Mask RCNN model shape error while generating prediction from unseen dataset

Open
#176 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty
4/5
Estimated time
3-5 days
Newbie friendliness
25/100
Issue type
Bug
Clarity
Needs clarification
Activity status
Stale
Tech stack
jupyter-notebook, tensorflow

Research direction

Start with the MaskRCNN_ZeroCostDL4Mic.ipynb notebook linked in the issue, focusing on section 6 where the trained .h5 model is loaded for prediction. Reproduce the mrcnn_bbox_fc weight-shape error using the reported 256×256 PNG input and compare the training and prediction configurations; done means prediction generation no longer produces the reported mismatch.

Written by the indexing model from the issue text.

Description

I have trained maskrcnn (https://github.com/HenriquesLab/ZeroCostDL4Mic/blob/master/Colab_notebooks/Beta%20notebooks/MaskRCNN_ZeroCostDL4Mic.ipynb) on nucleus dataset with cancer and non-cancerous class. I have resized images into 256 x 256.
Notebook works smoothly till section 5 but in section 6, I got following error : "
ValueError: Layer #391 (named "mrcnn_bbox_fc"), weight <tf.Variable 'mrcnn_bbox_fc_6/kernel:0' shape=(1024, 4) dtype=float32> has shape (1024, 4), but the saved weight has shape (1024, 12) ".
Used .h5 model file I trained for generating prediction. My input image is in .png format.

Dominant language
Jupyter Notebook
Stars
652
Forks
144
PR merge metrics
No merged PRs in 30d

Contributor guide

No contributing guide indexed for this repository

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 HenriquesLab/ZeroCostDL4Mic

All issues in HenriquesLab/ZeroCostDL4Mic

Similar issues

More Computer Vision issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.