Develop Reference

Tensorflow's decode_csv only reading one line

How do I get the decode_csv function to read every line in my CSV?
I'm currently trying to load data from my CSV file onto my GPU. Data loads fine onto the GPU, except... only one line of my 640-line CSV file is actually read. Where do you think I'm going wrong?
import tensorflow as tf
with tf.device('/gpu:0'):
filename_queue = tf.train.string_input_producer(['dataset.csv'])
reader = tf.TextLineReader()
key, value = reader.read(filename_queue)
record_defaults = [['']]*121
all_columns = tf.decode_csv(value, record_defaults=record_defaults)
with tf.Session(config=tf.ConfigProto(allow_soft_placement=True)) as sess:
# Start populating the filename queue.
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(coord=coord)
# Iterate through all the columns
vals = []
for x in range(121):
tmp = all_columns.pop()
myval = tmp.eval(session=sess)
vals.append(myval)
coord.request_stop()
coord.join(threads)
Then if I do...
>>> import numpy as np
>>> vals = np.asarray(vals)
>>> vals.shape
(121,)
I do have 121 columns per each of the 640 rows in my CSV. The values in vals look fine to me, except I'm not actually getting all 640 lines read. I'm guessing it has to do with:
all_columns = tf.decode_csv(value, record_defaults=record_defaults)

Nvm. Figured it out.
Apparently there is a difference between sess.run() and pop() in terms of how we extract row data.
I happen to have 640 lines in my CSV file and 121 columns, hence the:
record_defaults = [['']]*121
and
for x in range(640):
Note that this is mostly hardcoded just for testing purposes. Solution below:
import tensorflow as tf
with tf.device('/gpu:0'):
filename_queue = tf.train.string_input_producer(['../Datasets/CMU_face_images_dataset.csv'])
reader = tf.TextLineReader()
key, value = reader.read(filename_queue)
record_defaults = [['']]*121
all_columns = tf.decode_csv(value, record_defaults=record_defaults)
# TWO NEW LINES
name = all_columns[0]
data = all_columns[1:]
with tf.Session(config=tf.ConfigProto(allow_soft_placement=True)) as sess:
# Start populating the filename queue.
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(coord=coord)
vals = []
names = []
for x in range(640):
# THIS IS THE NEW LINE
_name, _val = sess.run([name, data])
# OLD LINES
# tmp = all_columns.pop()
# myval = tmp.eval(session=sess)
# vals.append(myval)
names.append(_name)
vals.append(_val)
coord.request_stop()
coord.join(threads)

Tensor Flow using old graph instead of new one

I have retrained two different classification models models using retrain.py.
For predicting labels for two images I have created getLabel method from Label_image.py as follows:
def getLabel(localFile, graphKey, labelKey):
image_data_str = tf.gfile.FastGFile(localFile, 'rb').read()
# Loads label file, strips off carriage return
label_lines = [line.rstrip() for line
in tf.gfile.GFile(labelKey)]
# Unpersists graph from file
with tf.gfile.FastGFile(graphKey, 'rb') as f:
graph_def = tf.GraphDef()
graph_def.ParseFromString(f.read())
_ = tf.import_graph_def(graph_def, name='')
sess = tf.Session()
with sess:
# Feed the image_data as input to the graph and get first prediction
softmax_tensor = sess.graph.get_tensor_by_name('final_result:0')
predictions = sess.run(softmax_tensor, {'DecodeJpeg/contents:0': image_data_str})
# Sort to show labels of first prediction in order of confidence
top_k = predictions[0].argsort()[-len(predictions[0]):][::-1]
series = []
count = 1
for node_id in top_k:
human_string = label_lines[node_id]
if count==1:
label = human_string
count+=1
score = predictions[0][node_id]
print('%s (score = %.5f)' % (human_string, score))
series.append({"name": human_string, "data": [score * 100]})
sess.close()
return label, series
And I am calling them as
label,series = predict.getLabel(localFile, 'graph1.pb', 'labels1.txt')
label,series = predict.getLabel(localFile, 'graph2.pb', 'labels2.txt')
But for the second function call it is using the old graph i.e. graph1.pb & it is giving below error since model 1 has more categories than model 2.
human_string = label_lines[node_id]
IndexError: list index out of range
I am not able to understand why is this happening. Can someone tell how to load second graph??

It looks like what is happening is that you are calling the same session for both calls to predict.getFinalLabel. What you should do is define two separate sessions, and initialize each separately (e.g. have predict1.getFinalLabel and predict2.getFinalLabel). If you post more of your code, I can provide more detail and code.

Loading images in tensorflow queue provides random image instead of FIFO

I am trying to load an image with tensorflow, but I need the files to be in order. When I load the image it loads a random image but not in the order I provided through my initial array. However, my understanding is that string_input_producer(file_names) is FIFO. Why are my images random and how do I make it load images in order?
with open("name.json", 'r') as f:
data = json.load(f)
file_names = []
for i, row in enumerate(data):
load_location = row['location']
file_names.append(load_location)
filename_queue = tf.train.string_input_producer(file_names) # list of files to read
count_num_files = tf.size(file_names)
reader=tf.WholeFileReader()
key,value=reader.read(filename_queue)
img = tf.image.decode_png(value)
init = tf.global_variables_initializer()
with tf.Session() as sess:
sess.run(init)
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(coord=coord)
num_files = sess.run(count_num_files)
for i in range(num_files):
# this does not match
location = file_names[i]
# with this image
image_eval=img.eval()
coord.request_stop()
coord.join(threads)

Stupid mistake, string_input_producer shuffle setting defaults to True:
filename_queue = tf.train.string_input_producer(file_names, shuffle=False)

Tensorflow Label_Image for PNG, GIF etc

I was playing around with Tensorflow for image classification. I used the image_retraining/retrain.py to retrain the inception library with new categories and used it to classify images using label_image.py from https://github.com/llSourcell/tensorflow_image_classifier/blob/master/src/label_image.py as below:
import tensorflow as tf
import sys
# change this as you see fit
image_path = sys.argv[1]
# Read in the image_data
image_data = tf.gfile.FastGFile(image_path, 'rb').read()
# Loads label file, strips off carriage return
label_lines = [line.rstrip() for line
in tf.gfile.GFile("/root/tf_files/output_labels.txt")]
# Unpersists graph from file
with tf.gfile.FastGFile("/root/tf_files/output_graph.pb", 'rb') as f:
graph_def = tf.GraphDef()
graph_def.ParseFromString(f.read())
_ = tf.import_graph_def(graph_def, name='')
with tf.Session() as sess:
# Feed the image_data as input to the graph and get first prediction
softmax_tensor = sess.graph.get_tensor_by_name('final_result:0')
#predictions = sess.run(softmax_tensor,{'DecodeJpeg/contents:0': image_data})
predictions = sess.run(softmax_tensor,{'DecodePng/contents:0': image_data})
# Sort to show labels of first prediction in order of confidence
top_k = predictions[0].argsort()[-len(predictions[0]):][::-1]
for node_id in top_k:
human_string = label_lines[node_id]
score = predictions[0][node_id]
print('%s (score = %.5f)' % (human_string, score))
I noticed two issues. When I retrain with new categories, it only trains JPG images. I am a noob in machine learning so not sure whether this is a limitation or is it possible to train other extension images like PNG, GIF?
Another one is when classifying the images the input is again only for JPG. I tried to change DecodeJpeg to DecodePng in label_image.py above but couldn't work. Another way I tried was to convert other formats into JPG before passing them in for classification like:
im = Image.open('/root/Desktop/200_s.gif').convert('RGB')
im.save('/root/Desktop/test.jpg', "JPEG")
image_path1 = '/root/Desktop/test.jpg'
Is there any other way to do this? Does Tensorflow have functions to handle other image formats other than JPG?
I tried the following by feeding in parsed image as compared to JPEG as suggested by #mrry
import tensorflow as tf
import sys
import numpy as np
from PIL import Image
# change this as you see fit
image_path = sys.argv[1]
# Read in the image_data
image_data = tf.gfile.FastGFile(image_path, 'rb').read()
image = Image.open(image_path)
image_array = np.array(image)[:,:,0:3] # Select RGB channels only.
# Loads label file, strips off carriage return
label_lines = [line.rstrip() for line
in tf.gfile.GFile("/root/tf_files/output_labels.txt")]
# Unpersists graph from file
with tf.gfile.FastGFile("/root/tf_files/output_graph.pb", 'rb') as f:
graph_def = tf.GraphDef()
graph_def.ParseFromString(f.read())
_ = tf.import_graph_def(graph_def, name='')
with tf.Session() as sess:
# Feed the image_data as input to the graph and get first prediction
softmax_tensor = sess.graph.get_tensor_by_name('final_result:0')
predictions = sess.run(softmax_tensor,{'DecodeJpeg:0': image_array})
# Sort to show labels of first prediction in order of confidence
top_k = predictions[0].argsort()[-len(predictions[0]):][::-1]
for node_id in top_k:
human_string = label_lines[node_id]
score = predictions[0][node_id]
print('%s (score = %.5f)' % (human_string, score))
It works for JPEG images but when I use PNG or GIF it throws
Traceback (most recent call last):
File "label_image.py", line 17, in <module>
image_array = np.array(image)[:,:,0:3] # Select RGB channels only.
IndexError: too many indices for array

The model can only train on (and evaluate) JPEG images, because the GraphDef that you've saved in /root/tf_files/output_graph.pb only contains a tf.image.decode_jpeg() op, and uses the output of that op for making predictions. There are at least a couple of options for using other image formats:
Feed in parsed images rather than JPEG data. In the current program, you feed in a JPEG-encoded image as a string value for the tensor "DecodeJpeg/contents:0". Instead, you can feed in a 3-D array of decoded image data for the tensor "DecodeJpeg:0" (which represents the output of the tf.image.decode_jpeg() op), and you can use NumPy, PIL, or some other Python library to create this array.
Remap the image input in tf.import_graph_def(). The tf.import_graph_def() function enables you to connect two different graphs together by remapping individual tensor values. For example, you could do something like the following to add a new image-processing op to the existing graph:
image_string_input = tf.placeholder(tf.string)
image_decoded = tf.image.decode_png(image_string_input)
# Unpersists graph from file
with tf.gfile.FastGFile("/root/tf_files/output_graph.pb", 'rb') as f:
graph_def = tf.GraphDef()
graph_def.ParseFromString(f.read())
softmax_tensor, = tf.import_graph_def(
graph_def,
input_map={"DecodeJpeg:0": image_decoded},
return_operations=["final_result:0"])
with tf.Session() as sess:
# Feed the image_data as input to the graph and get first prediction
predictions = sess.run(softmax_tensor, {image_string_input: image_data})
# ...

You should have a look at the tf.image package. It's got good functions to decode / encode JPEGs, GIFs and PNGs.

Following #mrry's suggestion to feed in parsed image, converted the image data into array and convert into RGB as stated below in the code. Now I am able to feed in JPG,PNG and GIF.
import tensorflow as tf
import sys
import numpy as np
from PIL import Image
# change this as you see fit
image_path = sys.argv[1]
# Read in the image_data
image_data = tf.gfile.FastGFile(image_path, 'rb').read()
image = Image.open(image_path)
image_array = image.convert('RGB')
# Loads label file, strips off carriage return
label_lines = [line.rstrip() for line
in tf.gfile.GFile("/root/tf_files/output_labels.txt")]
# Unpersists graph from file
with tf.gfile.FastGFile("/root/tf_files/output_graph.pb", 'rb') as f:
graph_def = tf.GraphDef()
graph_def.ParseFromString(f.read())
_ = tf.import_graph_def(graph_def, name='')
with tf.Session() as sess:
# Feed the image_data as input to the graph and get first prediction
softmax_tensor = sess.graph.get_tensor_by_name('final_result:0')
predictions = sess.run(softmax_tensor,{'DecodeJpeg:0': image_array})
# Sort to show labels of first prediction in order of confidence
top_k = predictions[0].argsort()[-len(predictions[0]):][::-1]
for node_id in top_k:
human_string = label_lines[node_id]
score = predictions[0][node_id]
print('%s (score = %.5f)' % (human_string, score))

tensorflow classify multiple images

I am using the Tensorflow image classification example (https://www.tensorflow.org/versions/r0.9/tutorials/image_recognition/index.html).
How could I classify multiple images at a time?
EDIT: Ideally, I would just pass in one image and a number (nb) as arguments, and then make the input-to-be-classified nb iterations of that image
The file is classify_image.py, and the important portion is:
def run_inference_on_image(image):
"""Runs inference on an image.
Args:
image: Image file name.
Returns:
Nothing
"""
if not tf.gfile.Exists(image):
tf.logging.fatal('File does not exist %s', image)
image_data = tf.gfile.FastGFile(image, 'rb').read()
# Creates graph from saved GraphDef.
create_graph()
with tf.Session() as sess:
# Some useful tensors:
# 'softmax:0': A tensor containing the normalized prediction across
# 1000 labels.
# 'pool_3:0': A tensor containing the next-to-last layer containing 2048
# float description of the image.
# 'DecodeJpeg/contents:0': A tensor containing a string providing JPEG
# encoding of the image.
# Runs the softmax tensor by feeding the image_data as input to the graph.
softmax_tensor = sess.graph.get_tensor_by_name('softmax:0')
predictions = sess.run(softmax_tensor,
{'DecodeJpeg/contents:0': image_data})
predictions = np.squeeze(predictions)
# Creates node ID --> English string lookup.
node_lookup = NodeLookup()
top_k = predictions.argsort()[-FLAGS.num_top_predictions:][::-1]
for node_id in top_k:
human_string = node_lookup.id_to_string(node_id)
score = predictions[node_id]
print('%s (score = %.5f)' % (human_string, score))
def main(_):
maybe_download_and_extract()
image = (FLAGS.image_file if FLAGS.image_file else
os.path.join(FLAGS.model_dir, 'cropped_panda.jpg'))
run_inference_on_image(image)

The code relevant to you would be this section:
def main(_):
maybe_download_and_extract()
image = (FLAGS.image_file if FLAGS.image_file else
os.path.join(FLAGS.model_dir, 'cropped_panda.jpg'))
run_inference_on_image(image)
In order to have predictions for all the png, jpeg or jpg files in a "images" folder, you could do this:
def main(_):
maybe_download_and_extract()
# search for files in 'images' dir
files_dir = os.getcwd() + '/images'
files = os.listdir(files_dir)
# loop over files, print prediction if it is an image
for f in files:
if f.lower().endswith(('.png', '.jpg', '.jpeg')):
image_path = files_dir + '/' + f
print run_inference_on_image(image_path)
This should print out the predictions for all your images in that folder