tensorflow / tensorflow/model-optimization
Support Quantizing a tf.keras Model inside another tf.keras Model
Open
Nobody has claimed this yet.
feature request
- Dominant language
- Python
- Stars
- 1.6k
- Forks
- 349
- Avg merge
- 3d 2h
- Merged PRs (30d)
- 1
Description
Right now if I do something like
Quantize functional model
inputs = tf.keras.Input((3,))
out = tf.keras.layers.Dense(2)(inputs)
seq = tf.keras.Sequential()
seq.add(tf.keras.layers.Dense(2))
model = tf.keras.Model(inputs, seq(inputs))
quantized_model = quantize_model(model)
I get
Quantizing a tf.keras Model inside another tf.keras Model is not supported.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start at the quantize_model entry point and reproduce the nested-model example from the issue. Trace where the unsupported-model error is raised, then verify that quantizing a functional model containing a tf.keras.Sequential model completes successfully.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- keras, python, tensorflow
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100