Can we detect multiple objects in image using caltech101 dataset containing label wise images?

0
votes

I have a caltech101 dataset for object detection. Can we detect multiple objects in single image using model trained on caltech101 dataset?
This dataset contains only folders (label-wise) and in each folder, some images label wise.

I have trained model on caltech101 dataset using keras and it predicts single object in image. Results are satisfactory but is it possible to detect multiple objects in single image?

As I know some how regarding this. for detecting multiple objects in single image, we should have dataset containing images and bounding boxes with name of objects in images.

Thanks in advance

1
pythonkerasdeep-learningobject-detectiontensorflow-datasets
Please edit into your question the code that you have tried, as a minimal reproducible example - balmy
I just trained some neural net using. Keras on caltech101 and save the model then predict any image - saifhassan
Just add some layers activation functions means complete network, didn't do any region maps, bboxes or other things for images - saifhassan

1 Answers

0
votes

The dataset can be used for detecting multiple objects but with below steps to be followed:

  1. The dataset has to be annotated with bounding boxes on the object present in the image

  2. After the annotations are done, you can use any of the Object detectors to do transfer learning and train on the annotated caltech 101 dataset

Note: - Without annotations, with just the caltech 101 dataset, detecting multiple objects in a single image is not possible