Question:

I'm using Tensorflow's <a href="https://github.com/tensorflow/models/tree/master/object_detection" rel="nofollow">Object Detection API</a>, but get the following error when training:

<blockquote>

InvalidArgumentError (see above for traceback): assertion failed: [maximum box coordinate value is larger than 1.01: ] [1.47]

</blockquote>

I get the error when I use any of the following:

<ul><li>faster_rcnn_inception_resnet_v2_atrous_coco </li> <li>rfcn_resnet101_coco</li> </ul>

But NOT when I use:

<ul><li>ssd_inception_v2_coco </li> <li>ssd_mobilenet_v1_coco</li> </ul>

My training images are a mixture of 300x300 and 450x450 pixels. I don't believe any of my bounding boxes are outside the image coordinates. Even if that's the case why would the last two models work but not the resnet models?

After looking at my raw bounding box data, turns out there were a few random instances where the bounding box coordinates either had very large numbers or negative numbers (not sure how that happened to begin with). I deleted these and now I have no issue training any of the models.

The first two networks you mentioned seem to be using a value between 0 and 1 to define the position of the bounding boxes. For that reason, I was getting the same error.

I had to change the script to create the TF records, from something like this:

# Assuming `x` & `y` are floats with the coordinates of the top-left corner: xmin = x ymin = y # Assuming `width` & `height` are floats with the size of the box xmax = x + width ymax = y + height

To something like this:

# Assuming `x` & `y` are floats with the coordinates of the top-left corner: xmin = x / image_width ymin = y / image_height # Assuming `width` & `height` are floats with the size of the box xmax = (x + width) / image_width ymax = (y + height) / image_height