Input layer's input shape is changed by tf.layers.centerCrop height and width argument.

[linus87]

Please make sure that this is a bug. As per our
GitHub Policy,
we only address code/doc bugs, performance issues, feature requests and
build/installation issues on GitHub. tag:bug_template

System information

• Have I written custom code (as opposed to using a stock example script provided in TensorFlow.js): Yes
• OS Platform and Distribution (e.g., Linux Ubuntu 16.04): MAC 14.2.1 (23C71)
• Mobile device (e.g. iPhone 8, Pixel 2, Samsung Galaxy) if the issue happens on mobile device:
• TensorFlow.js installed from (npm or script link): script link
• TensorFlow.js version (use command below): 4.20.0
• Browser version: Chrome 126.0.6478.127
• Tensorflow.js Converter Version:

Describe the current behavior
InputLayer's input shape is changed by centerCrop layer.

Describe the expected behavior
Change arbitrary size image into specified image.

Standalone code to reproduce the issue
Provide a reproducible test case that is the bare minimum necessary to generate
the problem. If possible, please share a link to Colab/CodePen/any notebook.

const imageSize = 200; const model = tf.sequential(); model.add(tf.layers.inputLayer({batchInputShape: [1, null, null, 3]})); model.add(tf.layers.centerCrop({height: imageSize, width: imageSize})); model.summary();

Other info / logs Include any logs or source code that would be helpful to
diagnose the problem. If including tracebacks, please include the full
traceback. Large logs and files should be attached.

[gaikwadrahul8]

Hi, @linus87

Thank you for bringing this issue to our attention and I'm able to replicate the same behavior from my end which you reported in the issue template so we'll have to dig more into this and will update you soon, for reference I've added screenshot below :

Thank you for your cooperation and patience.

[github-actions]

This issue has been marked stale because it has no recent activity since 7 days. It will be closed if no further activity occurs. Thank you.