Tao train image classification vs Tao train nvdinov2
Tao train image classification is an open-source agent skill for design and media. Tao train nvdinov2 is an open-source agent skill for computer vision.
- Tao train image classification is best for train an image classifier on a folder of labeled class images.
- Tao train nvdinov2 is best for pretrain a vit backbone on my unlabeled image collection.
- What it is
- Tao train image classification is an open-source agent skill for design and media.Tao train nvdinov2 is an open-source agent skill for computer vision.
- Best for
- Train an image classifier on a folder of labeled class imagesPretrain a ViT backbone on my unlabeled image collection
- Kind
- SkillSkill
- Pricing
- Open sourceOpen source
- Platforms
- Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf, GooseClaude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf, Goose
- GitHub stars
- 4K4K
- Last commit
- Nov 2026Nov 2026
- License
- Apache-2.0Apache-2.0
- Open source
- Good for
- Train an image classifier on a folder of labeled class images; Evaluate a trained classification checkpoint on a held-out test set; Distill a larger classifier into a smaller student modelPretrain a ViT backbone on my unlabeled image collection; Export a trained NVDINOv2 checkpoint to ONNX; Run inference with a trained NVDINOv2 model on a test folder
What Tao train image classification does
Backbone selection
Covers the supported PyTorch backbones and the input resolutions some of them require.
Distillation and quantization
Provides spec settings for distilling a teacher into a smaller model and for quantizing with a calibration set.
Dataset spec mapping
Lists which dataset folders and class files each action needs and how to point the spec at them.
Checkpoint resolution
Explains how training outputs are named and how the exact epoch checkpoint is selected for later actions.
Multi-GPU training
Describes GPU count, device selection, DDP strategy and multi-node environment variables.
Common error fixes
Lists fixes for CUDA out-of-memory errors, class count mismatches, empty class folders and root directory permission failures.
What Tao train nvdinov2 does
Self-supervised ViT training
Runs teacher-student self-distillation on unlabeled images to pretrain vision transformer backbones.
Checkpoint export to ONNX
Exports a selected student checkpoint to an ONNX file for downstream use.
Inference on image folders
Runs the trained backbone over a test image directory using matching model settings.
Spec override guidance
Lists the spec keys to set for batch size, image size, epochs, GPUs and data paths.
AutoML routing rules
Describes when train actions route through AutoML and how to turn it off per run.
Troubleshooting reference
Covers common errors such as out-of-memory failures, checkpoint key mismatches and persistent worker settings.
Tao train image classification vs Tao train nvdinov2: questions
Is Tao train image classification or Tao train nvdinov2 cheaper?
Both are open source. Compare current plans on each official site.
What is the difference between Tao train image classification and Tao train nvdinov2?
Tao train image classification is an open-source agent skill for design and media. Tao train nvdinov2 is an open-source agent skill for computer vision.
