DeepLab is a state-of-art deep learning model for semantic image segmentation. For details see paper.
Metric | Value |
---|---|
Type | Semantic segmentation |
GFLOPs | 11.469 |
MParams | 23.819 |
Source framework | TensorFlow* |
Metric | Value |
---|---|
mean_iou | 66.85% |
Image, name: ImageTensor
, shape: [1x513x513x3], format: [BxHxWxC], where:
Expected color order: RGB.
Image, name: mul_1/placeholder_port_1
, shape: [1x3x513x513], format: [BxCxHxW], where:
Expected color order: BGR.
Integer values in a range [0, 20], which represent an index of a predicted class for each image pixel. Name: ArgMax
, shape: [1x513x513] in [BxHxW] format, where
- B - batch size - H - image height - W - image width
Integer values in a range [0, 20], which represent an index of a predicted class for each image pixel. Name: ArgMax/Squeeze
, shape: [1x513x513] in [BxHxW] format, where
- B - batch size - H - image height - W - image width
You 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 Apache License, Version 2.0. A copy of the license is provided in APACHE-2.0-TF-Models.txt.