matlab/matlab-agentic-toolkit / skills-catalog/image-processing-and-computer-vision/matlab-integrate-pytorch-vision
matlab-integrate-pytorch-vision
VerifiedCreates MATLAB interfaces to Python image processing and computer vision models from GitHub repositories or pip-installable packages using MPyReq. Use when asked to interface MATLAB with a Python CV/image model (segmentation, depth estimation, object detection, image generation, super-resolution, etc.), given a GitHub repo URL for an image/vision model, or asked to create an MPyReq demo for a deep-learning vision pipeline. Do NOT use for general-purpose Python-MATLAB interfacing, non-vision models (NLP, tabular, audio), model deployment/serving, or MATLAB-only image processing workflows.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 14.7 KB |
| manifest.yaml | config | 535 B |
| references/common_gotchas.md | markdown | 1.8 KB |
| references/demo-birefnet.md | markdown | 2.0 KB |
| references/demo-cellpose.md | markdown | 839 B |
| references/demo-depthpro.md | markdown | 1.8 KB |
| references/demo-sam2.md | markdown | 2.2 KB |
| references/demo-stardist.md | markdown | 2.8 KB |
| references/demo-vggt.md | markdown | 2.2 KB |
| references/image_conversion_patterns.md | markdown | 3.1 KB |
| references/python_matlab_conversions.md | markdown | 1.5 KB |
| references/readme.md | markdown | 2.3 KB |
references/demo-vggt.md
View on GitHub# Demo: VGGT (Git Repo + requirements.txt, Point Cloud Output)
Pattern: **C** — git clone + requirements.txt, with 3D point cloud visualization.
## Setup
```matlab
terminate(pyenv); clear MPyReq
MPyReq.setInstallFolder(fullfile(tempdir, "MPyReq"));
MPyReq.autoAcceptDownloadPrompts(true);
MPyReq.python("3.12");
MPyReq.gitrepo("https://github.com/facebookresearch/vggt.git");
reqTxt = MPyReq.pathTo("vggt") + filesep + "requirements.txt";
MPyReq.requirementTextFile(reqTxt, Name="vggtPackages");
```
## Reference Python Code
```python
import torch
from vggt.models.vggt import VGGT
from vggt.utils.load_fn import load_and_preprocess_images
device = "cuda" if torch.cuda.is_available() else "cpu"
dtype = torch.bfloat16 if torch.cuda.get_device_capability()[0] >= 8 else torch.float16
model = VGGT.from_pretrained("facebook/VGGT-1B").to(device)
image_names = ["path/to/imageA.png", "path/to/imageB.png", "path/to/imageC.png"]
images = load_and_preprocess_images(image_names).to(device)
with torch.no_grad():
with torch.cuda.amp.autocast(dtype=dtype):
predictions = model(images)
```
## Inference
```matlab
model = py.vggt.models.vggt.VGGT.from_pretrained("facebook/VGGT-1B").to("cuda");
image_names = {'1.jpeg', '2.jpeg', '3.jpeg'};
images = py.vggt.utils.load_fn.load_and_preprocess_images(image_names).to("cuda");
py.torch.no_grad();
py.torch.cuda.amp.autocast(dtype="torch.bfloat16");
predictions = model(images);
% Extract and visualize point cloud
wp = double(predictions{'world_points'}.cpu().detach().numpy());
xyz = permute(squeeze(wp(1,1,:,:,:)), [1 2 3]);
c = im2uint8(permute(squeeze(wp(1,:,:,:,1)), [2 3 1]));
pcshow(xyz);
figure, montage(image_names);
```
## Notes
- Uses `.from_pretrained()` which auto-downloads weights from HuggingFace — no `MPyReq.weights()` needed.
- `torch.no_grad()` and `torch.cuda.amp.autocast()` are called as functions (not context managers) since MATLAB cannot use `with` statements.
- Dict-style output access uses `predictions{'world_points'}` syntax.
- Point cloud output is visualized with `pcshow` — requires Computer Vision Toolbox.
- Multi-image input is passed as a cell array of filenames.
----
Copyright 2026 The MathWorks, Inc.
----
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deployment | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |