Creating a Slim classifier using pretrained ResNet V2 model

Question

I am trying to create an image classifier that utilizes the pre-trained ResNet V2 model provided in the slim documentation.

Here is the code so far:

import tensorflow as tf
slim = tf.contrib.slim
from PIL import Image
from inception_resnet_v2 import *
import numpy as np

checkpoint_file = 'inception_resnet_v2_2016_08_30.ckpt'
sample_images = ['carrot.jpg']

input_tensor = tf.placeholder(tf.float32, shape=(None,299,299,3), name='input_image')
scaled_input_tensor = tf.scalar_mul((1.0/255), input_tensor)
scaled_input_tensor = tf.subtract(scaled_input_tensor, 0.5)
scaled_input_tensor = tf.multiply(scaled_input_tensor, 2.0)


variables_to_restore = slim.get_model_variables()
print(variables_to_restore)

init_fn = slim.assign_from_checkpoint_fn(
        checkpoint_file,
        slim.get_model_variables('InceptionResnetV2'))

sess = tf.Session()
init_fn(sess)
arg_scope = inception_resnet_v2_arg_scope()
with slim.arg_scope(arg_scope):
  logits, end_points = inception_resnet_v2(scaled_input_tensor, is_training=False)

for image in sample_images:
  im = Image.open(image).resize((299,299))
  im = np.array(im)
  im = im.reshape(-1,299,299,3)
  predict_values, logit_values = sess.run([end_points['Predictions'], logits], feed_dict={input_tensor: im})
  print (np.max(predict_values), np.max(logit_values))
  print (np.argmax(predict_values), np.argmax(logit_values))

The problem is I keep getting this error:

Traceback (most recent call last):
  File "./classify.py", line 21, in <module>
    slim.get_model_variables('InceptionResnetV2'))
  File "/home/ubuntu/tensorflow/local/lib/python2.7/site-packages/tensorflow/contrib/framework/python/ops/variables.py", line 584, in assign_from_checkpoint_fn
    saver = tf_saver.Saver(var_list, reshape=reshape_variables)
  File "/home/ubuntu/tensorflow/local/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 1040, in __init__
    self.build()
  File "/home/ubuntu/tensorflow/local/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 1061, in build
    raise ValueError("No variables to save")
ValueError: No variables to save

So it seems TF/Slim is unable to find any variables and this is made clear when I call:

variables_to_restore = slim.get_model_variables()
    print(variables_to_restore)

As it outputs an empty array.

How can I go about using the pre-trained model?

score 1 · Answer 1 · answered May 24 '17 at 18:28

This happens because you haven't constructed the model in your graph yet to have any variables starting with the name "InceptionResnetV2" to be captured and restored by the saver.

I believe you should put the model construction before using slim.get_variables_to_restore().

For instance:

with slim.arg_scope(arg_scope):
  logits, end_points = inception_resnet_v2(scaled_input_tensor, is_training=False)

variables_to_restore = slim.get_model_variables()

This way, the Tensor variables will be constructed and you should see variables_to_restore is no longer empty.

score 0 · Answer 2 · answered Nov 10 '17 at 02:03

You need to manually add the model variables.

Try this

with slim.arg_scope(arg_scope):
  logits, end_points = inception_resnet_v2(scaled_input_tensor, is_training=False)

# Add model variables
for var in tf.global_variables(scope='inception_resnet_v2'):
  slim.add_model_variable(var)

Creating a Slim classifier using pretrained ResNet V2 model

2 Answers2