Dmitry.AI

`batch_size` > 1 requires an `image_resizer` of `fixed_shape_resizer` in Tensorflow

computer-vision
object-detection
сonvolutional-neural-network
training
batch-size
tensorflow-image-resizer
tensorflow
tensorflow-object-detection
(Dmitry Fedyuk) #1

Tensorflow requires each input array to have the same dimensionality, which means that any batch_size > 1 requires an image_resizer of fixed_shape_resizer

blog.algorithmia.com/deep-dive-into-object-detection-with-open-images-using-tensorflow

What does mean «faster_rcnn» → «image_resizer» in TensorFlow?
What does mean «faster_rcnn» → «image_resizer» → «keep_aspect_ratio_resizer» in TensorFlow?
What does mean «train_config» → «batch_size» in TensorFlow?