Problem With Himax HM01B0 Camera On The Sparkfun Edge Board

Skip to content Dismiss alert {{ message }} tensorflow / tensorflow Public

• Notifications You must be signed in to change notification settings
• Fork 75.2k
• Star 193k

• Code
• Issues 849
• Pull requests 1.5k
• Actions
• Projects 2
• Security

  Uh oh!

  There was an error while loading. Please reload this page.

• Insights

Additional navigation options

Problem with Himax HM01B0 camera on the Sparkfun Edge board #37157New issueCopy linkNew issueCopy linkClosedClosedProblem with Himax HM01B0 camera on the Sparkfun Edge board#37157Copy linkAssignees Labelscomp:liteTF Lite related issuesTF Lite related issuescomp:microRelated to TensorFlow Lite MicrocontrollersRelated to TensorFlow Lite MicrocontrollersstaleThis label marks the issue/pr stale - to be closed automatically if no activityThis label marks the issue/pr stale - to be closed automatically if no activitystat:awaiting responseStatus - Awaiting response from authorStatus - Awaiting response from authortype:supportSupport issuesSupport issues

Description

anfericoopened on Feb 28, 2020Issue body actions

@tensorflow/micro

System information

• Host OS Platform and Distribution: Linux Ubuntu 18.04
• TensorFlow installed from (source or binary): Cloned from source, but not installed
• TensorFlow version (commit SHA if source): 642708d
• Target platform: Sparkfun Edge

I'm trying to run an image classification model on a Sparkfun Edge, starting from the person_detection example available in this repository. The logic for acquiring and resizing an image from the camera (Himax HM01B0) is included in himax_driver/HM01B0_optimized.c. For some reason, if I specify an image size greater than 102x102, the resulting image is padded with zeros in each of its four sides, yet the camera I'm using has a maximum pixel resolution of 320x320, as mentioned in the official website. Here's what I mean:

102x102 image:

320x320 image:

Please provide the exact sequence of commands/steps when you ran into the problem I simply passed w=320, h=320 and channels=1 to the function hm01b0_blocking_read_oneframe_scaled defined in himax_driver/HM01B0_optimized.c, printed each pixel value over the serial port and finally parsed such pixels with a Python script, displaying the resulting image.

Metadata

Metadata

Assignees

• mohantym
• rockyrhodes

Labels

comp:liteTF Lite related issuesTF Lite related issuescomp:microRelated to TensorFlow Lite MicrocontrollersRelated to TensorFlow Lite MicrocontrollersstaleThis label marks the issue/pr stale - to be closed automatically if no activityThis label marks the issue/pr stale - to be closed automatically if no activitystat:awaiting responseStatus - Awaiting response from authorStatus - Awaiting response from authortype:supportSupport issuesSupport issues

Type

No type

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions

You can’t perform that action at this time.