与「TensorFlow」相关的搜索结果
TensorFlow 贴吧
一个关键词就是一个贴吧，路径全站唯一。
用户
未找到
包含 TensorFlow 的内容
卧槽！微软偷偷把价值上万的AI完整课程免费扔GitHub了，几乎没人发现！
12周24节课，像打游戏一样一关关通关。从AI是什么开始，到自己手写感知机和神经网络，再到CNN、目标检测、GAN生成图片、Transformer、大模型提示工程，最后还讲负责任AI。
最猛的是每节课都是能直接跑的Jupyter Notebook，PyTorch和TensorFlow双版本都有。打开就能敲代码，敲完立刻看结果，不是那种只会讲概念的水课。
我昨晚直接肝到凌晨三点，脑子里全是卷积核在跳舞。这种级别的课，以前要么贵到离谱，要么水到想退款。现在微软直接白送。
还在纠结AI从哪学起？别再浪费时间搜了。先把这个仓库Star下来慢慢啃：
再回来谢我，真的不亏。
显示更多
AI & ML Full Course 2026! #BigData# #Analytics# #AI# #MachineLearning# #DataScience# #IoT# #IIoT# #Python# #RStats# #TensorFlow# #JavaScript# #ReactJS# #CloudComputing# #Serverless# #DataScientist# #Linux# #Programming# #Coding# #100DaysofCode#
显示更多
阿里平头哥把真武AI芯片的整套软件栈开源了。
开发者可以直接获取底层驱动，编译器，算子库和调试工具，不用只靠芯片厂商内部适配。
这套软件栈叫T-Head SAIL，已经适配PyTorch，TensorFlow，vLLM和SGLang等260多个训练与推理框架。平头哥称，主流推理框架的平均适配时间可以压到7天以内。
公司同时披露，真武AI芯片截至今年4月累计出货超过56万片，覆盖400多家客户。
显示更多
20 个 AI GitHub 仓库正把软件工程师的开发边界从“写代码”推向“编排智能体”。如果你还在纠结如何实现本地化执行，这几个库能让你直接跳过环境搭建的坑：
1. OpenClaw：实现本地 Agent 的关键，能直接在你的设备上执行计划并操作文件。
2. TensorFlow：生产级机器学习框架，处理大规模模型训练的底座。
3. 重点看这几个库的集成能力，它们能把原本需要云端 API 才能完成的逻辑，压缩到本地运行。
显示更多
KerasHub lets you use any Hugging Face checkpoint for all top models like Llama, Gemma, Mistral, etc...
Run your workflows in JAX, PyTorch, TensorFlow - inference, LoRA fine-tuning, large-scale training from scratch
Blog post:
显示更多
It's always useful to test how fast your models run on different backends -- JAX is often the fastest, but TensorFlow can surprise you!
There are often huge differences between backends. If you think that your go-to backend is "probably always fast enough", you're wrong
显示更多
Super simple Colab that shows you how to build a chatbot using Gemma 2 9B:
Built with Keras 3, runs on any backend -- JAX, PyTorch, TensorFlow. Personally recommend JAX for best performance.
显示更多
We're releasing a new high-performing open LLM: Gemma 2! Written in Keras 3, and compatible with TensorFlow, JAX, and PyTorch.
Gemma 2 comes in two sizes, 9B and 27B parameters, with standard and instruction-tuned variants. Find them here:
On Kaggle:
On Hugging Face:
显示更多
A neat feature of Keras is that its `keras.ops` API follows the NumPy API syntax exactly. And since it runs on JAX, PyTorch, TensorFlow, and NumPy itself, you can use Keras to write GPU-accelerated NumPy code that runs with any framework.
显示更多
Rewriting my old Grad-Cam code example in TensorFlow, PyTorch, and JAX. The JAX style of factoring out loss function and gradient function is growing on me.
