# NPU Inference Discrepancy: Local conversion works, but Docker conversion results in "Ghost Boxes" at top-left

**URL:** <https://forum.amebaiot.com/t/npu-inference-discrepancy-local-conversion-works-but-docker-conversion-results-in-ghost-boxes-at-top-left/4667>\
**Category:** AI\
**Created:** [January 24, 2026, 10:01am UTC](https://forum.amebaiot.com/t/npu-inference-discrepancy-local-conversion-works-but-docker-conversion-results-in-ghost-boxes-at-top-left/4667 "2026-01-24T10:01:30Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![t114c75035](https://sea2.discourse-cdn.com/flex016/user_avatar/forum.amebaiot.com/t114c75035/32/2986_2.png) [@t114c75035](https://forum.amebaiot.com/u/t114c75035)\
**Post date:** [January 24, 2026, 10:01am UTC](https://forum.amebaiot.com/t/npu-inference-discrepancy-local-conversion-works-but-docker-conversion-results-in-ghost-boxes-at-top-left/4667/1 "2026-01-24T10:01:30Z")

</div>

I am attempting to package my NPU conversion toolchain (PyTorch to .nb) into a Docker container.

- **Input Model:** YOLOv7 `.pt` file (already **reparameterized** , already fix Torch 2.6 loading issue in in yolo/models/experimental.py by setting `weights_only=False` \*\*,\*\*will be exported to onnx within Docker .).

- **Scenario:**

- **Abnormal Behavior on NPU:** Using the `ObjDetectionLoop` example:

Here is the comparison between the **Working Local Environment** and the **Failing Docker Environment**.

1. Local Environment

```auto
OS / Machine

Linux (22.04)

1.1 Local – YOLO Environment python 3.13
PyTorch: 2.8.0

TorchVision: 0.23.0

TorchAudio: 2.8.0

NumPy: 2.2.6

SciPy: 1.14.1

ONNX: 1.20.0

OpenCV: 4.10.0

Ultralytics: 8.3.235

THOP: 0.1.1

Roboflow: 1.2.6

LabelImg: 1.8.6

Matplotlib / Seaborn / Pandas

1.2 Local – Tool Environment (Acuity / Conversion Tool)
Acuity Toolkit: 6.18.8

TensorFlow: 2.10.0

TensorBoard: 2.10.1

Keras: 2.10.0

NumPy: 1.21.6

SciPy: 1.10.1

ONNX: 1.12.0

ONNX Simplifier: 0.4.36

ONNX Optimizer: 0.3.1

PyTorch: 1.13.1+cpu

TorchVision: 0.14.1+cpu

libclang: 18.1.1

LMDB: 0.93

```

2.Docker Environment

```auto
2.1 Docker – YOLO Environment
PyTorch: 2.8.0

TorchVision: 0.23.0

TorchAudio: 2.8.0

NumPy: 1.23.5

SciPy: 1.15.3

ONNX: 1.20.0

ONNX GraphSurgeon: 0.5.8

ONNX Simplifier: 0.4.36

OpenCV: 4.11.0

2.2 Docker – Tool Environment
Acuity Toolkit: 6.18.8

TensorFlow: 2.10.0

TensorBoard: 2.10.1

Keras: 2.10.0

NumPy: 1.21.6

SciPy: 1.10.1

ONNX: 1.12.0

ONNX Runtime: 1.12.0

ONNX Simplifier: 0.4.36

ONNX Optimizer: 0.3.1

PyTorch: 1.13.1

LMDB: 0.93

libclang: 18.1.1

```

Since the Acuity/Toolchain environment (Section 2) is nearly identical between Local and Docker, the issue seems to stem from the **Export Environment** (Section 1). Could you advise on how to align the Docker environment or if there are specific PyTorch/ONNX versions required to avoid this “top-left corner” coordinate shift on the NPU?

---

<div class="post-metadata">

**Author:** ![KevinKL](https://sea2.discourse-cdn.com/flex016/user_avatar/forum.amebaiot.com/kevinkl/32/2632_2.png) [@KevinKL](https://forum.amebaiot.com/u/KevinKL)\
**Post date:** [January 27, 2026, 2:13am UTC](https://forum.amebaiot.com/t/npu-inference-discrepancy-local-conversion-works-but-docker-conversion-results-in-ghost-boxes-at-top-left/4667/2 "2026-01-27T02:13:06Z")

</div>

Hi @t114c75035 ,

May I know if there is a need to perform conversion on a Docker environment? If yes, would you mind to tryout our Docker toolkit image to verify if this issue still persists? You may refer to the installation guide [here](https://ameba-doc-ai-video-analytics-doc.readthedocs-hosted.com/en/latest/user_manual/Acuity_tool/Acuity_installation_docker.html). Remember to login to docker using your GitHub username and PAT before pulling the image.

Thank you.

---

<div class="post-metadata">

**Author:** ![t114c75035](https://sea2.discourse-cdn.com/flex016/user_avatar/forum.amebaiot.com/t114c75035/32/2986_2.png) [@t114c75035](https://forum.amebaiot.com/u/t114c75035)\
**Post date:** [January 29, 2026, 7:47am UTC](https://forum.amebaiot.com/t/npu-inference-discrepancy-local-conversion-works-but-docker-conversion-results-in-ghost-boxes-at-top-left/4667/3 "2026-01-29T07:47:07Z")

</div>

**The issue is resolved. Docker is working perfectly now. Thanks for the help!**