No output to log or output directory

[afeltham]

Hello, I'm rather new to all this so forgive me if this is a daft question. However, i just can't get the examples to work with my data. I've basically followed the "Training" section of https://www.tensorflow.org/tutorials/image_retraining and have had some good results from the resulting model. However, i want to visualise them and your library seems perfect for the job!

What am i doing wrong in the code below? I get no errors and 'is_success' is True so it appears to have worked?

import os
import sys
import time
import copy
import h5py
import numpy as np

from tf_cnnvis import *

import tensorflow as tf
from scipy.misc import imread, imresize

t_input = tf.placeholder(np.float32, name='Placeholder') # define the input tensor

graph = tf.Graph()
graph_def = tf.GraphDef()

with open('./path/to/my/graph.pb', "rb") as f:
  graph_def.ParseFromString(f.read())

with graph.as_default():
  tf.import_graph_def(graph_def)

# reading sample image
im = np.expand_dims(imread(os.path.join("./", "FILENAME.JPG")), axis = 0)

tensor_names = [t.name for op in graph.get_operations() for t in op.values()]
print(tensor_names[0])
print(tensor_names[len(tensor_names) - 1])

start = time.time()
# api call

is_success  = activation_visualization(
                                            sess_graph_path=tf.get_default_graph(),
                                            value_feed_dict = {t_input : im}, 
                                            input_tensor=tensor_names[len(tensor_names) - 1],
                                            layers=[ 'r', 'p', 'c'], 
                                            path_outdir="./output",
                                            path_logdir="./log"
                                         )
start = time.time() - start
print("Total Time = %f" % (start))
print(is_success)

The main things i don't seem to understand is the value_feed_dict, the input_tensor and the t_input / im variables.

I'm sure i'm doing something daft but would be trivial for someone in the know to spot what is wrong.

Thank you!

[falaktheoptimist]

You do not need to add an extra placeholder for the input. The one which your network has for taking in the input image would work. In the feed_dict, you need to pass in the input image to the placeholder in your network which takes in the input image, not into the extra one you added (re iterating - there is no need for that extra placeholder).
Hope this helps. Let us know if you need any further help with the debugging.

[afeltham]

HI @falaktheoptimist thanks for the reply... sorry for being basic... but could you put that last paragraph into a code example? As mentioned before... i'm a bit new to all this.... Thanks!

[falaktheoptimist]

There are 3 example notebooks in the repo ( https://github.com/InFoCusp/tf_cnnvis/tree/master/examples ), which I think would help you understand this idea very clearly. Please have a look and if you have any questions there, I would be happy to clarify.

[BhagyeshVikani]

@afeltham Closing this issue for now. Re-open if you are still facing the issue.