Gemte
Vælg det navn, der skal vises i menuen Gemte.
Færdig!
| Udvikler: | Linn Lim (6) | ||
| Pris: | ▼ $4.99 | ||
| Vurdering: | 960 Sølv | ||
| Rangeringer: | 0 | ||
| Kommentarer: | 0 Skriv kommentar | ||
| Lister: | 0 + 0 | ||
| Point: | 0 + 0 ¡ | ||
| +1 Point | |||
Beskrivelse
Train a custom detector on your own image folders in minutes. The trainer automatically calibrates a working threshold, exports a portable ONNX model, and writes everything you need so the model is production-ready the moment training finishes. No separate calibration step, no Python environment to set up, no glue code to write.
Run inference with ONNX Runtime — fast, portable, and PyTorch-free at predict time. Score thousands of images, view side-by-side heatmap overlays that show exactly where each anomaly is, and export verdicts to CSV with one click.
For QA and manufacturing teams — point AnomalyKit at a folder of "good" example images plus a folder of known defects, and you get a working visual inspector. The calibration tool helps you pick conservative thresholds for high-recall inspection or aggressive thresholds when false alarms matter. Models exported by AnomalyKit can be integrated into existing line software via ONNX Runtime.
For ML engineers and researchers — AnomalyKit ships a faithful implementation of SimpleNet (CVPR 2023) with WideResNet50 and ResNet50 backbones, full PyTorch 2.12 training pipeline, ONNX export with verification, and built-in support for MVTec-style dataset layouts. Reproduce paper benchmarks, evaluate against your own data, or use the underlying scripts directly.
What's included:
SimpleNet Train & Eval — full training pipeline with CUDA, auto-calibration, ONNX export
Predict Anomalies — ONNX inference with heatmap visualization and CSV export
Threshold Calibration — histogram analysis, ROC/F1 metrics, three operating points (optimal, conservative, aggressive)
Supervised Classifier Suite — binary good/defect classification, separate from the unsupervised SimpleNet path
Dataset Builder — guided folder-structure creation for MVTec-style training
Binary Mask Annotator — paint defect regions for supervised pipelines
Environment Health — diagnostics for the bundled stack
AnomalyKit bundles a complete Python environment: PyTorch 2.12 with CUDA 13, ONNX Runtime with DirectML, and every dependency needed for both training and inference. Install once and run — no separate setup, no version conflicts, no missing DLLs.
Built for Windows 10 and Windows 11. NVIDIA GPU recommended for training; CPU and integrated graphics work for inference. Fully offline, with no telemetry or network calls of any kind.
Skærmbilleder





Ad
Prishistorie
- Nuværende pris: $4.99
$9.99-50% - Minimum: ▼ $4.99
- Maksimalt: $9.99
Overvåg priser
AppAgg-vurdering
960
Estimeret AppAgg-vurdering for
AnomalyKit
960 Sølv
Højere vurderinger betyder som regel stærkere signaler på AppAgg.
Baseret på: popularitet · brugervurderinger · aktualitet · tilbud · butiksdata · fællesskabsaktivitet
Genberegnes dagligt ud fra aktuelle AppAgg-data.
Kort webadresse: Kopieret!
Nyheder
- Version: PC
- Sidst opdateret:
Yderligere oplysninger
- Udgivelsesdato:
- Kategori:
Windows Apps›Udviklerværktøjer - Operativsystem:
PC - Størrelse:
2 Gb - Understøttet sprog:
English - Indholdsklassificering:
EVERYONE - Windows Store Bedømmelse:
0
Udvikler
- Linn Lim
- Platforme: Windows Apps (5) Windows Spil (1)
- Lister: 0 + 0
- Point: 0 + 0 ¡
- Rangeringer: 0
- Kommentarer: 0
- Rabatter: 2
- Videoer: 0
- RSS: Abonner
Lister (0)
0
- AnomalyKit
Point (0)
0
Rangeringer (0)
0
Kommentarer (0)
Vær den første til at kommentere
Kort fortalt
- Del
- Windows Store
«AnomalyKit». Platform: Windows. Kategori: Udviklerværktøjer. Udvikler: «Linn Lim». Første udgivelse: . Sidste opdatering: . Tidligere pris: $9.99. Nuværende pris: $4.99 (50% rabat). Laveste registrerede pris: $4.99 (). Højeste registrerede pris: $9.99 (). Denne titel har endnu ikke modtaget vurderinger eller anmeldelser på AppAgg. Tilgængelige sprog: English. AppAgg sporer prishistorik, vurderinger og brugerfeedback for «AnomalyKit». AppAgg hoster ikke applikationer eller distribuerer software. Alle varemærker, logoer og skærmbilleder tilhører deres respektive ejere. Følg fremtidige rabatter og opdateringer via RSS
Lignende
-
- Total War: Warhammer II – Assembly Kit
- Windows Apps: Udviklerværktøjer Ved: Creative Assembly Ltd
- Gratis
- Lister: 0 0 0
- Point: 0 + 0 550 · Bronze Version: PC Welcome to the Total War: WARHAMMER II Assembly Kit. These powerful tools allow you to edit and create new experiences within the game, from new characters, factions, battle maps and ...
-
- HTML Developer Kit
- Windows Apps: Udviklerværktøjer Ved: Carlos Rafael Ramirez
- Gratis
- Lister: 0 0 0
- Point: 1 + 7 570 · Bronze Version: PC HTML Developer Kit allows you to author, edit, preview and save HTML documents.
-
- exabox —Developer survival kit
- Windows Apps: Udviklerværktøjer Ved: Alberto Malagoli
- $9.99
- Lister: 0 + 1 0 0
- Point: 0 + 0 1K · Sølv Version: PC exabox is a set of 30+ essential tools for developers. With it you can: convert JSON to YAML, encode and decode Base64 values, generate fake data, parse JWTs, transform a text using ...
-
- Database Designer SDK
- Windows Apps: Udviklerværktøjer Ved: Ezyware Software
- $6.99
- Lister: 0 + 1 0 0
- Point: 3 + 0 1K · Sølv Version: PC Database Designer Software Development kit is a tool for designing and developing standalone custom desktop database software applications for all versions of Windows Designed for ...
-
- SearchInFiles
- Windows Apps: Udviklerværktøjer Ved: Andrew Whitechapel
- Gratis
- Lister: 1 + 1 0 0
- Point: 1 + 0 660 · Sølv Version: PC A simple app that allows you to search for text in files. You can search in any files in any folder to which you have access. One example is searching for a supported API in the ...
-
- JS King
- Windows Apps: Udviklerværktøjer Ved: Neonway
- $4.99
- Lister: 0 0 0
- Point: 0 + 0 590 · Bronze Version: PC Try 1 day for FREE! Be the King of JavaScript! Edit and run JavaScript-Code right away with just one click. Take advantage of the build-in components: - JavaScript-interpreter: no ...