Remove deprecated MXNet models (#3900)

Author: Wovchena

CONTRIBUTING.md

@@ -10,7 +10,6 @@ Frameworks supported by the Open Model Zoo:
 * TensorFlow\*
 * PyTorch\* (via conversion to ONNX\*)
 * PaddlePaddle\*
-* MXNet\*
 
 Open Model Zoo also supports models already in the ONNX format.
 

data/datasets.md

@@ -90,7 +90,7 @@ To use this dataset with OMZ tools, make sure `<DATASET_DIR>` contains the follo
 
 ### Datasets in dataset_definitions.yml
 * `wider` used for evaluation models on WIDER Face dataset where the face is the first class. (model example: [mtcnn](../models/public/mtcnn/README.md))
-* `wider_without_bkgr` used for evaluation models on WIDER Face dataset where the face is class zero. (model examples: [mobilefacedet-v1-mxnet](../models/public/mobilefacedet-v1-mxnet/README.md))
+* `wider_without_bkgr` used for evaluation models on WIDER Face dataset where the face is class zero. (model example: [face-detection-0204](../models/intel/face-detection-0204/README.md))
 
 ## Visual Object Classes Challenge 2012 (VOC2012)
 

demos/3d_segmentation_demo/python/3d_segmentation_demo.py

@@ -367,9 +367,7 @@ def main():
     if args.output_nifti and is_nifti_data:
         for seg_res in list_seg_result:
             nii_filename = os.path.join(args.path_to_output, 'output_{}.nii.gz'.format(list_seg_result.index(seg_res)))
-            # Nifti1Image expects uint8, but brain-tumor-segmentation-0001 gives int64.
-            # brain-tumor-segmentation-0002 gives uint8
-            nib.save(nib.Nifti1Image(seg_res.astype(np.uint8), affine=affine), nii_filename)
+            nib.save(nib.Nifti1Image(seg_res, affine=affine), nii_filename)
             log.debug("Result nifti file was saved to {}".format(nii_filename))
 
 if __name__ == "__main__":

demos/3d_segmentation_demo/python/README.md

@@ -28,7 +28,6 @@ omz_converter --list models.lst
 
 ### Supported Models
 
-* brain-tumor-segmentation-0001
 * brain-tumor-segmentation-0002
 
 > **NOTE**: Refer to the tables [Intel's Pre-Trained Models Device Support](../../../models/intel/device_support.md) and [Public Pre-Trained Models Device Support](../../../models/public/device_support.md) for the details on models inference support at different devices.
@@ -76,29 +75,29 @@ For example, to do inference on a 3D TIFF image using a trained network with mul
 command:
 
 ```sh
-python3 3d_segmentation_demo.py -i <path_to_image>/inputImage.tiff -m <path_to_model>/brain-tumor-segmentation-0001.xml -d CPU -o <path_to_output>
+python3 3d_segmentation_demo.py -i <path_to_image>/inputImage.tiff -m <path_to_model>/brain-tumor-segmentation-0002.xml -d CPU -o <path_to_output> -ms 1,2,3,0 --full_intensities_range
 ```
 
 For example, to do inference on 3D NIfTI images using a trained network with multiple outputs on CPU and save
 output TIFF and NIFTI images, run the following command:
 
 ```sh
-python3 3d_segmentation_demo.py -i <path_to_nifti_images> -m <path_to_model>/brain-tumor-segmentation-0001 -d CPU -o <path_to_output> -nii -ms 2,0,3,1
+python3 3d_segmentation_demo.py -i <path_to_nifti_images> -m <path_to_model>/brain-tumor-segmentation-0002 -d CPU -o <path_to_output> -nii -ms 1,2,3,0 --full_intensities_range
 ```
 
 For example, to do inference on a single 3D NIfTI image and save an output TIFF image, run the following command:
 
 ```sh
-python3 3d_segmentation_demo.py -i <path_to_nifti_image>/PackedImage.nii -m <path_to_model>/brain-tumor-segmentation-0001 -d CPU -o <path_to_output> -ms 2,0,3,1
+python3 3d_segmentation_demo.py -i <path_to_nifti_image>/PackedImage.nii -m <path_to_model>/brain-tumor-segmentation-0002 -d CPU -o <path_to_output> -ms 1,2,3,0 --full_intensities_range
 ```
 
-`-ms` option aligns input modalities that depend on a dataset. For example, [Medical Decathlon](http://medicaldecathlon.com/) brain tumor segmentation data modalities follow in different order than it's required by nets. To make a correct order using Medical Decathlon brain tumor data the correct option is `2,0,3,1` for `brain-tumor-segmentation-0001` and `1,2,3,0` for `brain-tumor-segmentation-0002`.
+`-ms` option aligns input modalities that depend on a dataset. For example, [Medical Decathlon](http://medicaldecathlon.com/) brain tumor segmentation data modalities follow in different order than it's required by nets. To make a correct order using Medical Decathlon brain tumor data the correct option is `1,2,3,0` for `brain-tumor-segmentation-0002`.
 
 ```sh
 python3 3d_segmentation_demo.py -i <path_to_nifti_images> -m <path_to_model>/brain-tumor-segmentation-0002 -d CPU -o <path_to_output> -nii -ms 1,2,3,0 --full_intensities_range
 ```
 
-`--full_intensities_range` option is related to preprocessing of input data. It can be different for different models, for example, `brain-tumor-segmentation-0001` expects normalized data in [0,1] range and nullified non-positive values, while `brain-tumor-segmentation-0002` just requires z-score normalization in a full range. So to use `brain-tumor-segmentation-0002` model, the flag `--full_intensities_range` should be set, while for `brain-tumor-segmentation-0001` no preprocessing option is required.
+`--full_intensities_range` option is related to preprocessing of input data. It can be different for different models, for example, `brain-tumor-segmentation-0002` just requires z-score normalization in a full range. So to use `brain-tumor-segmentation-0002` model, the flag `--full_intensities_range` should be set.
 
 ## Demo Output
 

demos/classification_benchmark_demo/cpp/README.md

@@ -68,7 +68,6 @@ omz_converter --list models.lst
 * mobilenet-v3-small-1.0-224-paddle
 * mobilenet-v3-small-1.0-224-tf
 * nfnet-f0
-* octave-resnet-26-0.25
 * regnetx-3.2gf
 * repvgg-a0
 * repvgg-b1

demos/classification_benchmark_demo/cpp/models.lst

@@ -32,7 +32,6 @@ mobilenet-v3-large-1.0-224-tf
 mobilenet-v3-small-1.0-224-paddle
 mobilenet-v3-small-1.0-224-tf
 nfnet-f0
-octave-resnet-26-0.25
 regnetx-3.2gf
 repvgg-a0
 repvgg-b1

demos/classification_benchmark_demo/cpp_gapi/README.md

@@ -68,7 +68,6 @@ omz_converter --list models.lst
 * mobilenet-v3-small-1.0-224-paddle
 * mobilenet-v3-small-1.0-224-tf
 * nfnet-f0
-* octave-resnet-26-0.25
 * regnetx-3.2gf
 * repvgg-a0
 * repvgg-b1

demos/classification_benchmark_demo/cpp_gapi/models.lst

@@ -33,7 +33,6 @@ mobilenet-v3-large-1.0-224-paddle
 mobilenet-v3-small-1.0-224-paddle
 # mobilenet-v3-small-1.0-224-tf
 nfnet-f0
-octave-resnet-26-0.25
 regnetx-3.2gf
 repvgg-a0
 repvgg-b1

demos/classification_demo/python/README.md

@@ -70,7 +70,6 @@ omz_converter --list models.lst
 * mobilenet-v3-small-1.0-224-paddle
 * mobilenet-v3-small-1.0-224-tf
 * nfnet-f0
-* octave-resnet-26-0.25
 * regnetx-3.2gf
 * repvgg-a0
 * repvgg-b1

demos/classification_demo/python/models.lst

@@ -32,7 +32,6 @@ mobilenet-v3-large-1.0-224-tf
 mobilenet-v3-small-1.0-224-paddle
 mobilenet-v3-small-1.0-224-tf
 nfnet-f0
-octave-resnet-26-0.25
 regnetx-3.2gf
 repvgg-a0
 repvgg-b1