基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
探索 AI 模型 1529
This model features: * ReLU activations * tiered 3-layer stem of 3x3 convolutions with pooling * 2x2 average pool + 1x1 convolution shortcut downsample * Efficient Channel Attention Recipe details: * ResNet Strikes Back `A1` recipe * LAMB optimizer with BCE loss * Cosine LR schedule with warmup
译文排队中 · 当前显示来源原文
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
An EdgeNeXt image classification model. Trained on ImageNet-1k by paper authors using distillation (`USI` as per `Solving ImageNet`). - **Model Type:** Image classification / feature backbone - **Model Stats:** - Params (M): 5.6 - GMACs: 1.3 - Activations (M): 9.1 - Image size: train = 256 x 256, test = 320 x 320 - **Papers:** - EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications: https://arxiv.org/abs/2206.10589 - Solving ImageNet: a Unified Scheme for Training any Backbone to Top Results: https://arxiv.org/abs/2204.03475 - **Dataset:** ImageNet-1k - **Original:** https://github.com/mmaaz60/EdgeNeXt
译文排队中 · 当前显示来源原文
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
A EfficientNet image classification model. Trained on ImageNet-1k in `timm` using recipe template described below. Recipe details: * RandAugment `RA` recipe. Inspired by and evolved from EfficientNet RandAugment recipes. Published as `B` recipe in ResNet Strikes Back. * RMSProp (TF 1.0 behaviour) optimizer, EMA weight averaging * Step (exponential decay w/ staircase) LR schedule with warmup - **Model Type:** Image classification / feature backbone - **Model Stats:** - Params (M): 5.3 - GMACs: 0.4 - Activations (M): 6.7 - Image size: 224 x 224 - **Papers:** - EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks: https://arxiv.org/abs/1905.11946 - ResNet strikes back: An improved training procedure in timm: https://arxiv.org/abs/2110.00476 - **Dataset:** ImageNet-1k - **Original:** https://github.com/huggingface/pytorch-image-models
译文排队中 · 当前显示来源原文
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
A EfficientNet image classification model. Fine-tuned on ImageNet-1k from original Tensorflow "SAME" padding weights for use in PyTorch.
译文排队中 · 当前显示来源原文
Trained with `timm` scripts using hyper-parameters inspired by the MobileNet-V4 small, mixed with go-to hparams from `timm` and "ResNet Strikes Back". A collection of hparams (timm .yaml config files) for this training series can be found here: https://gist.github.com/rwightman/f6705cb65c03daeebca8aa129b1b94ad
译文排队中 · 当前显示来源原文
A EfficientNet image classification model. Trained on ImageNet-1k in `timm` using recipe template described below. Recipe details: * RandAugment `RA` recipe. Inspired by and evolved from EfficientNet RandAugment recipes. Published as `B` recipe in ResNet Strikes Back. * RMSProp (TF 1.0 behaviour) optimizer, EMA weight averaging * Step (exponential decay w/ staircase) LR schedule with warmup - **Model Type:** Image classification / feature backbone - **Model Stats:** - Params (M): 9.1 - GMACs: 0.9 - Activations (M): 12.8 - Image size: train = 256 x 256, test = 288 x 288 - **Papers:** - EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks: https://arxiv.org/abs/1905.11946 - ResNet strikes back: An improved training procedure in timm: https://arxiv.org/abs/2110.00476 - **Dataset:** ImageNet-1k - **Original:** https://github.com/huggingface/pytorch-image-models
译文排队中 · 当前显示来源原文
A EfficientNet image classification model. Trained on ImageNet-1k in `timm` using recipe template described below. Recipe details: * RandAugment `RA2` recipe. Inspired by and evolved from EfficientNet RandAugment recipes. Published as `B` recipe in ResNet Strikes Back. * RMSProp (TF 1.0 behaviour) optimizer, EMA weight averaging * Step (exponential decay w/ staircase) LR schedule with warmup - **Model Type:** Image classification / feature backbone - **Model Stats:** - Params (M): 12.2 - GMACs: 1.6 - Activations (M): 21.5 - Image size: train = 288 x 288, test = 320 x 320 - **Papers:** - EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks: https://arxiv.org/abs/1905.11946 - ResNet strikes back: An improved training procedure in timm: https://arxiv.org/abs/2110.00476 - **Dataset:** ImageNet-1k - **Original:** https://github.com/huggingface/pytorch-image-models
译文排队中 · 当前显示来源原文
A EfficientNet image classification model. Trained on ImageNet-1k in `timm` using recipe template described below. Recipe details: * RandAugment `RA2` recipe. Inspired by and evolved from EfficientNet RandAugment recipes. Published as `B` recipe in ResNet Strikes Back. * RMSProp (TF 1.0 behaviour) optimizer, EMA weight averaging * Step (exponential decay w/ staircase) LR schedule with warmup - **Model Type:** Image classification / feature backbone - **Model Stats:** - Params (M): 19.3 - GMACs: 3.1 - Activations (M): 34.8 - Image size: train = 320 x 320, test = 384 x 384 - **Papers:** - EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks: https://arxiv.org/abs/1905.11946 - ResNet strikes back: An improved training procedure in timm: https://arxiv.org/abs/2110.00476 - **Dataset:** ImageNet-1k - **Original:** https://github.com/huggingface/pytorch-image-models
译文排队中 · 当前显示来源原文
A EfficientNet image classification model. Pretrained on ImageNet-12k and fine-tuned on ImageNet-1k by Ross Wightman in `timm` using recipe template described below. Recipe details: * Based on Swin Transformer train / pretrain recipe with modifications (related to both DeiT and ConvNeXt recipes) * AdamW optimizer, gradient clipping, EMA weight averaging * Cosine LR schedule with warmup
译文排队中 · 当前显示来源原文
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
暂未找到匹配模型
可以调整厂商、分类或输入输出条件;新模型正持续收录。
好模型,也要算好成本。
调整月度 Token 用量,直观比较不同模型的预估 API 开支。
仅比较同一渠道的基础文本 Token 报价
使用已采集且单位可比的 USD / 百万 Token 渠道报价。报价为采集时快照;不计缓存优惠、阶梯价、推理额外输出与税费,请以来源的当前报价为准。
读懂模型,再做选择
API 价格应该怎么比较?+
先区分输入、输出和缓存价格,再使用同一任务和用量估算总费用。图像、音频和视频可能按张、时长或分辨率计费,不能直接与 Token 单价比较。
开放权重,就代表可以免费商用吗?+
不一定。必须逐一核对具体模型版本的许可证、商用限制及使用政策。自己部署还需要考虑显存、推理资源和运维费用。
排行榜第一,就是最适合我的模型吗?+
榜单取决于测试任务、版本与评测方法。建议用实际业务样本比较准确性、时延、稳定性和成本,再选择模型。