Skip to content

remote-debug-example: Describe how to debug apps using run options #443

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
johan-hultberg-work merged 2 commits into from
Dec 15, 2025
Merged

remote-debug-example: Describe how to debug apps using run options #443

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
5f7acce
remote-debug-example: Describe how to debug apps using run options
isak-jakobsson Nov 25, 2025
7725602
Lint: Fix lint issues in markdown tables
isak-jakobsson Dec 1, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 7 additions & 7 deletions object-detection-cv25/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -294,13 +294,13 @@ Depending on selected chip, different output is received. The label file is used

In the system log the chip is sometimes only mentioned as a string, they are mapped as follows:

| Chips | Larod 1 (int) | Larod 3 |
|-------|--------------|------------------|
| CPU with TensorFlow Lite | 2 | cpu-tflite |
| Google TPU | 4 | google-edge-tpu-tflite |
| Ambarella CVFlow (NN) | 6 | ambarella-cvflow |
| ARTPEC-8 DLPU | 12 | axis-a8-dlpu-tflite |
| ARTPEC-9 DLPU | - | a9-dlpu-tflite |
| Chips | Larod 1 (int) | Larod 3 |
| ------------------------ | ------------- | ---------------------- |
| CPU with TensorFlow Lite | 2 | cpu-tflite |
| Google TPU | 4 | google-edge-tpu-tflite |
| Ambarella CVFlow (NN) | 6 | ambarella-cvflow |
| ARTPEC-8 DLPU | 12 | axis-a8-dlpu-tflite |
| ARTPEC-9 DLPU | - | a9-dlpu-tflite |

There are four outputs from MobileNet SSD v2 (COCO) model. The number of detections, cLasses, scores, and locations are shown as below. The four location numbers stand for \[top, left, bottom, right\]. By the way, currently the saved images will be overwritten continuously, so those saved images might not all from the detections of the last frame, if the number of detections is less than previous detection numbers.

Expand Down
17 changes: 17 additions & 0 deletions remote-debug-example/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -191,6 +191,23 @@ ssh acap-remote_debug@<AXIS_DEVICE_IP>
/tmp/gdbserver :1234 /usr/local/packages/remote_debug/remote_debug
```

> [!NOTE]
> If your `manifest.json` file contains runtime options under
> `acapPackageConf.setup.runOptions`, these are not automatically propagated to
> the gdbserver. You must explicity include them when starting the `gdbserver`.
>
> For example, if your `manifest.json` contains:
>
> ```json
> "runOptions": "--arg1 value1 --arg2 value2"
> ```
>
> Start the gdbserver with:
>
> ```sh
> /tmp/gdbserver :1234 /usr/local/packages/remote_debug/remote_debug --arg1 value1 --arg2 value2
> ```

You should see output similar to:

```sh
Expand Down
10 changes: 5 additions & 5 deletions tensorflow-to-larod/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -122,11 +122,11 @@ be done using less precision. This generally results in significantly lower
inference latency and model size with only a slight penalty to the model's
accuracy.

| Chip | Supported precision |
|---------- |------------------ |
| Edge TPU | INT8 |
| Common CPUs | FP32, INT8 |
| Common GPUs | FP32, FP16, INT8 |
| Chip | Supported precision |
| ----------- | ------------------- |
| Edge TPU | INT8 |
| Common CPUs | FP32, INT8 |
| Common GPUs | FP32, FP16, INT8 |

As noted in the first chapter, this example uses a camera equipped with an Edge TPU.
As the Edge TPU chip **only** uses INT8 precision, the model will need to be quantized from
Expand Down
14 changes: 7 additions & 7 deletions vdo-larod/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -276,13 +276,13 @@ Depending on the selected chip, different output is received.

In previous larod versions, the chip was referred to as a number instead of a string. See the table below to understand the mapping:

| Chips | Larod 1 (int) | Larod 3 |
|-------|--------------|------------------|
| CPU with TensorFlow Lite | 2 | cpu-tflite |
| Google TPU | 4 | google-edge-tpu-tflite |
| Ambarella CVFlow (NN) | 6 | ambarella-cvflow |
| ARTPEC-8 DLPU | 12 | axis-a8-dlpu-tflite |
| ARTPEC-9 DLPU | - | a9-dlpu-tflite |
| Chips | Larod 1 (int) | Larod 3 |
| ------------------------ | ------------- | ---------------------- |
| CPU with TensorFlow Lite | 2 | cpu-tflite |
| Google TPU | 4 | google-edge-tpu-tflite |
| Ambarella CVFlow (NN) | 6 | ambarella-cvflow |
| ARTPEC-8 DLPU | 12 | axis-a8-dlpu-tflite |
| ARTPEC-9 DLPU | - | a9-dlpu-tflite |

#### Output - ARTPEC-8 with TensorFlow Lite

Expand Down