How do I debug the middle tensor by using tf.estimator? about ssd.tensorflow HOT 6 CLOSED

@xtanitfy It's quite easy to debug or view the contents of some tensors by tensorflow, e.g. tf.Print, tf.Debug, or you can use tf.py_func to wrap any function in python with anything you can do.

from ssd.tensorflow.

Thank you very much!
But with the callback of tf.estimator, what time do I print by using tf.Print or tf.Debug?

from ssd.tensorflow.

@xtanitfy there is no necessary to use callback, you can place tf.Print anywhere in you codes

from ssd.tensorflow.

I think i can use tf.py_func to dispose of any tensor。Thanks！

from ssd.tensorflow.

def my_function(array1, array2):
return array1 + array2, array1 - array2, array1 * array2, np.dot(array1, array2)

def debug_value(array,name):
with open(name+'.txt','w') as f:
f.write(str(array))
return array

if name == 'main':
array1 = np.array([[1, 2], [3, 4]])
array2 = np.array([[5, 6], [7, 8]])

a1 = tf.placeholder(dtype=tf.float32, shape=[2, 2], name='array1')
a2 = tf.placeholder(dtype=tf.float32, shape=[2, 2], name='array2')
b1 = a1 * 2

b1 = tf.py_func(debug_value,[b1,'b1'],[tf.float32])
y1, y2, y3, y4 = tf.py_func(my_function, [b1, a2], [tf.float32, tf.float32, tf.float32, tf.float32])
    
with tf.Session() as sess:
    tf.global_variables_initializer().run()
    _y1, _y2, _y3, _y4 = sess.run([y1, y2, y3, y4], feed_dict={a1: array1, a2: array2})
    print(_y1)
    print('*' * 8)
    print(_y2)
    print('*' * 8)
    print(_y3)
    print('*' * 8)
    print(_y4)

from ssd.tensorflow.

I use this way to debug the value.

from ssd.tensorflow.