StatefulPartitionedCall/map/while_loop body SSD model conversion custom trained
Open
Nobody has claimed this yet.
question
- Dominant language
- Jupyter Notebook
- Stars
- 2.6k
- Forks
- 473
- Avg merge
- 1d 3h
- Merged PRs (30d)
- 5
Description
I use tensorflow 2 to train a mobilenetv2 320 ssd object detection but if i convert the pretrained i get a model with input without the StatefulPartitionedCall/map/while_loop body if i train custom then i have this layer that break me the input from the model.Using opset 12.For Does anyone have a solution for this problem?
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 by reproducing the TensorFlow 2 conversion for a custom-trained MobileNetV2 320 SSD model with opset 12, then compare it with the pretrained conversion. Investigate the StatefulPartitionedCall/map/while_loop body and confirm that the converted model exposes the expected input without the reported layer breaking it.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- tensorflow
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100