drn-d-38#

Use Case and High-Level Description#

The drn-d-38 model is a one of the Dilated Residual Networks (DRN) models for semantic segmentation task. DRN models dilate ResNet models, DRN-C version additionally removes residual connections from some of the added blocks and DRN-D version is a simplified version of DRN-C.

This model pre-trained on Cityscapes dataset for 19 object classes, listed in <omz_dir>/data/dataset_classes/cityscapes_19cl.txt file. See Cityscapes classes definition for more details.

More details provided in the paper and repository.

Specification#

Metric

Value

Type

Semantic segmentation

GFLOPs

1768.3276

MParams

25.9939

Source framework

PyTorch*

Accuracy#

Metric

Value

mean_iou

71.31%

Input#

Original model#

Image, name: input, shape: 1, 3, 1024, 2048, format: B, C, H, W, where:

  • B - batch size

  • C - number of channels

  • H - image height

  • W - image width

Expected color order: RGB. Mean values: [73.975742869, 83.660769353, 73.175805779], scale values: [46.653282963, 47.574230671, 47.041147921]

Converted Model#

Image, name: input, shape: 1, 3, 1024, 2048, format: B, C, H, W, where:

  • B - batch size

  • C - number of channels

  • H - image height

  • W - image width

Expected color order: BGR.

Output#

Original Model#

Float values, which represent scores of a predicted class for each image pixel. The model was trained on Cityscapes dataset with 19 categories of objects. Name: output, shape: 1, 19, 1024, 2048 in B, N, H, W format, where:

  • B - batch size

  • N - number of classes

  • H - image height

  • W - image width

Converted Model#

Float values, which represent scores of a predicted class for each image pixel. The model was trained on Cityscapes dataset with 19 categories of objects. Name: output, shape: 1, 19, 1024, 2048 in B, N, H, W format, where:

  • B - batch size

  • N - number of classes

  • H - image height

  • W - image width

Download a Model and Convert it into OpenVINO™ IR Format#

You can download models and if necessary convert them into OpenVINO™ IR format using the Model Downloader and other automation tools as shown in the examples below.

An example of using the Model Downloader:

omz_downloader --name <model_name>

An example of using the Model Converter:

omz_converter --name <model_name>

Demo usage#

The model can be used in the following demos provided by the Open Model Zoo to show its capabilities: