Example code doesn't work

[ghost]

Hi. I tried to play with the same code, inception model graph and test image (doberman.png) which you provided in examples section as iPython notebook. But I got an error during making the prediction:

ValueError: Cannot feed value of shape (1, 252, 261, 4) for Tensor 'Placeholder:0', which has shape '(?, 299, 299, 3)'

Do you have any idea how to force example code to work?
Thanks.

# Boilerplate imports.
import tensorflow as tf
import numpy as np
import PIL.Image
from matplotlib import pylab as P
import pickle
import os
from subprocess import call
from tensorflow.contrib.slim.python.slim.nets import inception_v3
import saliency

slim = tf.contrib.slim

if not os.path.exists('models/research/slim'):
  call(["git", "clone", "https://github.com/tensorflow/models/"])
old_cwd = os.getcwd()
os.chdir('models/research/slim')
os.chdir(old_cwd)

# Boilerplate methods.
def ShowImage(im, title='', ax=None):
  if ax is None:
    P.figure()
  P.axis('off')
  im = ((im + 1) * 127.5).astype(np.uint8)
  P.imshow(im)
  P.title(title)

def ShowGrayscaleImage(im, title='', ax=None):
  if ax is None:
    P.figure()
  P.axis('off')

  P.imshow(im, cmap=P.cm.gray, vmin=0, vmax=1)
  P.title(title)

def ShowDivergingImage(grad, title='', percentile=99, ax=None):
  if ax is None:
    fig, ax = P.subplots()
  else:
    fig = ax.figure

  P.axis('off')
  divider = make_axes_locatable(ax)
  cax = divider.append_axes('right', size='5%', pad=0.05)
  im = ax.imshow(grad, cmap=P.cm.coolwarm, vmin=-1, vmax=1)
  fig.colorbar(im, cax=cax, orientation='vertical')
  P.title(title)

def LoadImage(file_path):
  im = PIL.Image.open(file_path)
  im = np.asarray(im)
  return im / 127.5 - 1.0

if not os.path.exists('inception_v3.ckpt'):
  call(["curl", "-O", "http://download.tensorflow.org/models/inception_v3_2016_08_28.tar.gz"])
  call(["tar", "-xvzf", "inception_v3_2016_08_28.tar.gz"])

ckpt_file = './inception_v3.ckpt'

graph = tf.Graph()

with graph.as_default():
  images = tf.placeholder(tf.float32, shape=(None, 299, 299, 3))

  with slim.arg_scope(inception_v3.inception_v3_arg_scope()):
    _, end_points = inception_v3.inception_v3(images, is_training=False, num_classes=1001)

    # Restore the checkpoint
    sess = tf.Session(graph=graph)
    saver = tf.train.Saver()
    saver.restore(sess, ckpt_file)

  # Construct the scalar neuron tensor.
  logits = graph.get_tensor_by_name('InceptionV3/Logits/SpatialSqueeze:0')
  neuron_selector = tf.placeholder(tf.int32)
  y = logits[0][neuron_selector]

  # Construct tensor for predictions.
  prediction = tf.argmax(logits, 1)

  # Load the image
im = LoadImage('./doberman.png')

# Show the image
ShowImage(im)

# Make a prediction.
prediction_class = sess.run(prediction, feed_dict = {images: [im]})[0]

print("Prediction class: " + str(prediction_class))  # Should be a doberman, class idx = 237

[joabim]

What if you replace im = LoadImage('./doberman.png') with

im = PIL.Image.open('./doberman.png')
im = np.expand_dims(im, 0) # instate missing batch dimension
# im.shape == (1, 299, 299, 3)

# optional imshow
plt.imshow(im[0,:,:,:])
plt.show()

[aish-where-ya]

I am using tensorflow 2.x and the example code simple does not work. Anybody else facing the same issue?

[giangnguyen2412]

You can resize your image to (229,229) when testing.

[tolga-b]

We unfortunately haven't had the chance to update this library to TF 2 and there are some internal calls that depend on TF 1 sessions. You should be able to use it with TF 1 still. One way I can imagine generalizing this library is to separate gradient computation code from saliency computation code (pass a gradient function separately) to make the library work with any python model.

[bwedin]

Examples/code overhauled in #49, issue is now obsolete.