The training does not converge about spatial-transformer-network HOT 10 OPEN

me too

from spatial-transformer-network.

me too, and all of the images in samples are empty

from spatial-transformer-network.

Hey guys, I'll take a look at the code when I get the time.

from spatial-transformer-network.

I have the same issue. Looks like it is related to the initialization of the conv and fc layers. I tried only using fc layers for regression and the training converged. Remember to initialize the weight to zeros and bias to identity.

Haven't figured out how to initialize conv layers yet. If anyone make progress on this please let us know.

from spatial-transformer-network.

i think that the bilinear interpolation process in funtion bilinear_sampler is wrong, and a good example of this process can be found in https://github.com/tensorflow/models/tree/master/research/transformer
` # get pixel value at corner coords
Ia = get_pixel_value(img, x0, y0)
Ib = get_pixel_value(img, x0, y1)
Ic = get_pixel_value(img, x1, y0)
Id = get_pixel_value(img, x1, y1)

# recast as float for delta calculation
x0 = tf.cast(x0, 'float32')
x1 = tf.cast(x1, 'float32')
y0 = tf.cast(y0, 'float32')
y1 = tf.cast(y1, 'float32')

# calculate deltas
wa = (x1-x) * (y1-y)
wb = (x1-x) * (y-y0)
wc = (x-x0) * (y1-y)
wd = (x-x0) * (y-y0)

# add dimension for addition
wa = tf.expand_dims(wa, axis=3)
wb = tf.expand_dims(wb, axis=3)
wc = tf.expand_dims(wc, axis=3)
wd = tf.expand_dims(wd, axis=3)

# compute output
out = tf.add_n([wa*Ia, wb*Ib, wc*Ic, wd*Id])`

from spatial-transformer-network.

me too

from spatial-transformer-network.

how to start the training?

from spatial-transformer-network.

如何开始培训？

Excuse me,do you know how to train now?

from spatial-transformer-network.

Excuse me, I would like to know how to start training the model？thank you！

from spatial-transformer-network.

I think the problem is the gradients of bilinear sampling can not be auto-generated by tensorflow properly. In the original paper, author defined special gradients during this process, and this package has not included it for now.

from spatial-transformer-network.