代码拉取完成，页面将自动刷新
Our workloads demonstrate how to run inference using tensorflow.
We select four common inference scenarios, covering image classification and recognition, object detection, natural language processing, and recommendation system. The representative models used are as follows:
| Area | Task | Model |
|---|---|---|
| Vision | Image Classification | Resnet50-v1.5 and VGG19 |
| Vision | Object Detection | SSD-Resnet34 |
| Language | Natural Language Processing | BERT-Large |
| Recommendation | Click-Through Rate Prediction | DIN |
Resnet, SSD and BERT are all from the MLPerf Inference Benchmark project. DIN is the click-through rate prediction model proposed by Alibaba.
Completed images can be pulled from cape2/tensorflow.
docker pull cape2/tensorflow:latest
Run on different platforms (Yitian, Icelake, Ampere etc.) to compare the inference results:
docker run --rm cape2/tensorflow:latest
此处可能存在不合适展示的内容，页面不予展示。您可通过相关编辑功能自查并修改。
如您确认内容无涉及 不当用语 / 纯广告导流 / 暴力 / 低俗色情 / 侵权 / 盗版 / 虚假 / 无价值内容或违法国家有关法律法规的内容，可点击提交进行申诉，我们将尽快为您处理。
马建仓 AI 助手