- What's New
- Function Overview
- Service Overview
- Getting Started
-
User Guide
- Who Uses HiLens
- Procedures for Using HiLens
- Permissions Management
- Creating a Workspace
- Registering HiLens Kit Devices
- Managing Devices
- Developing Skills on the Console
- Using the Skill Market
- Managing Data
- Managing Products
- Caffe Operator Boundaries
- TensorFlow Operator Boundaries
- Best Practices
-
Developer Guide
- Before You Start
- HiLens Framework Introduction
- Initialization
- Video Input Module
- Audio Input Module
- Preprocessing Module
- Model Management Module
- Output Module
- EIServices Module
- Resource Management Module
-
Hard Example Upload Module
- Introduction to Hard Example Upload
- Initializing
- Determining a Hard Example Image in a Detection Algorithm
- Determining a Hard Example Image in a Classification Algorithm
- Uploading a Hard Example Image Set
- Obtaining Hard Example Configurations
- Updating Hard Example Configurations
- Example - Hard Example Upload
- Log Module
- Error Codes
- Change History
- SDK Reference
-
FAQs
-
FAQs
-
HiLens Kit Devices
-
Device Introduction
- What Are the Differences Between HiLens Kit and Atlas 500?
- What Are the Differences Between HiLens Kit and Atlas 200 DK?
- What Is HiLens Kit?
- What Is the Focal Length of a HiLens Kit Camera? Can It be Adjusted?
- What Cameras Can Be Connected to HiLens Kit?
- Can I Develop HiLens Kit Skills Using Compute Architecture for Neural Networks (CANN)?
-
Device Hardware Operations
- What Storage Devices Can Be Mounted to the USB Port of a HiLens Kit Device?
- What Does the Red Indicator of a HiLens Kit Device Mean?
- How Do I Restore HiLens Kit Devices to Factory Settings?
- Can HiLens Kit Connect to Multiple USB Cameras?
- Do I Need to Use Other Devices Together with HiLens Kit Devices?
- How Do I Quickly Switch a HiLens Kit Device to the Wireless Network Configuration Mode?
- Does HiLens Kit Support Infrared Interfaces?
-
Device System Operations
- How Do I Log In to a Device Using SSH?
- After I Change the Password for a Huawei HiLens Device, Why Can't I Use PuTTY to Log In to the Device Even Though I Can Use the New Password to Log in to Huawei HiLens IES?
- How Do I Perform Bottom-Layer Operations on the HiLens Kit System?
- Can I Import a Custom Python Module to a HiLens Kit Device?
- How Do I Install YUM on HiLens Kit Devices?
- How Do I Manage Device Files?
- How Do I Install Software Packages on HiLens Kit Devices?
- How Do I Log In to a Device as Root User and Disable Connection Timeout?
- Can Python-based OpenMV Devices Invoke HiLens Kit Skills by Calling APIs?
- Why a HiLens Kit Device Cannot Display Chinese Characters?
- How Do I Clear Wi-Fi Information Saved on a HiLens Kit Device?
- How Do I Use SSH Commands to Connect a HiLens Kit Device to a Wi-Fi Network?
- How Do I Configure Permanent DNS on a HiLens Kit Device?
-
Device Introduction
-
Device Registration
- How Do I Handle Device Registration Failures with Different Causes Returned?
- How Do I Check Whether a Huawei Cloud Account Is Bound to a Device?
- What Should I Do If I Can't Access the Huawei HiLens IES?
- What Should I Do If There Is Not Enough Quota for Device Registration?
- Why Do HiLens Kit Devices Fail to Connect to Wi-Fi?
- How Do I View the IP address of a Wireless Network?
- What Do I Do If the System Displays a Message Indicating that Only Firmware 1.0.3 or Later Can Be Registered When I Use Register a Device with the Intelligent Edge System?
- What Are the Differences Between Using IES and SSH to Register a HiLens Kit Device?
- What Do I Do If I Forgot the Password to the Huawei HiLens Intelligent Edge System?
-
Managing Devices
- What Should I Do If the Device Is Offline for More Than 5 Minutes After a Firmware Upgrade?
- Do I Need to Upgrade Firmware in Sequence?
- Why Does the Firmware Upgrade Fail When the Device Is Online?
- What Should I Do If the System Displays a Message Indicating That the Upgraded Version Must Be Later Than the Current Version During Firmware Upgrade?
- What Can I Do If a Device Alarm Is Reported Indicating That the Directory Space Is Full?
-
Skill Development
- What Are the Causes of Skill Creation Failures?
- What Models Does Huawei HiLens Support?
- How Do I Upload Models to Huawei HiLens?
- Can One Skill Use Multiple Models? How Do I Add Multiple Models When Developing a Skill?
- Why Does Skill Releasing Fail?
- Can Sockets Be Used During Skill Development?
- How Do I Handle a Model Conversion Failure?
- To What Devices Does the HiLens Framework SDK Apply?
- How Do I Determine the Input Tensor Shape During Model Conversion?
- Does Huawei HiLens Only Support Models Trained by ModelArts?
- Can Skills Developed on Huawei HiLens Be Deployed on Edge Servers That Use P4 GPUs?
-
Installing and Starting Skills
- What Are the Possible Causes for Skill Installation Failures?
- How Many Skills Can Run on a HiLens Kit Device Concurrently?
- Why Does a Skill Stop After Being Started?
- Can a HiLens Kit Device Run Skills Offline?
- What Can I Do If Skill A Is Successfully Started But Skill B Fails to Be Started When the Two Skills Purchased from the Skill Market Are Both Output by HDMI?
- Purchasing Skills
- Managing Products
-
Managing Data
- Why Is There No HDMI Skill Data on the Data Management Page?
- How Do I Configure the Data Storage Location (OBS Storage Path)?
- Why Does HDMI Black Screen Occur or HDMI Output Stop Working?
- Can I Record the Images Captured by a HiLens Kit Camera or the Skill Running Result for Storage?
- Why Don't the Logs Contain Any Device Data?
-
Algorithm Issues
- Why Is Error Code 17 Displayed During Model Inference?
- How Do I Use and Program the SDK or License of a Skill?
- Can a Huawei HiLens Skill Run on an Android or Arm Platform?
- What TensorFlow and Caffe Models Can Run on Huawei HiLens?
- Does Huawei HiLens Support Self-Developed Operators?
- What Language Does the Huawei HiLens Development Environment Support?
- Does HiLens Kit Provide an Interface that Converts a Color Image to a Grayscale Image?
- How Do I Configure Python Dependencies for a Skill?
-
Other
- Why Does the Huawei HiLens Console Keep Reporting 404 Errors?
- How Do I Assign Huawei HiLens Permissions to New IAM Users?
- Does Huawei HiLens Support 3D Object Recognition?
- What Can I Do If the System Displays a Message Indicating that the AK/SK Pair Is Unusable?
- What Devices Does Huawei HiLens Support?
-
HiLens Kit Devices
-
FAQs
- General Reference
Copied.
How Do I Handle a Model Conversion Failure?
You can view the model conversion logs to locate the failure cause and rectify the fault accordingly.
- Viewing Model Conversion Logs: View the model conversion logs to locate the failure cause.
- Resolving Model Conversion Failures: Common causes and solutions for model conversion failures.
Viewing Model Conversion Logs
- Log in to the Huawei HiLens console. In the navigation pane, choose Skill Development > Models. The Models page is displayed.
If the model fails to convert, you can view that the model status is Conversion failed.
- Locate the failed model and click Details in the Operation column. The Model Details page is displayed.
You can view the Basic Information and Log Information of the model, as shown in Figure 1.
You can enter a keyword about the failed model in the search box of the Log Information area to quickly locate the failure cause.
Resolving Model Conversion Failures
Solutions for common model conversion failures:
- Check whether the uploaded model file is correct.
Before importing a custom model, upload it to OBS. A non-om model package contains Caffe model files .caffemodel and .prototxt and configuration file .cfg, or TensorFlow model file .pb and configuration file .cfg.
- Check whether the model to be imported or converted uses the TensorFlow or Caffe operator boundaries supported by .om models.
Not all models can be successfully converted. Before importing and converting a model, check whether it uses the TensorFlow and Caffe operator boundaries supported by .om models. For details, see Caffe Operator Boundaries and TensorFlow Operator Boundaries.
- Check whether the parameters are correctly set for model conversion.
For details about the parameters, see Importing (Converting) Models. The parameters that may be incorrectly set are listed below.
- Input Tensor Shape
Mandatory. The shape of the input data, in the format of NHWC, for example, input_name:1,224,224,3. input_name must be a node name in the network model before model conversion, which must be configured when the model has dynamic shape input. For example, in input_name1:?,h,w,c, the question mark (?) indicates the batch size, that is, the number of images processed at a time. It is used to convert the original model with a dynamic shape into an offline model with a fixed shape.
Use commas to separate multiple inputs.
- Type
Select the correct model conversion type for the imported model.
- TF-FrozenGraph-To-Ascend-HiLens
This template converts TensorFlow frozen_graph models into those run on Ascend chips. If the firmware version of your HiLens Kit system is 2.2.200.011, you are advised to use this template for model conversion.
- TF-SavedModel-To-Ascend-HiLens
This template converts TensorFlow saved_model models into those run on Ascend chips. If the firmware version of your HiLens Kit system is 2.2.200.011, you are advised to use this template for model conversion.
- TF-FrozenGraph-To-Ascend
This template converts TensorFlow frozen_graph models into those run on Ascend chips. If the firmware version of your HiLens Kit system is earlier than 2.2.200.011, you are advised to use this template for model conversion.
- TF-SavedModel-To-Ascend
This template converts TensorFlow saved_model models into those run on Ascend chips. If the firmware version of your HiLens Kit system is earlier than 2.2.200.011, you are advised to use this template for model conversion.
- Caffe to Ascend
Caffe models can be converted into models that can run on Ascend chips.
- TF-FrozenGraph-To-Ascend-893
This template converts TensorFlow frozen_graph models into those run on Ascend chips. If the firmware version of your HiLens Kit system is earlier than 2.2.200.011, you are advised to use this template for model conversion.
- TF-FrozenGraph-To-Ascend-HiLens
- Import From
For Ascend chip-supported models developed locally or developed in ModelArts and converted on HiLens, set this parameter by referring to Model Input Directory Specifications.
NOTE:
- The model input directory cannot contain multiple models.
- The directory must contain the model file. Other files are optional.
- Export To
For conversion tasks of models supported by Ascend chips, set this parameter by referring to Model Output Directory Specifications.
- Input Tensor Shape
Feedback
Was this page helpful?
Provide feedbackThank you very much for your feedback. We will continue working to improve the documentation.See the reply and handling status in My Cloud VOC.
For any further questions, feel free to contact us through the chatbot.
Chatbot