruntime
+onnxruntime
+neural-compressor
+