test a batch about flownet2-tf HOT 2 OPEN

Have the same request, any idea?

from flownet2-tf.

You should use sess.run with feed_dict and change the input.
Firstly we create a placeholder for images:

im1_pl = tf.placeholder(tf.float32, [n, res.shape[0], res.shape[1], 3])
im2_pl = tf.placeholder(tf.float32, [n, res.shape[0], res.shape[1], 3])
#n is the size of your batch

and rewrite inputs in this way:
inputs = {'input_a': im1_pl, 'input_b': im2_pl}

then in running of a session:
first_sequence=[images you want]
second_sequence=[images you want]
feed_dict = {im1_pl: first_sequence , im2_pl: second_sequence}

and give this feed_dict to sess.run:
pred_flow = sess.run(pred_flow, feed_dict = feed_dict)[0, :, :, :]

from flownet2-tf.