问题
I've trained a model with a custom dataset (Garfield images) with Tensorflow Object Detection API (ssd_mobilenet_v1 model) and referring it in the android sample application available on Tensorflow repository. The application can only detected the images in distances less or equal 20cm approximately.
Do you have any clue about I can improve the model to perform recognitions in longer distances (about 30cm or more) ?
I don't know with this limitation is related with input size I'm using (tested with images with 300x300 and 68x68) or any custom data augmentation is needed to improve that.
回答1:
SSD models are known to have worse performance on small objects. Have you tried using one of our FasterRCNN models to see if the result is acceptable?
来源：https://stackoverflow.com/questions/46674517/ssd-mobilenet-trained-model-with-custom-data-only-recognize-images-in-short-dist