Dynamic batch size in tensorflow

Question

I have built a classifier using tesnorflow. I generate proposal regions from images and those proposals are individually classified by my classifier.

My problem is that I do not have a constant batch size when evaluating my model. Because every image has a different number of proposals, the number of proposals to be evaluated for every image is not constant.

Right now I have set the batch size to 1, but this is inefficient and limits the processing speed of my classifier.

Below is the placeholder for the input to the model

self.image_op = tf.placeholder(tf.float32, shape=[batch_size, 48, 48, 3], name='input_image')

And this is how I feed the input to the model

def predict(self,image):
    cls_prob = self.sess.run([self.cls_prob], feed_dict={self.image_op: image})
    return cls_prob

Is there any way of setting the batch size to a dynamic value without having to restore the model for every image?

try with self.image_op = tf.placeholder(tf.float32, shape=[None, 48, 48, 3], name='input_image'). It should take variable batch sizes — Biswadip Mandal
– Biswadip Mandal, Commented Nov 22, 2018 at 4:29

Navan Chauhan · Accepted Answer · 2019-12-18 17:21:49Z

1

You can simply set tf.Variable(validate_shape=False)

This will disable the validation of shape on iterations and therefore you will be able to use dynamic batch sizes.

Since tf.placeholder is being depreciated you should not use it, but if you still want to use tf.placeholder then you need to disable TF 2.x behaviour

import tensorflow.compat.v1 as tf
tf.disable_v2_behavior()

answered Dec 18, 2019 at 17:21

Navan Chauhan

4476 silver badges16 bronze badges

Sign up to request clarification or add additional context in comments.

Collectives™ on Stack Overflow

Dynamic batch size in tensorflow

1 Answer 1

Comments

Your Answer

Linked

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

Comments

Your Answer

Sign up or log in

Post as a guest

Linked

Related