Sample Overview

Sample Obtaining

Visit the Ascend samples repository on Gitee and download the sample package that matches your CANN version in use. For the version mapping, see "Release Notes" in the README file. Find the resnet50_async_imagenet_classification sample in the python/level2_simple_inference/1_classification/resnet50_async_imagenet_classification directory.

Function Description

This sample shows how to classify images based on the Caffe ResNet-50 network (single input with batch size = 1).

Convert the model file of the Caffe ResNet-50 network into an offline model (.om file) adapted to the Ascend AI Processor. In the sample, load the .om file and perform n (an application parameter configured by the user. It is defaulted to 4 and can be set by the --execute_times parameter.) times of asynchronous inference on two .jpg images. Then, process the obtained n inference results, and output the class indexes with the top 5 confidence values of each image.

Main APIs

Table 1 shows the main APIs.

**Table 1** Main APIs
Function	ACL Module	ACL Interface Function	Description
Resource initialization	Initialization	acl.init	Initializes the ACL configuration.
	Device management	acl.rt.set_device	Specifies the device for computation.
	Context management	acl.rt.create_context	Creates a context.
Model initialization	Model loading and execution	acl.mdl.load_from_file	Loads the model from the .om file to the device.
	Data types and operation APIs	acl.mdl.create_desc	Creates data for describing the model.
	Data types and operation APIs	acl.mdl.get_desc	Obtains data for describing the model.
Model inference	Model loading and execution	acl.mdl.execute_async	Performs asynchronous model inference.
Synchronization	Synchronization	acl.rt.subscribe_report	Specifies the thread that processes the callback function in the stream.
	Synchronization	acl.rt.unsubscribe_report	Unsubscribes from a thread and specifies a callback function in a stream to not be handled by a specified thread.
	Synchronization	acl.rt.launch_callback	Adds a callback function executed on the host or device to the stream task queue.
	Synchronization	acl.rt.process_report	Triggers callback handling after a specified period.
Data exchange	Memory management	acl.rt.memcpy	Sends data from the host to the device or from the device to the host.
	Memory management	acl.rt.malloc	Allocates device memory.
	Memory management	acl.rt.malloc_host	Allocates memory on the host.
Common module	--	acl.util.ptr_to_numpy	Converts void* data to NumPy data.
	--	acl.util.numpy_to_ptr	Converts NumPy data to void* data.
	--	acl.util.start_thread	Starts a callback function thread.
	--	acl.util.stop_thread	Reclaims a callback function thread.
Data postprocessing	Data types and operation APIs	acl.mdl.get_dataset_buffer	Obtains dataset information.
Data postprocessing	Data types and operation APIs	acl.mdl.get_dataset_num_buffers	Obtains dataset information.
Allocation destruction	Memory management	acl.rt.free	Frees device memory.
	Memory management	acl.rt.free_host	Frees the memory on the host.
	Model loading and execution	acl.mdl.unload	Unloads a model.
	Context management	acl.rt.destroy_context	Destroys a context.
	Device management	acl.rt.reset_device	Resets the current device and reclaims the resources on the device.
	Deinitialization	acl.finalize	Deinitializes ACL.

Asynchronous Model Inference Process

Figure 1 shows the asynchronous model inference process.

Figure 1 Asynchronous model inference process

Directory Structure

The directory structure is as follows:

resnet50_async_imagenet_classification
├──src
│ ├── acl_net.py // Running file
│ └── constant.py // Constant definition
├── data
│ ├── dog1_1024_683.jpg // Test image data
│ └── dog2_1024_683.jpg // Test image data
├── caffe_model
│ ├── resnet50.caffemodel // ResNet-50 model
│ └── resnet50.prototxt // ResNet-50 network file
└── model
  └── resnet50.om // Model file generated after conversion

Parent topic: Image Classification with Caffe ResNet-50 (Asynchronous Inference)