MODEL PROFILE

tf_efficientnetv2_s.in21k_ft_in1k

timm · tf_efficientnetv2_s.in21k_ft_in1k

A EfficientNet-v2 image classification model. Trained on ImageNet-21k and fine-tuned on ImageNet-1k in Tensorflow by paper authors, ported to PyTorch by Ross Wightman. - **Model Type:** Image classification / feature backbone - **Model Stats:** - Params (M): 21.5 - GMACs: 5.4 - Activations (M): 22.7 - Image size: train = 300 x 300, test = 384 x 384 - **Papers:** - EfficientNetV2: Smaller Models and Faster Training: https://arxiv.org/abs/2104.00298 - **Dataset:** ImageNet-1k - **Pretrain Dataset:** ImageNet-21k - **Original:** https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet Explore the dataset and runtime metrics of this model in timm model results.

Visual QAlicense:apache-2.0
Context windowNot disclosed
Input → OutputImage → Text
Model weightsOpen weights
Profile updated2026/11/15 11:10:43
OVERVIEW

Model overview

A EfficientNet-v2 image classification model. Trained on ImageNet-21k and fine-tuned on ImageNet-1k in Tensorflow by paper authors, ported to PyTorch by Ross Wightman. - **Model Type:** Image classification / feature backbone - **Model Stats:** - Params (M): 21.5 - GMACs: 5.4 - Activations (M): 22.7 - Image size: train = 300 x 300, test = 384 x 384 - **Papers:** - EfficientNetV2: Smaller Models and Faster Training: https://arxiv.org/abs/2104.00298 - **Dataset:** ImageNet-1k - **Pretrain Dataset:** ImageNet-21k - **Original:** https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet Explore the dataset and runtime metrics of this model in timm model results.

The summary below is compiled from sources by an AI model, not our own testing. Verify selection decisions against original sources and your workload.

Key features

  • Based on EfficientNet-V2 architecture with optimized scaling and training improvements
  • Pretrained on ImageNet-21k and fine-tuned on ImageNet-1k for strong transfer learning capability
  • Supports variable input resolution (train at 300×300, test at 384×384) and serves as both classifier and feature backbone

Limitations & considerations

  • No explicit mention of robustness to distribution shift, adversarial examples, or out-of-distribution inputs
  • No information provided about inference latency, memory footprint under constrained environments, or quantization support
  • License and usage constraints are not detailed beyond 'apache-2.0' tag — no clarification on commercial use, modification, or attribution requirements
PRICING & COST

Source prices & cost analysis

Prices vary by channel, region and configuration. Channel quotes are listed independently and are not treated as a single official provider price.

Source / channelInputOutputBilling unitCollected at
No verified prices yet. Check the source channel.

Estimate monthly base token costs

—

Estimates exclude cache discounts, tiered pricing, multimodal surcharges, web search, taxes and additional reasoning output.

INDEPENDENT BENCHMARKS

Public benchmarks & run configuration

暂无已采集的可核验公开评分。模型未上榜不代表能力较低。

View full indexed rankings →

Frequently asked questions

What is the input image size expected during inference?

The model expects test-time input images of size 384 × 384.

Which datasets were used for pretraining and fine-tuning?

It was pretrained on ImageNet-21k and fine-tuned on ImageNet-1k.

Is this model natively implemented in PyTorch or ported from another framework?

It was originally trained in TensorFlow by the paper authors and ported to PyTorch by Ross Wightman.

Do open weights permit free commercial use?

Not necessarily. Check the version license, commercial conditions and usage policies. Self-hosting incurs compute and maintenance costs.

Are these real-time billing prices?

These are timestamped source snapshots, not live billing prices. Check the channel for current versions, regions, discounts and billing methods.

Sources & traceability

许可证:apache-2.0。模型介绍与第三方评测均以原来源的具体版本和方法为准。