0

I need to implement CAM for a model trained on the base model ssd_mobilenet_v2_320x320_coco17_tpu-8 in the pre-trained Object Detection Zoo.

How could I accesses the layers and other fields necessary to implement Grad-CAM?

I tried converting the model to other model formats (eg. Keras), where I know how to access model layers. I did not have any success with this.

Improve this question
1
  • The SavedModel format is not suitable for Grad-CAM because it obscures the model's internal structure. Instead, rebuild the Keras DetectionModel directly by calling the API's model_builder.build() function with your pipeline.config and .ckpt checkpoint. This method provides full programmatic access to the _feature_extractor and its layers. Please provide the minimum reproducible code if you are still running into any issues. Commented Nov 12 at 8:49
Related questions
2
How to reuse classification layers in Tensorflow Object Detection API
0
Freeze layers using Tensorflow Object Detection API
5
Retrain Tensorflow Object detection API
Load 5 more related questions Show fewer related questions

0

Reset to default

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Start asking to get answers

Find the answer to your question by asking.

Ask question

Explore related questions

See similar questions with these tags.