Hacktoberfest 2026: the issues maintainers tagged for October, open and beginner-friendly. Browse Hacktoberfest issues

DepthwiseConv2D Layers cannot be clustered or sparsely pruned

Open
  • Is something wrong?
#1,132 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty
4/5
Estimated time
3-5 days
Newbie friendliness
35/100
Issue type
Bug
Clarity
Mostly clear
Activity status
Stale
Tech stack
python, tensorflow
Domain
machine-learning

Research direction

Start by running the provided MNIST reproduction with TensorFlow Model Optimization's cluster_weights and sparse pruning APIs. Trace how DepthwiseConv2D kernels are handled, then verify that clustering produces three unique weights and that m-by-n pruning produces the expected sparsity pattern.

Written by the indexing model from the issue text.

Description

bug

When attempting to sparsely prune or cluster DepthwiseConv2D Layers it appears that no clustering or sparse pruning actually occurs.

System information

TensorFlow version (installed from source or binary): 2.16.1/2.15.1

TensorFlow Model Optimization version (installed from source or binary): 0.8.0/0.7.5

Python version: 3.9.18

Describe the expected behavior

I should see that the kernel for the Depthwise layer should have 3 unique weights, not 9.

Describe the current behavior

The Depthwise layer has 9 unique weights

The same issue occurs for sparse m by n pruning, the weights are not pruned correctly in an m by n manner

Code to reproduce the issue

import tensorflow as tf
import tensorflow_model_optimization as tfmot
from tensorflow import keras

import numpy as np

(train_images, train_labels), (test_images, test_labels) = tf.keras.datasets.mnist.load_data()
train_images = train_images / 255.0
test_images = test_images / 255.0

model = keras.Sequential([
keras.layers.InputLayer(input_shape=(28, 28)),
keras.layers.Reshape(target_shape=(28, 28, 1)),
keras.layers.DepthwiseConv2D(kernel_size=(3, 3), activation=tf.nn.relu),
keras.layers.MaxPooling2D(pool_size=(2, 2)),
keras.layers.Flatten(),
keras.layers.Dense(10)
])

model.compile(optimizer='adam',
loss=keras.losses.SparseCategoricalCrossentropy(from_logits=True),
metrics=['accuracy'])

model.fit(
train_images,
train_labels,
validation_split=0.1,
epochs=10
)

cluster_weights = tfmot.clustering.keras.cluster_weights
CentroidInitialization = tfmot.clustering.keras.CentroidInitialization

clustering_params = {
'number_of_clusters': 3,
'cluster_centroids_init': CentroidInitialization.LINEAR
}

clustered_model = cluster_weights(model, **clustering_params)

opt = keras.optimizers.Adam(learning_rate=1e-5)

clustered_model.compile(
loss=keras.losses.SparseCategoricalCrossentropy(from_logits=True),
optimizer=opt,
metrics=['accuracy'])
clustered_model.fit(
train_images,
train_labels,
batch_size=500,
epochs=1,
validation_split=0.1)

for layer in model.layers:
for weight in layer.weights:
print(weight.name)
print(len(np.unique(weight)))

Dominant language
Python
Stars
1.6k
Forks
349
No merged PRs in 30d

Getting set up

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from tensorflow/model-optimization

All issues in tensorflow/model-optimization

Similar issues

More Python issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.