Brtdku

I'm trying to take data from a csv with a list of files and a list of labels, and convert it to being one-hot labeled for a categorical classification using tf.keras. I am using eager mode for the code.

I'm trying to follow the tf.data example from CS230 building a data pipeline.

https://cs230-stanford.github.io/tensorflow-input-data.html

my code is below under the code section.

the csv file that lists the location of all the pictures is located on dropbox here:
https://www.dropbox.com/s/5uo8o1p30g2aeta/Clock.csv?dl=0

When I run the code as shown below I get a

TypeError: Cannot convert a TensorShape to dtype: <dtype: 'float32'>

error.

When I add to line 55 and make line 56 :

one_hot_Hr = tf.one_hot(file.Hr,classes)

one_hot_Hr = tf.to_int32(one_hot_Hr)

I get this error:

InvalidArgumentError: cannot compute Mul as input #0 was expected to be 

a float tensor but is a int32 tensor [Op:Mul] 

name: loss/activation_2_loss/mul/

when I run

iterator.get_next()

the pictures are formated as

<tf.Tensor: id=12462, shape=(32, 300, 300, 3), dtype=float32, numpy=

the labels are formated as:

 <tf.Tensor: id=12463, shape=(32, 13), dtype=float32, numpy=

based on the errors, it seems like it should be a simple formatting issue with the labels, but I'm stumped and neither error brings up much useful information on stack overflow.

Code:

import pandas as pd

import tensorflow as tf

import tensorflow.keras as k

#import cv2

#tf.enable_eager_execution()

#import argparse

#from tensorflow.keras.preprocessing.image import ImageDataGenerator

from tensorflow.keras.layers import Conv2D, MaxPooling2D

from tensorflow.keras.layers import Activation, Dropout, Flatten, Dense







def parse_function(filename, label):

    image_string = tf.read_file(filename)



    # Don't use tf.image.decode_image, or the output shape will be undefined

    image = tf.image.decode_jpeg(image_string, channels=3)



    # This will convert to float values in [0, 1]

    image = tf.image.convert_image_dtype(image, tf.float32)





    image = tf.image.resize_images(image, [300, 300])

    return image, label







def train_preprocess(image, label):

    image = tf.image.random_flip_left_right(image)



    image = tf.image.random_brightness(image, max_delta=32.0 / 255.0)

    image = tf.image.random_saturation(image, lower=0.5, upper=1.5)



    # Make sure the image is still in [0, 1]

    image = tf.clip_by_value(image, 0.0, 1.0)



    return image, label



batch_size = 32

classes = 13



fileLoc = "C:/Users/USAgData/TF/Clock.csv"

file = pd.read_csv(fileLoc)

file['Loc']=''

file.Loc = str(str(file.Location)[9:23] + str(file.Location)[28:46])





one_hot_Hr = tf.one_hot(file.Hr,classes)

#one_hot_Hr = tf.to_int32(one_hot_Hr)







dataset = tf.data.Dataset.from_tensor_slices((file.Loc, one_hot_Hr))

dataset = dataset.shuffle(len(file.Location))

dataset = dataset.map(parse_function, num_parallel_calls=4)

dataset = dataset.map(train_preprocess, num_parallel_calls=4)

dataset = dataset.batch(batch_size)

dataset = dataset.prefetch(1)



#print(dataset.shape) # ==> "(tf.float32, tf.float32)"



iterator = dataset.make_one_shot_iterator()

next_element = iterator.get_next()



#print(next_element)



tf.keras.backend.clear_session()



model_name="Documentation"

model = k.Sequential()

model.add(Conv2D(64, (3, 3), input_shape=(300,300,3))) #Changed shape to include batch

model.add(Activation('relu'))

model.add(MaxPooling2D(pool_size=(2, 2)))



#model.add(Conv2D(32, (3, 3)))

#model.add(Activation('relu'))

#model.add(MaxPooling2D(pool_size=(2, 2)))



#model.add(Conv2D(64, (3, 3)))

#model.add(Activation('relu'))

#model.add(MaxPooling2D(pool_size=(2, 2)))



model.add(Flatten())

model.add(Dense(32))

model.add(Activation('relu'))

model.add(Dropout(0.5))

model.add(Dense(classes))

model.add(Activation('softmax')) #Changed from sigmoid









#changed from categorical cross entropy

model.compile(loss='categorical_crossentropy',

              optimizer=tf.train.RMSPropOptimizer(.0001),

              metrics=['accuracy'])



model.summary()







fitting = model.fit_generator(iterator,epochs =1 ,shuffle=False, steps_per_epoch=14400//batch_size)





#model.evaluate(dataset,steps=30)





import sys

print(sys.version)

tf.__version__

I'm running:
tf: 1.10.0
Python: 3.6.7 |Anaconda custom (64-bit)| (default, Dec 10 2018, 20:35:02) [MSC v.1915 64 bit (AMD64)]

I don't know if this should truly be the solution, but when I switch:

fitting = model.fit_generator(iterator,epochs =1 ,shuffle=False, steps_per_epoch=14400//batch_size)

to

fitting = model.fit(iterator,epochs = 1 , shuffle = False, steps_per_epoch = 14400//batch_size)

The model does start to train. But, then them model runs out of data points because the iterator will not start over again.