Srihari Humbarwadi

Here is the signature of the current implementation of `pack_nbrs` --- ```python def pack_nbrs(labeled_examples_path, unlabeled_examples_path, graph_path, output_training_data_path, add_undirected_edges=False, max_nbrs=None, id_feature_name='id'): ``` `labeled_examples_path` and `unlabeled_examples_path` are paths to a single TFRecord...

Thank you @aheydon-google, I will start working on this!

@aheydon-google I'll push some changes in a couple of days!

Can you please explain how this repository is related to the issue? Do you see a similar error while running the code in this repository?

https://github.com/srihari-humbarwadi/TensorRT-for-keras/blob/master/keras_freeze_model.py https://github.com/srihari-humbarwadi/TensorRT-for-keras/blob/master/optimize_graph.py @mrgloom this is something similar to what you were suggesting

@siriusmehta Yeah you can added any backbone you wish, only thing that you need to take care is the scales of the feature map that go into the FPN

I didn't run the code with your changes. But by looking at the error message, its likely that you are feeding in the wrong feature layers from the backbone. IIRC...

@vismayaps this should help you run inference with your own images ```python image_path = ... # path to your image file image = tf.image.decode_image(tf.io.read_file(image_path), channels=3) image = tf.cast(image, dtype=tf.float32) input_image,...

To make sure that the example doesn't have a lot of code around processing and preparing the data, we uses tensorflow-datasets to load mscoco dataset. If you wish to train...

It follows the format returned by the tensorflow_datasets builders, You can try matching it by doing something like --- ``` { "image": , "objects": { "bbox": [ [y1, x1, y2,...