C.W.K.
Stream
Lesson 05 of 07 · published

The Ecosystem Map — What Else Lives in TF

~10 min · ecosystem, keras-cv, keras-hub, tfx

Level 0Level 0
0 XP0/78 lessons0/17 achievements
0/100 XP to next level100 XP to go0% complete

What you'll reach for, and when

TensorFlow proper (the core library) is the entry point. The ecosystem around it is bigger than the core. Knowing the map prevents you from re-implementing things polished for years.

LibraryPurpose2026 status
tf.kerasHigh-level model API (Keras 3 underneath since TF 2.16)Primary API
tf.dataData pipelinesCore — won't go anywhere
TensorBoardTraining visualization, profilingActive (separate pip install from TF 2.21+)
TFLite → LiteRTMobile + edge inferenceMigrating to LiteRT
TF ServingProduction REST/gRPC serverActive
TF.jsBrowser + Node inferenceActive
KerasCVDetection, segmentation, augmentationActive
KerasHub (was KerasNLP)Pretrained LLMs (Gemma, LLaMA 3, BERT, GPT-2)Active — replacing KerasNLP
TF ProbabilityBayesian inference, MCMC, normalizing flowsActive
TF Decision Forests / YDFRandom forests, gradient-boosted treesActive — strong on tabular
TF RecommendersRetrieval + ranking systemsActive
TF AgentsRL: DQN, PPO, SAC, TD3Active
TF FederatedFederated learning on decentralized dataActive research

The unifying theme: everything in this table speaks Keras. A KerasCV YOLOv8 detector, a KerasHub BERT classifier, and a TF-DF gradient-boosted tree all expose .fit, .predict, and .save. Once you know the Keras shape, the rest of the ecosystem is one pip install away.

Code

KerasHub LLM 한 줄 호출·python
# pip install keras-hub
import keras_hub

llm = keras_hub.models.Llama3CausalLM.from_preset("llama3_instruct_8b_en")
print(llm.generate("Explain TensorFlow in one sentence:", max_length=64))

External links

Progress

Progress is local-only — sign in to sync across devices.
Spotted a bug or have feedback on this page?Report an Issue

Comments 0

🔔 Reply notifications (sign in)
Sign inPlease sign in to comment.

No comments yet — be the first.