EngineX-Iluvatar/enginex-bi_series-vc-cnn
17
1
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

update readme

Browse Source
This commit is contained in:
zhousha
2025-08-12 18:32:14 +08:00
parent 9d18371bb7
commit 8bc7005d63
2 changed files with 18 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

BIN
.DS_Store vendored
View File

Binary file not shown.

18
README.md
View File

@@ -1,2 +1,20 @@
# image-classification-transformers # image-classification-transformers
transformers框架支持多种图像分类模型，现对天垓100加速卡进行transformers框架的适配并且带入到信创算力测试框架中。将视觉分类模型放在天数卡（天垓100）上运行且测试性能，与CPU(4c)运行结果对比，注意该测试框架下的模型需适配transformers库
【天垓100模型适配情况】
| 模型地址 | 类型 | 适配状态 | 天垓100准确率 | 天垓100吞吐量（张/秒） | cpu准确率 | cpu吞吐量（4C）（张/秒） | Submit Id |
| ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- |
| https://www.modelscope.cn/models/apple/mobilevit-x-small | MobileViT | 成功 | 22.6667% | 31.6415 | 22.6667% | 2.6574 | 249973 |
| https://www.modelscope.cn/models/facebook/convnextv2-tiny-22k-384 | ConvNeXt V2（ConvNeXt 模型的改进版本） | 成功 | 29.3333% | 25.1330 | 29.3333% | 0.7301 | 249985 |
| https://www.modelscope.cn/models/google/vit-base-patch16-224 | ViT（Vision Transformer） | 成功 | 29.3333% | 40.0226 | 29.3333% | 1.1306 | 249992 |
| https://www.modelscope.cn/models/microsoft/beit-base-patch16-224-pt22k-ft22k | BEiT（BERT Pre-training of Image Transformers） | 成功 | 34.0000% | 23.7485 | 34.0000% | 0.9773 | 249537 |
| https://www.modelscope.cn/models/microsoft/swinv2-tiny-patch4-window16-256 | Swin Transformer V2（基于Swin Transformer） | 成功 | 29.3333% | 13.8379 | 29.3333% | 1.0331 | 249557 |
| https://www.modelscope.cn/models/timm/mobilenetv3_small_100.lamb_in1k | MobileNetV3（Google 提出的 MobileNet 系列第三代） | 失败 | | | | | 250057 |
| https://www.modelscope.cn/models/timm/resnet50.a1_in1k | ResNet（Residual Network | 失败 | | | | | 250004 |
| https://www.modelscope.cn/models/facebook/deit-small-patch16-224 | DeiT（Data-efficient Image Transformer）由 Facebook AI 提出 | 成功 | 29.3333% | 40.5675 | 29.3333% | 3.2749 | 250034 |
| https://www.modelscope.cn/models/microsoft/dit-base-finetuned-rvlcdip | DiT(Document Image Transformer) | 成功 | 0.0000% | 35.5122 | 0.0000% | 1.0823 | 250035 |
| https://www.modelscope.cn/models/microsoft/cvt-13 | CvT(Convolutional Vision Transformer) | 成功 | 29.3333% | 27.1214 | 29.3333% | 1.7240 | 250039 |
| https://www.modelscope.cn/models/google/efficientnet-b7 | EfficientNet 架构（基于卷积神经网络CNN） | 成功 | 28.6667% | 10.0449 | 28.6667% | 0.1541 | 250042 |
| https://www.modelscope.cn/models/microsoft/resnet-18 | ResNet（Residual Network） | 成功 | 22.6667% | 43.5976 | 22.6667% | 7.3915 | 250047 |