fastseg-small is an accurate real-time semantic segmentation model, pretrained on Cityscapes dataset for 19 object classes, see Cityscapes classes definition. The model was built on MobileNetV3 small backbone and modified segmentation head based on LR-ASPP. This model can be used for efficient segmentation on a variety of real-world street images. For details see repository.
Metric | Value |
---|---|
Type | Semantic segmentation |
GOps | 69.2204 |
MParams | 1.1 |
Source framework | PyTorch* |
Metric | Value |
---|---|
mean_iou | 67.15% |
Image, name: input0
, shape: 1, 3, 1024, 2048
, format: B, C, H, W
, where:
B
- batch sizeC
- number of channelsH
- image heightW
- image widthExpected color order: RGB. Mean values: [123.675, 116.28, 103.53], scale values: [58.395, 57.12, 57.375]
Image, name: input0
, shape: 1, 3, 1024, 2048
, format: B, C, H, W
, where:
B
- batch sizeC
- number of channelsH
- image heightW
- image widthExpected color order: BGR.
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: output0
, shape: 1, 19, 1024, 2048
in B, N, H, W
format, where
B
- batch sizeN
- number of classesH
- image heightW
- image widthFloat 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: output0
, shape: 1, 19, 1024, 2048
in B, N, H, W
format, where
B
- batch sizeN
- number of classesH
- image heightW
- image widthYou can download models and if necessary convert them into Inference Engine format using the Model Downloader and other automation tools as shown in the examples below.
An example of using the Model Downloader:
An example of using the Model Converter:
The original model is distributed under the following license: