Obtaining More Samples (Atlas 200/300/500 Inference Product)

The following table lists the samples provided by pyACL.

Table 1 Linux samples

Sample

How to Obtain

Description

Description

acl_operator_add

Sample

Implement the matrix-matrix addition operation.

This sample verifies the functionality of the custom operator by converting the custom operator file into a single-operator offline model file and loading the file using the pyACL for execution.

vpc_resnet50_imagenet_classification

Sample

Image classification based on Caffe ResNet-50 (image decoding+resizing+synchronous inference)

This sample shows how to classify images based on the Caffe ResNet-50 network (single input with batch size = 1). For details, see pyACL Sample Usage Guide.

vdec_resnet50_classification

Sample

Image classification based on Caffe ResNet-50 (video decoding+synchronous inference)

resnet50_imagenet_classification

Sample

Image Classification with Caffe ResNet-50 (Synchronous Inference)

resnet50_async_imagenet_classification

Sample

Image Classification with Caffe ResNet-50 (Asynchronous Inference)

vpc_jpeg_resnet50_imagenet_classification

Sample

Image classification based on Caffe ResNet-50 (image decoding+cropping and resizing+image encoding+synchronous inference)

In this sample, one or more 224 x 224 YUV420SP NV12 images are cropped from a YUV420SP NV12 input image.

venc_image

Sample

Media Data Processing (Video Encoding)

In this sample, a YUV420SP NV12 image is encoded for n consecutive times to generate an H.265 video stream.