EfficientNet-B2 is a convolutional image-classification backbone; the sources show it as a backbone option in NVIDIA's TAO image classification action 11, and PyTorch 9 and ONNX 8 are general frameworks for building and exporting such models. Source 1 lists NVIDIA's TAO image classification as the one indexed action that supports EfficientNet backbones.
- 1
NVIDIA TAOnvidia.comverified and signed
Its tao-train-image-classification action trains image classifiers with PyTorch and supports backbones including EfficientNet, with distillation and quantization 11.
+81 community tools built for it
for agents: tao-train-image-classification · tao-finetune-clip · tao-train-nvdinov2
- 2
- 3
ONNXonnx.aiwebsite read, tools not yet checked
An interoperability format that lets a trained model be moved from its training framework to a chosen inference engine 8.
+55 community tools built for it
Sources
- 1Brev.dev Consolebrev.nvidia.com · read 2026-10-29
- 8ONNX | Homeonnx.ai · read 2026-10-29
- 9PyTorch Foundation - PyTorchpytorch.org · read 2026-10-29
- 11tao-train-image-classification: declares "tao-train-image-classification" (the record we read and signed)unfragile.ai · read 2026-10-24
- 19export: declares "export" (the record we read and signed)unfragile.ai · read 2026-10-24
For agents: the 10 actions behind this answer
tao-train-image-classification · tao-train-image-classification verified and signed
PyTorch-based TAO image classification. Supports a wide range of backbones (FAN, EfficientNet, ResNet, etc.) with distillation and quantization for deployment. Use when training, evaluating, distilling, quantizing, exporting, or running inference for a TAO image-classification (PyT) model. Trigger p
nano-banana-pro-openrouter · nano-banana-pro-openrouter verified and signed
Generate or edit images via OpenRouter with the Gemini 3 Pro Image model. Use for prompt-only image generation, image edits, and multi-image compositing; supports 1K/2K/4K output.
python · fastcore verified and signed
cloudflare-images-base-image · Cloudflare API verified and signed
Download image
black-forest-labs/flux-schnell-lora · black-forest-labs/flux-schnell-lora verified and signed
The fastest image generation model tailored for fine-tuned use
· Research website read, tools not yet checked
Discover Google Research. We publish research papers across a wide range of domains and share our latest developments in AI and science research.
· Ollama website read, tools not yet checked
Ollama is the easiest way to run and build with open AI models locally or in the cloud on macOS, Windows, and Linux.
· ONNX website read, tools not yet checked
export · export verified and signed
Export a PyTorch model to .pte format for ExecuTorch. Use when converting models, lowering to edge, or generating .pte files.
black-forest-labs/flux-dev-lora · black-forest-labs/flux-dev-lora verified and signed
A version of flux-dev, a text to image model, that supports fast fine-tuned lora inference
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.