# DeepSparkInference **Repository Path**: fengying11/deepsparkinference ## Basic Information - **Project Name**: DeepSparkInference - **Description**: DeepSparkInference推理模型示例库一期甄选了48个推理模型示例,涵盖计算机视觉,自然语言处理,语音识别等领域,后续将逐步拓展更多AI领域。 - **Primary Language**: Python - **License**: Apache-2.0 - **Default Branch**: master - **Homepage**: None - **GVP Project**: No ## Statistics - **Stars**: 0 - **Forks**: 31 - **Created**: 2024-03-27 - **Last Updated**: 2024-03-27 ## Categories & Tags **Categories**: Uncategorized **Tags**: None ## README # DeepSparkInference DeepSparkInference推理模型库作为DeepSpark开源社区的核心项目,于2024年3月正式开源,一期甄选了48个推理模型示例,涵盖计算机视觉,自然语言处理,语音识别等领域,后续将逐步拓展更多AI领域。 DeepSparkInference中的模型提供了在国产推理引擎IGIE或IxRT下运行的推理示例和指导文档,部分模型提供了基于国产通用GPU[智铠100](https://www.iluvatar.com/productDetails?fullCode=cpjs-yj-tlxltt-zk100)的评测结果。 IGIE(Iluvatar GPU Inference Engine)是基于TVM框架研发的高性能、高通用、全流程的AI推理引擎。支持多框架模型导入、量化、图优化、多算子库支持、多后端支持、算子自动调优等特性,为推理场景提供易部署、高吞吐量、低延迟的完整方案。 IxRT(Iluvatar CoreX RunTime)是天数智芯自研的高性能推理引擎,专注于最大限度发挥天数智芯通用GPU 的性能,实现各领域模型的高性能推理。IxRT支持动态形状推理、插件和INT8/FP16推理等特性。 DeepSparkInference将按季度进行版本更新,后续会逐步丰富模型类别并拓展大模型推理。 ## Computer Vision ### Classification
Models Precison IGIE IxRT
AlexNet FP16 Supported Supported
INT8 Supported Supported
CLIP FP16 Supported -
INT8 - -
Conformer-B FP16 Supported -
INT8 - -
CSPResNet50 FP16 - Supported
INT8 - Supported
DenseNet121 FP16 Supported -
INT8 - -
EfficientNet-B0 FP16 Supported Supported
INT8 - Supported
EfficientNet_B1 FP16 - Supported
INT8 - Supported
GoogLeNet FP16 Supported Supported
INT8 Supported Supported
HRNet-W18 FP16 Supported -
INT8 - -
InceptionV3 FP16 Supported -
INT8 Supported -
MobileNetV2 FP16 Supported Supported
INT8 Supported Supported
MobileNetV3 FP16 - Supported
INT8 - -
RepVGG FP16 - Supported
INT8 - -
Res2Net50 FP16 - Supported
INT8 - -
ResNet101 FP16 - Supported
INT8 - -
ResNet18 FP16 Supported Supported
INT8 Supported Supported
ResNet34 FP16 - Supported
INT8 - Supported
ResNet50 FP16 Supported Supported
INT8 Supported -
ResNeXt50_32x4d FP16 Supported -
INT8 Supported -
ShuffleNetV1 FP16 - Supported
INT8 - -
SqueezeNet 1.0 FP16 - Supported
INT8 - Supported
Swin Transformer FP16 Supported -
INT8 - -
VGG16 FP16 Supported Supported
INT8 Supported -
### Detection
Models Precison IGIE IxRT
RetinaNet FP16 Supported -
INT8 - -
YOLOv3 FP16 Supported -
INT8 Supported -
YOLOv4 FP16 Supported -
INT8 Supported -
YOLOv5 FP16 Supported -
INT8 Supported -
YOLOv6 FP16 Supported -
INT8 - -
YOLOv7 FP16 Supported -
INT8 Supported -
YOLOv8 FP16 Supported -
INT8 Supported -
YOLOX FP16 Supported Supported
INT8 Supported Supported
### Segmentation
Models Precison IGIE IxRT
Mask R-CNN FP16 - Supported
INT8 - -
### Trace
Models Precison IGIE IxRT
FastReID FP16 Supported -
INT8 - -
DeepSort FP16 Supported -
INT8 Supported -
## NLP ### Language Model
Models Precison IGIE IxRT
BERT Base NER FP16 - -
INT8 Supported -
BERT Base SQuAD FP16 Supported Supported
INT8 - -
BERT Large SQuAD FP16 Supported Supported
INT8 Supported Supported
## Speech ### Speech Recognition
Models Precison IGIE IxRT
Conformer FP16 Supported -
INT8 - -
------ ## 社区 ### 治理 请参见 DeepSpark Code of Conduct on [Gitee](https://gitee.com/deep-spark/deepspark/blob/master/CODE_OF_CONDUCT.md) or on [GitHub](https://github.com/Deep-Spark/deepspark/blob/main/CODE_OF_CONDUCT.md)。 ### 交流 请联系 contact@deepspark.org.cn。 ### 贡献 请参见 [DeepSparkInference Contributing Guidelines](CONTRIBUTING.md)。 ## 许可证 本项目许可证遵循[Apache-2.0](LICENSE)。