Mask RCNN model shape error while generating prediction from unseen dataset
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
- Domain
- computer-vision, machine-learning
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
- 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.
More from HenriquesLab/ZeroCostDL4Mic
-
Difficulty 3/5 1-2 days Newbie friendliness 32/100
HenriquesLab/ZeroCostDL4Mic#351 ·
-
Difficulty 4/5 3-5 days Newbie friendliness 38/100
HenriquesLab/ZeroCostDL4Mic#350 ·
-
Difficulty 5/5 Over a week Newbie friendliness 20/100
HenriquesLab/ZeroCostDL4Mic#348 · 1 comment ·
-
Difficulty 3/5 1-2 days Newbie friendliness 20/100
HenriquesLab/ZeroCostDL4Mic#347 · 1 comment ·
-
dependencies
Difficulty 4/5 3-5 days Newbie friendliness 25/100
HenriquesLab/ZeroCostDL4Mic#346 · 2 comments ·
All issues in HenriquesLab/ZeroCostDL4Mic
Similar issues
-
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
alicevision/AliceVision#2180 · 1 comment ·
-
lk_single_level's det.abs() < f64::EPSILON degeneracy guard is on the wrong scale after #130/#138 Openbug help wanted video-module
Difficulty 2/5 1-3 hours Newbie friendliness 84/100
-
Difficulty 1/5 Under an hour Newbie friendliness 88/100
alicevision/popsift#193 · 1 comment ·
-
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
-
RandomMotionBlur: the kernel_size range never draws its upper bound (truncation of a float draw) Open
Difficulty 2/5 1-3 hours Newbie friendliness 84/100