[MXNET-1083] Write examples to demonstrate the inference workflow using C++ API.

• Type: Story
• Status: Done
• Priority: Major
• Resolution: Unresolved
• Component/s: Apache MXNet C/C++ API
• Sprint: C/C++ API 1 (10/22 - 11/5), C/C++ API 2 (12/3 - 12/17)
• Assignee: Amol Lele
• Reporter: Amol Lele
• Created: 10/Oct/18 00:19
• Updated: 10/Jun/19 18:15

Description

We are planning to provide examples that demonstrate the inference workflow using C++ API.

These examples will demonstrate:

1.   How to load pre-trained network and its parameters.
2.   How to pre-process the data for validation/inference.
3.  Measure the throughput and validation accuracy.

 

These examples will be available under separate folder. We will primarily focus on CiFar10 dataset. We will use models that are available at http://data.mxnet.io/models/

In order to be consistent with python examples, the cpp-package examples will demonstrate usage of

1. 'imagenet1k-inception-bn'
2. 'imagenet1k-resnet-18'
3. 'imagenet1k-resnet-34'
4. 'imagenet1k-resnet-50'
5. 'imagenet1k-resnet-101'
6. 'imagenet1k-resnet-152'
7. 'imagenet1k-resnext-50'
8. 'imagenet1k-resnext-101'
9. 'imagenet1k-resnext-101-64x4d'
10. 'imagenet11k-resnet-152'
11. 'imagenet11k-place365ch-resnet-152'
12. 'imagenet11k-place365ch-resnet-50'

 

 

 

Issue Links

• links to: GitHub Pull Request #12915
• links to: GitHub Pull Request #12930
• links to: GitHub Pull Request #13294