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: RGB.
NOTE: By default, Open Model Zoo demos expect input with BGR channels order. Reverse input channels operation via Model Optimizer conversion can not be applied to this model in proper way. For running this model with Open Model Zoo demos, you need to manually rearrange the default channels order in the demo application.
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
The original model is distributed under the Apache License, Version 2.0. A copy of the license is provided in APACHE-2.0-TensorFlow.txt.