| ---
|
| license: other
|
| library_name: ultralytics
|
| pipeline_tag: object-detection
|
| tags:
|
| - yolo
|
| - yolo26
|
| - object-detection
|
| - counter-strike
|
| - cs2
|
| ---
|
|
|
| # YOLO26 player detection for CS2 — 640x640 native crops
|
|
|
| Detects player bodies and heads, split by team, on a **640x640 centre crop at
|
| native resolution**. Trained on [fvossel/csgo-player-detection](https://huggingface.co/datasets/fvossel/csgo-player-detection), plus a small set of images that dataset does not redistribute.
|
|
|
| > ### ⚠ Intended use
|
| >
|
| > This model was trained to study how well a detector performs on a real-time task
|
| > and what that costs in latency. It is part of a demonstration project, and it is
|
| > **explicitly not meant to be used for cheating.**
|
| >
|
| > Use it offline, against bots, or on your own `-insecure` server. Not on a
|
| > VAC-secured server, not in matchmaking, not on an account you care about.
|
| >
|
| > Pointing a detector at a screen is the easy half. Acting on it is where it falls
|
| > apart: synthetic mouse input is flagged as injected by the operating system
|
| > itself, and a system that reacts in milliseconds produces an aim distribution no
|
| > human produces. Neither is a gap that a more careful implementation closes. The
|
| > [project repository](https://github.com/fvossel/RealTimeObjectDetectionCSGO) explains this in full and includes the tooling
|
| > to measure it.
|
|
|
| ## Metrics
|
|
|
| Measured on a **persistent holdout of 1204 images** that no
|
| training run has ever seen. The split is block-wise by scene, not per frame — a
|
| random per-frame split puts near-identical neighbouring frames on both sides and
|
| inflates the numbers.
|
|
|
| | | mAP50 | mAP50-95 | Precision | Recall |
|
| |---|---|---|---|---|
|
| | overall | 0.905 | 0.727 | 0.937 | 0.840 |
|
|
|
| | Class | Instances | Precision | Recall | mAP50 | mAP50-95 |
|
| |---|---|---|---|---|---|
|
| | `ct_body` | 563 | 0.922 | 0.867 | 0.919 | 0.797 |
|
| | `ct_head` | 511 | 0.930 | 0.831 | 0.888 | 0.608 |
|
| | `t_body` | 677 | 0.930 | 0.833 | 0.908 | 0.784 |
|
| | `t_head` | 634 | 0.967 | 0.828 | 0.906 | 0.718 |
|
|
|
| Class `none` (ID 0) is an empty placeholder kept so the IDs stay stable.
|
|
|
| Inference 3.9 ms per image at the reported batch size,
|
| on the training machine.
|
|
|
| ## Usage
|
|
|
| ```python
|
| from ultralytics import YOLO
|
|
|
| model = YOLO("yolo26n_csgo_20260727-231745.pt")
|
| results = model.predict("crop.png", conf=0.25, iou=0.5)
|
| ```
|
|
|
| **Feed it a 640x640 centre crop cut at native resolution, not a resized
|
| screenshot.** A 1920x1080 frame scaled down to 640 shrinks a head from roughly
|
| 13x17 px to 4x6 px, which is not the scale this model was trained on. This is the
|
| single most common way to get bad results out of it.
|
|
|
| ## Training
|
|
|
| | | |
|
| |---|---|
|
| | Base weight | `yolo26n.pt` |
|
| | Epochs | 150 |
|
| | Batch | 32 |
|
| | Image size | 640 |
|
| | Optimizer | auto, cosine LR |
|
| | Mosaic | 1.0, closed for the last 15 epochs |
|
|
|
| Augmentation is deliberately conservative: no rotation, no vertical flip, limited
|
| hue and scale. The game renders a fixed, upright world — augmenting it into poses
|
| that cannot occur costs capacity without buying robustness.
|
|
|
| Only images **confirmed by hand** were trained on. The labelling loop pre-annotates
|
| with a larger model and then confirms or corrects each image; unchecked model
|
| output never reaches training.
|
|
|
| ## Files
|
|
|
| * `yolo26n_csgo_20260727-231745.pt` — PyTorch weight, the one to use
|
| * `yolo26n_csgo_20260727-231745.onnx` — portable ONNX export
|
|
|
| No TensorRT engine is published. An `.engine` is tied to the exact GPU, driver and
|
| TensorRT version it was built on. Build your own:
|
|
|
| ```bash
|
| python scripts/export.py --weights models/yolo26n_csgo_20260727-231745.pt --format engine
|
| ```
|
|
|
| ## Licence
|
|
|
| The training images show Counter-Strike 2 and are derivative of Valve's assets.
|
| The weights are published for research. Check whether your intended use is covered
|
| before building on this.
|
|
|
