Home TechnologyCoding Deep Learning: Convolutional Neural Networks

Deep Learning: Convolutional Neural Networks

Deep Learning with Keras and Tensorflow: Predicting cats and dogs

by Ivan
What is TensorFlow? | Opensource.com

In this project I will investigate the basics of Convolutional Neuron Networks (CNN) and aim to predict whether an image is a cat or a dog.

Understanding the problem statement and business case

Web services are often protected with a challenge that’s supposed to be easy for people to solve, but difficult for computers. Such a challenge is often called a CAPTCHA (Completely Automated Public Turing test to tell Computers and Humans Apart) or HIP (Human Interactive Proof). HIPs are used for many purposes, such as to reduce email and blog spam and prevent brute-force attacks on web site passwords. Asirra (Animal Species Image Recognition for Restricting Access) is a HIP that works by asking users to identify photographs of cats and dogs. This task is difficult for computers, but studies have shown that people can accomplish it quickly and accurately. Asirra is unique because of its partnership with Petfinder.com, the world’s largest site devoted to finding homes for homeless pets. They’ve provided Microsoft Research with over three million images of cats and dogs, manually classified by people at thousands of animal shelters across the United States.

These images are used to train a CNN model to make predictions on whether an image is a cat or a dog.

Content

Dataset can be found in Microsoft’s website: https://www.microsoft.com/en-us/download/details.aspx?id=54765

Working with Custom Images

The Data (Please note: the data set is VERY large).


ORIGINAL DATA SOURCE:

The dataset contains four folders:

  • Image Data Folder
    • training set
      • cats
      • dogs
    • test set
      • cats
      • dogs

And a total of 12,501 cat images, and 12,501 dog images.

Note: We will be dealing with real image files. Which means a large part of this process will be learning how to work with and deal with large groups of image files. This is too much data to fit in memory as a numpy array, so we’ll need to feed it into our model in batches.

The sample package created in this post can be found here:

https://github.com/allitnils/Deep_Learning

GITHUB.COM

Visualizing the Data

Let’s take a closer look at the data.In [76]:

import os import pandas as pd import numpy as np import seaborn as sns import matplotlib.pyplot as plt from matplotlib.image import imread 

Ensure your data is unzipped and you’re able to locate it within your computer.In [79]:

my_data_dir = 'dataset' 

In [80]:

my_data_dir = 'dataset' # CONFIRM THAT THIS REPORTS BACK 'test', and 'train' test_path = my_data_dir+'test_set' train_path = my_data_dir+'training_set' 

In [ ]:

print(os.listdir(my_data_dir)) print(os.listdir(test_path)) 

In [ ]:

os.listdir(train_path) 

In [ ]:

os.listdir(train_path+'dogs')[1] 

In [131]:

print(os.listdir(train_path+'dogs')[40]) dog_sample = train_path+'dogs'+'dog.40.jpg' dog_img= imread(dog_sample) plt.imshow(dog_img); print(dog_img.shape) 
dog.1034.jpg (197, 149, 3) 

In [141]:

print(os.listdir(train_path+'cats')[1111]) cat_sample = train_path+'cats'+'cat.1111.jpg' cat_img= imread(cat_sample) plt.imshow(cat_img); print(cat_img.shape) 
cat.2.jpg (375, 499, 3) 

Let’s check how many images there are.

In [111]:

print(len(os.listdir(train_path+'dogs'))) print(len(os.listdir(train_path+'cats'))) print(len(os.listdir(test_path+'dogs'))) print(len(os.listdir(test_path+'cats'))) 
4000 4000 1000 1000 

Let’s find out the average dimensions of these images.In [142]:

cat_img.shape dog_img.shape 

Out[142]:

(375, 499, 3)

And perform some visualisations

In [117]:

print(dog_img.shape) print(cat_img.shape) # Other options: https://stackoverflow.com/questions/1507084/how-to-check-dimensions-of-all-images-in-a-directory-using-python dim1 = [] dim2 = [] dim3 = [] dim4 = [] for image_filename in os.listdir(test_path+'dogs'): img = imread(test_path+'dogs'+''+image_filename) d1,d2,colors = img.shape dim1.append(d1) dim2.append(d2) for image_filename in os.listdir(test_path+'cats'): img = imread(test_path+'cats'+''+image_filename) d3,d4,colors = img.shape dim3.append(d3) dim4.append(d4) 

In [143]:

sns.jointplot(dim1,dim2); 

In [144]:

sns.jointplot(dim3,dim4); 

In [23]:

np.mean(dim1) 

Out[23]:

365.171

In [148]:

print(f'Dog test, x: {np.mean(dim1)}') print(f'Dog test, y: {np.mean(dim2)}') print(f'Cat test, x: {np.mean(dim3)}') print(f'Cat test, y: {np.mean(dim4)}') 
Dog test, x: 365.171 Dog test, y: 396.317 Cat test, x: 356.267 Cat test, y: 413.064 

In [145]:

 
Cat test: 356.267 

Out[145]:

413.064

In [25]:

image_shape = (250,250,3) 

Preparing the Data for the model

There is too much data for us to read all at once in memory. We can use some built in functions in Keras to automatically process the data, generate a flow of batches from a directory, and also manipulate the images.

Image Manipulation

Its usually a good idea to manipulate the images with rotation, resizing, and scaling so the model becomes more robust to different images that our data set doesn’t have. We can use the ImageDataGenerator to do this automatically for us. Check out the documentation for a full list of all the parameters you can use here!In [26]:

from tensorflow.keras.preprocessing.image import ImageDataGenerator 

In [27]:

help(ImageDataGenerator) 
Help on class ImageDataGenerator in module tensorflow.python.keras.preprocessing.image: class ImageDataGenerator(keras_preprocessing.image.image_data_generator.ImageDataGenerator) | ImageDataGenerator(featurewise_center=False, samplewise_center=False, featurewise_std_normalization=False, samplewise_std_normalization=False, zca_whitening=False, zca_epsilon=1e-06, rotation_range=0, width_shift_range=0.0, height_shift_range=0.0, brightness_range=None, shear_range=0.0, zoom_range=0.0, channel_shift_range=0.0, fill_mode='nearest', cval=0.0, horizontal_flip=False, vertical_flip=False, rescale=None, preprocessing_function=None, data_format=None, validation_split=0.0, dtype=None) | | Generate batches of tensor image data with real-time data augmentation. | | The data will be looped over (in batches). | | Arguments: | featurewise_center: Boolean. | Set input mean to 0 over the dataset, feature-wise. | samplewise_center: Boolean. Set each sample mean to 0. | featurewise_std_normalization: Boolean. | Divide inputs by std of the dataset, feature-wise. | samplewise_std_normalization: Boolean. Divide each input by its std. | zca_epsilon: epsilon for ZCA whitening. Default is 1e-6. | zca_whitening: Boolean. Apply ZCA whitening. | rotation_range: Int. Degree range for random rotations. | width_shift_range: Float, 1-D array-like or int | - float: fraction of total width, if < 1, or pixels if >= 1. | - 1-D array-like: random elements from the array. | - int: integer number of pixels from interval | `(-width_shift_range, +width_shift_range)` | - With `width_shift_range=2` possible values | are integers `[-1, 0, +1]`, | same as with `width_shift_range=[-1, 0, +1]`, | while with `width_shift_range=1.0` possible values are floats | in the interval [-1.0, +1.0). | height_shift_range: Float, 1-D array-like or int | - float: fraction of total height, if < 1, or pixels if >= 1. | - 1-D array-like: random elements from the array. | - int: integer number of pixels from interval | `(-height_shift_range, +height_shift_range)` | - With `height_shift_range=2` possible values | are integers `[-1, 0, +1]`, | same as with `height_shift_range=[-1, 0, +1]`, | while with `height_shift_range=1.0` possible values are floats | in the interval [-1.0, +1.0). | brightness_range: Tuple or list of two floats. Range for picking | a brightness shift value from. | shear_range: Float. Shear Intensity | (Shear angle in counter-clockwise direction in degrees) | zoom_range: Float or [lower, upper]. Range for random zoom. | If a float, `[lower, upper] = [1-zoom_range, 1+zoom_range]`. | channel_shift_range: Float. Range for random channel shifts. | fill_mode: One of {"constant", "nearest", "reflect" or "wrap"}. | Default is 'nearest'. | Points outside the boundaries of the input are filled | according to the given mode: | - 'constant': kkkkkkkk|abcd|kkkkkkkk (cval=k) | - 'nearest': aaaaaaaa|abcd|dddddddd | - 'reflect': abcddcba|abcd|dcbaabcd | - 'wrap': abcdabcd|abcd|abcdabcd | cval: Float or Int. | Value used for points outside the boundaries | when `fill_mode = "constant"`. | horizontal_flip: Boolean. Randomly flip inputs horizontally. | vertical_flip: Boolean. Randomly flip inputs vertically. | rescale: rescaling factor. Defaults to None. | If None or 0, no rescaling is applied, | otherwise we multiply the data by the value provided | (after applying all other transformations). | preprocessing_function: function that will be applied on each input. | The function will run after the image is resized and augmented. | The function should take one argument: | one image (Numpy tensor with rank 3), | and should output a Numpy tensor with the same shape. | data_format: Image data format, | either "channels_first" or "channels_last". | "channels_last" mode means that the images should have shape | `(samples, height, width, channels)`, | "channels_first" mode means that the images should have shape | `(samples, channels, height, width)`. | It defaults to the `image_data_format` value found in your | Keras config file at `~/.keras/keras.json`. | If you never set it, then it will be "channels_last". | validation_split: Float. Fraction of images reserved for validation | (strictly between 0 and 1). | dtype: Dtype to use for the generated arrays. | | Examples: | | Example of using `.flow(x, y)`: | | ```python | (x_train, y_train), (x_test, y_test) = cifar10.load_data() | y_train = np_utils.to_categorical(y_train, num_classes) | y_test = np_utils.to_categorical(y_test, num_classes) | datagen = ImageDataGenerator( | featurewise_center=True, | featurewise_std_normalization=True, | rotation_range=20, | width_shift_range=0.2, | height_shift_range=0.2, | horizontal_flip=True) | # compute quantities required for featurewise normalization | # (std, mean, and principal components if ZCA whitening is applied) | datagen.fit(x_train) | # fits the model on batches with real-time data augmentation: | model.fit(datagen.flow(x_train, y_train, batch_size=32), | steps_per_epoch=len(x_train) / 32, epochs=epochs) | # here's a more "manual" example | for e in range(epochs): | print('Epoch', e) | batches = 0 | for x_batch, y_batch in datagen.flow(x_train, y_train, batch_size=32): | model.fit(x_batch, y_batch) | batches += 1 | if batches >= len(x_train) / 32: | # we need to break the loop by hand because | # the generator loops indefinitely | break | ``` | | Example of using `.flow_from_directory(directory)`: | | ```python | train_datagen = ImageDataGenerator( | rescale=1./255, | shear_range=0.2, | zoom_range=0.2, | horizontal_flip=True) | test_datagen = ImageDataGenerator(rescale=1./255) | train_generator = train_datagen.flow_from_directory( | 'data/train', | target_size=(150, 150), | batch_size=32, | class_mode='binary') | validation_generator = test_datagen.flow_from_directory( | 'data/validation', | target_size=(150, 150), | batch_size=32, | class_mode='binary') | model.fit( | train_generator, | steps_per_epoch=2000, | epochs=50, | validation_data=validation_generator, | validation_steps=800) | ``` | | Example of transforming images and masks together. | | ```python | # we create two instances with the same arguments | data_gen_args = dict(featurewise_center=True, | featurewise_std_normalization=True, | rotation_range=90, | width_shift_range=0.1, | height_shift_range=0.1, | zoom_range=0.2) | image_datagen = ImageDataGenerator(**data_gen_args) | mask_datagen = ImageDataGenerator(**data_gen_args) | # Provide the same seed and keyword arguments to the fit and flow methods | seed = 1 | image_datagen.fit(images, augment=True, seed=seed) | mask_datagen.fit(masks, augment=True, seed=seed) | image_generator = image_datagen.flow_from_directory( | 'data/images', | class_mode=None, | seed=seed) | mask_generator = mask_datagen.flow_from_directory( | 'data/masks', | class_mode=None, | seed=seed) | # combine generators into one which yields image and masks | train_generator = zip(image_generator, mask_generator) | model.fit_generator( | train_generator, | steps_per_epoch=2000, | epochs=50) | ``` | | Method resolution order: | ImageDataGenerator | keras_preprocessing.image.image_data_generator.ImageDataGenerator | builtins.object | | Methods defined here: | | __init__(self, featurewise_center=False, samplewise_center=False, featurewise_std_normalization=False, samplewise_std_normalization=False, zca_whitening=False, zca_epsilon=1e-06, rotation_range=0, width_shift_range=0.0, height_shift_range=0.0, brightness_range=None, shear_range=0.0, zoom_range=0.0, channel_shift_range=0.0, fill_mode='nearest', cval=0.0, horizontal_flip=False, vertical_flip=False, rescale=None, preprocessing_function=None, data_format=None, validation_split=0.0, dtype=None) | Initialize self. See help(type(self)) for accurate signature. | | flow(self, x, y=None, batch_size=32, shuffle=True, sample_weight=None, seed=None, save_to_dir=None, , save_format='png', subset=None) | Takes data & label arrays, generates batches of augmented data. | | Arguments: | x: Input data. Numpy array of rank 4 or a tuple. If tuple, the first | element should contain the images and the second element another numpy | array or a list of numpy arrays that gets passed to the output without | any modifications. Can be used to feed the model miscellaneous data | along with the images. In case of grayscale data, the channels axis of | the image array should have value 1, in case of RGB data, it should | have value 3, and in case of RGBA data, it should have value 4. | y: Labels. | batch_size: Int (default: 32). | shuffle: Boolean (default: True). | sample_weight: Sample weights. | seed: Int (default: None). | save_to_dir: None or str (default: None). This allows you to optionally | specify a directory to which to save the augmented pictures being | generated (useful for visualizing what you are doing). | save_prefix: Str (default: `''`). Prefix to use for filenames of saved | pictures (only relevant if `save_to_dir` is set). | save_format: one of "png", "jpeg" | (only relevant if `save_to_dir` is set). Default: "png". | subset: Subset of data (`"training"` or `"validation"`) if | `validation_split` is set in `ImageDataGenerator`. | | Returns: | An `Iterator` yielding tuples of `(x, y)` | where `x` is a numpy array of image data | (in the case of a single image input) or a list | of numpy arrays (in the case with | additional inputs) and `y` is a numpy array | of corresponding labels. If 'sample_weight' is not None, | the yielded tuples are of the form `(x, y, sample_weight)`. | If `y` is None, only the numpy array `x` is returned. | | flow_from_dataframe(self, dataframe, directory=None, x_col='filename', y_col='class', weight_col=None, target_size=(256, 256), color_mode='rgb', classes=None, class_mode='categorical', batch_size=32, shuffle=True, seed=None, save_to_dir=None, , save_format='png', subset=None, interpolation='nearest', validate_filenames=True, **kwargs) | Takes the dataframe and the path to a directory + generates batches. | | The generated batches contain augmented/normalized data. | | **A simple tutorial can be found **[here]( | http://bit.ly/keras_flow_from_dataframe). | | Arguments: | dataframe: Pandas dataframe containing the filepaths relative to | `directory` (or absolute paths if `directory` is None) of the images | in a string column. It should include other column/s | depending on the `class_mode`: - if `class_mode` is `"categorical"` | (default value) it must include the `y_col` column with the | class/es of each image. Values in column can be string/list/tuple | if a single class or list/tuple if multiple classes. - if | `class_mode` is `"binary"` or `"sparse"` it must include the given | `y_col` column with class values as strings. - if `class_mode` is | `"raw"` or `"multi_output"` it should contain the columns | specified in `y_col`. - if `class_mode` is `"input"` or `None` no | extra column is needed. | directory: string, path to the directory to read images from. If `None`, | data in `x_col` column should be absolute paths. | x_col: string, column in `dataframe` that contains the filenames (or | absolute paths if `directory` is `None`). | y_col: string or list, column/s in `dataframe` that has the target data. | weight_col: string, column in `dataframe` that contains the sample | weights. Default: `None`. | target_size: tuple of integers `(height, width)`, default: `(256, 256)`. | The dimensions to which all images found will be resized. | color_mode: one of "grayscale", "rgb", "rgba". Default: "rgb". Whether | the images will be converted to have 1 or 3 color channels. | classes: optional list of classes (e.g. `['dogs', 'cats']`). Default is | None. If not provided, the list of classes will be automatically | inferred from the `y_col`, which will map to the label indices, will | be alphanumeric). The dictionary containing the mapping from class | names to class indices can be obtained via the attribute | `class_indices`. | class_mode: one of "binary", "categorical", "input", "multi_output", | "raw", sparse" or None. Default: "categorical". | Mode for yielding the targets: | - `"binary"`: 1D numpy array of binary labels, | - `"categorical"`: 2D numpy array of one-hot encoded labels. | Supports multi-label output. | - `"input"`: images identical to input images (mainly used to work | with autoencoders), | - `"multi_output"`: list with the values of the different columns, | - `"raw"`: numpy array of values in `y_col` column(s), | - `"sparse"`: 1D numpy array of integer labels, - `None`, no targets | are returned (the generator will only yield batches of image data, | which is useful to use in `model.predict_generator()`). | batch_size: size of the batches of data (default: 32). | shuffle: whether to shuffle the data (default: True) | seed: optional random seed for shuffling and transformations. | save_to_dir: None or str (default: None). This allows you to optionally | specify a directory to which to save the augmented pictures being | generated (useful for visualizing what you are doing). | save_prefix: str. Prefix to use for filenames of saved pictures (only | relevant if `save_to_dir` is set). | save_format: one of "png", "jpeg" | (only relevant if `save_to_dir` is set). Default: "png". | subset: Subset of data (`"training"` or `"validation"`) if | `validation_split` is set in `ImageDataGenerator`. | interpolation: Interpolation method used to resample the image if the | target size is different from that of the loaded image. Supported | methods are `"nearest"`, `"bilinear"`, and `"bicubic"`. If PIL version | 1.1.3 or newer is installed, `"lanczos"` is also supported. If PIL | version 3.4.0 or newer is installed, `"box"` and `"hamming"` are also | supported. By default, `"nearest"` is used. | validate_filenames: Boolean, whether to validate image filenames in | `x_col`. If `True`, invalid images will be ignored. Disabling this | option can lead to speed-up in the execution of this function. | Defaults to `True`. | **kwargs: legacy arguments for raising deprecation warnings. | | Returns: | A `DataFrameIterator` yielding tuples of `(x, y)` | where `x` is a numpy array containing a batch | of images with shape `(batch_size, *target_size, channels)` | and `y` is a numpy array of corresponding labels. | | flow_from_directory(self, directory, target_size=(256, 256), color_mode='rgb', classes=None, class_mode='categorical', batch_size=32, shuffle=True, seed=None, save_to_dir=None, , save_format='png', follow_links=False, subset=None, interpolation='nearest') | Takes the path to a directory & generates batches of augmented data. | | Arguments: | directory: string, path to the target directory. It should contain one | subdirectory per class. Any PNG, JPG, BMP, PPM or TIF images inside | each of the subdirectories directory tree will be included in the | generator. See [this script]( | https://gist.github.com/fchollet/0830affa1f7f19fd47b06d4cf89ed44d) | for more details. | target_size: Tuple of integers `(height, width)`, defaults to `(256, | 256)`. The dimensions to which all images found will be resized. | color_mode: One of "grayscale", "rgb", "rgba". Default: "rgb". Whether | the images will be converted to have 1, 3, or 4 channels. | classes: Optional list of class subdirectories | (e.g. `['dogs', 'cats']`). Default: None. If not provided, the list | of classes will be automatically inferred from the subdirectory | names/structure under `directory`, where each subdirectory will be | treated as a different class (and the order of the classes, which | will map to the label indices, will be alphanumeric). The | dictionary containing the mapping from class names to class | indices can be obtained via the attribute `class_indices`. | class_mode: One of "categorical", "binary", "sparse", | "input", or None. Default: "categorical". | Determines the type of label arrays that are returned: - | "categorical" will be 2D one-hot encoded labels, - "binary" will | be 1D binary labels, "sparse" will be 1D integer labels, - "input" | will be images identical to input images (mainly used to work with | autoencoders). - If None, no labels are returned (the generator | will only yield batches of image data, which is useful to use with | `model.predict_generator()`). Please note that in case of | class_mode None, the data still needs to reside in a subdirectory | of `directory` for it to work correctly. | batch_size: Size of the batches of data (default: 32). | shuffle: Whether to shuffle the data (default: True) If set to False, | sorts the data in alphanumeric order. | seed: Optional random seed for shuffling and transformations. | save_to_dir: None or str (default: None). This allows you to optionally | specify a directory to which to save the augmented pictures being | generated (useful for visualizing what you are doing). | save_prefix: Str. Prefix to use for filenames of saved pictures (only | relevant if `save_to_dir` is set). | save_format: One of "png", "jpeg" | (only relevant if `save_to_dir` is set). Default: "png". | follow_links: Whether to follow symlinks inside | class subdirectories (default: False). | subset: Subset of data (`"training"` or `"validation"`) if | `validation_split` is set in `ImageDataGenerator`. | interpolation: Interpolation method used to resample the image if the | target size is different from that of the loaded image. Supported | methods are `"nearest"`, `"bilinear"`, and `"bicubic"`. If PIL version | 1.1.3 or newer is installed, `"lanczos"` is also supported. If PIL | version 3.4.0 or newer is installed, `"box"` and `"hamming"` are also | supported. By default, `"nearest"` is used. | | Returns: | A `DirectoryIterator` yielding tuples of `(x, y)` | where `x` is a numpy array containing a batch | of images with shape `(batch_size, *target_size, channels)` | and `y` is a numpy array of corresponding labels. | | ---------------------------------------------------------------------- | Methods inherited from keras_preprocessing.image.image_data_generator.ImageDataGenerator: | | apply_transform(self, x, transform_parameters) | Applies a transformation to an image according to given parameters. | | # Arguments | x: 3D tensor, single image. | transform_parameters: Dictionary with string - parameter pairs | describing the transformation. | Currently, the following parameters | from the dictionary are used: | - `'theta'`: Float. Rotation angle in degrees. | - `'tx'`: Float. Shift in the x direction. | - `'ty'`: Float. Shift in the y direction. | - `'shear'`: Float. Shear angle in degrees. | - `'zx'`: Float. Zoom in the x direction. | - `'zy'`: Float. Zoom in the y direction. | - `'flip_horizontal'`: Boolean. Horizontal flip. | - `'flip_vertical'`: Boolean. Vertical flip. | - `'channel_shift_intensity'`: Float. Channel shift intensity. | - `'brightness'`: Float. Brightness shift intensity. | | # Returns | A transformed version of the input (same shape). | | fit(self, x, augment=False, rounds=1, seed=None) | Fits the data generator to some sample data. | | This computes the internal data stats related to the | data-dependent transformations, based on an array of sample data. | | Only required if `featurewise_center` or | `featurewise_std_normalization` or `zca_whitening` are set to True. | | When `rescale` is set to a value, rescaling is applied to | sample data before computing the internal data stats. | | # Arguments | x: Sample data. Should have rank 4. | In case of grayscale data, | the channels axis should have value 1, in case | of RGB data, it should have value 3, and in case | of RGBA data, it should have value 4. | augment: Boolean (default: False). | Whether to fit on randomly augmented samples. | rounds: Int (default: 1). | If using data augmentation (`augment=True`), | this is how many augmentation passes over the data to use. | seed: Int (default: None). Random seed. | | get_random_transform(self, img_shape, seed=None) | Generates random parameters for a transformation. | | # Arguments | seed: Random seed. | img_shape: Tuple of integers. | Shape of the image that is transformed. | | # Returns | A dictionary containing randomly chosen parameters describing the | transformation. | | random_transform(self, x, seed=None) | Applies a random transformation to an image. | | # Arguments | x: 3D tensor, single image. | seed: Random seed. | | # Returns | A randomly transformed version of the input (same shape). | | standardize(self, x) | Applies the normalization configuration in-place to a batch of inputs. | | `x` is changed in-place since the function is mainly used internally | to standardize images and feed them to your network. If a copy of `x` | would be created instead it would have a significant performance cost. | If you want to apply this method without changing the input in-place | you can call the method creating a copy before: | | standardize(np.copy(x)) | | # Arguments | x: Batch of inputs to be normalized. | | # Returns | The inputs, normalized. | | ---------------------------------------------------------------------- | Data descriptors inherited from keras_preprocessing.image.image_data_generator.ImageDataGenerator: | | __dict__ | dictionary for instance variables (if defined) | | __weakref__ | list of weak references to the object (if defined) 

In [149]:

image_gen = ImageDataGenerator(rotation_range=20, # rotate the image 20 degrees
                               width_shift_range=0.10, # Shift the pic width by a max of 5%
                               height_shift_range=0.10, # Shift the pic height by a max of 5%
                               rescale=1/255, # Rescale the image by normalzing it.
                               shear_range=0.1, # Shear means cutting away part of the image (max 10%)
                               zoom_range=0.1, # Zoom in by 10% max
                               horizontal_flip=True, # Allo horizontal flipping
                               fill_mode='nearest' # Fill in missing pixels with the nearest filled value
                              )

In [153]:

plt.imshow(dog_img)

Out[153]:

<matplotlib.image.AxesImage at 0x1a4762c7f40>

In [154]:

plt.imshow(image_gen.random_transform(dog_img))

Out[154]:

<matplotlib.image.AxesImage at 0x1a4763266d0>

In [156]:

plt.imshow(image_gen.random_transform(dog_img))

Out[156]:

<matplotlib.image.AxesImage at 0x1a47b835b50>

In [157]:

plt.imshow(image_gen.random_transform(dog_img))

Out[157]:

<matplotlib.image.AxesImage at 0x1a47b8935e0>

In [158]:

plt.imshow(image_gen.random_transform(dog_img))

Out[158]:

<matplotlib.image.AxesImage at 0x1a47b8e2640>

In [159]:

plt.imshow(image_gen.random_transform(dog_img))

Out[159]:

<matplotlib.image.AxesImage at 0x1a47b941a60>

In [160]:

plt.imshow(image_gen.random_transform(dog_img))

Out[160]:

<matplotlib.image.AxesImage at 0x1a47b99f4c0>

Generating many manipulated images from a directory

In order to use .flow_from_directory, you must organize the images in sub-directories. This is an absolute requirement, otherwise the method won’t work. The directories should only contain images of one class, so one folder per class of images.

Structure Needed:

  • Image Data Folder
    • Class 1
      • 0.jpg
      • 1.jpg
    • Class 2
      • 0.jpg
      • 1.jpg
    • Class n

In [161]:

image_gen.flow_from_directory(train_path)
image_gen.flow_from_directory(test_path)
Found 8000 images belonging to 2 classes.
Found 2000 images belonging to 2 classes.

Out[161]:

<tensorflow.python.keras.preprocessing.image.DirectoryIterator at 0x1a47b90ef70>

Creating the Model

In [34]:

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Activation, Dropout, Flatten, Dense, Conv2D, MaxPooling2D

In [35]:

#https://stats.stackexchange.com/questions/148139/rules-for-selecting-convolutional-neural-network-hyperparameters
model = Sequential()

model.add(Conv2D(filters=32, kernel_size=(3,3),input_shape=image_shape, activation='relu',))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(filters=64, kernel_size=(3,3),input_shape=image_shape, activation='relu',))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(filters=64, kernel_size=(3,3),input_shape=image_shape, activation='relu',))
model.add(MaxPooling2D(pool_size=(2, 2)))


model.add(Flatten())


model.add(Dense(128))
model.add(Activation('swish'))

# Dropouts help reduce overfitting by randomly turning neurons off during training.
# Here we say randomly turn off 50% of neurons.
model.add(Dropout(0.2))

# Last layer, remember its binary so we use sigmoid
model.add(Dense(1))
model.add(Activation('sigmoid'))

model.compile(loss='binary_crossentropy',
              optimizer='adam',
              metrics=['accuracy'])

early_stop = EarlyStopping(monitor='val_loss',patience=5)

In [36]:

model.summary()
Model: "sequential"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv2d (Conv2D)              (None, 248, 248, 32)      896       
_________________________________________________________________
max_pooling2d (MaxPooling2D) (None, 124, 124, 32)      0         
_________________________________________________________________
conv2d_1 (Conv2D)            (None, 122, 122, 64)      18496     
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 61, 61, 64)        0         
_________________________________________________________________
conv2d_2 (Conv2D)            (None, 59, 59, 64)        36928     
_________________________________________________________________
max_pooling2d_2 (MaxPooling2 (None, 29, 29, 64)        0         
_________________________________________________________________
flatten (Flatten)            (None, 53824)             0         
_________________________________________________________________
dense (Dense)                (None, 128)               6889600   
_________________________________________________________________
activation (Activation)      (None, 128)               0         
_________________________________________________________________
dropout (Dropout)            (None, 128)               0         
_________________________________________________________________
dense_1 (Dense)              (None, 1)                 129       
_________________________________________________________________
activation_1 (Activation)    (None, 1)                 0         
=================================================================
Total params: 6,946,049
Trainable params: 6,946,049
Non-trainable params: 0
_________________________________________________________________

Early Stopping

In [37]:

from tensorflow.keras.callbacks import EarlyStopping

In [38]:

early_stop = EarlyStopping(monitor='val_loss',patience=5)

Training the Model

In [39]:

help(image_gen.flow_from_directory)
Help on method flow_from_directory in module tensorflow.python.keras.preprocessing.image:

flow_from_directory(directory, target_size=(256, 256), color_mode='rgb', classes=None, class_mode='categorical', batch_size=32, shuffle=True, seed=None, save_to_dir=None, save_prefix='', save_format='png', follow_links=False, subset=None, interpolation='nearest') method of tensorflow.python.keras.preprocessing.image.ImageDataGenerator instance
    Takes the path to a directory & generates batches of augmented data.
    
    Arguments:
        directory: string, path to the target directory. It should contain one
          subdirectory per class. Any PNG, JPG, BMP, PPM or TIF images inside
          each of the subdirectories directory tree will be included in the
          generator. See [this script](
            https://gist.github.com/fchollet/0830affa1f7f19fd47b06d4cf89ed44d)
              for more details.
        target_size: Tuple of integers `(height, width)`, defaults to `(256,
          256)`. The dimensions to which all images found will be resized.
        color_mode: One of "grayscale", "rgb", "rgba". Default: "rgb". Whether
          the images will be converted to have 1, 3, or 4 channels.
        classes: Optional list of class subdirectories
            (e.g. `['dogs', 'cats']`). Default: None. If not provided, the list
              of classes will be automatically inferred from the subdirectory
              names/structure under `directory`, where each subdirectory will be
              treated as a different class (and the order of the classes, which
              will map to the label indices, will be alphanumeric). The
              dictionary containing the mapping from class names to class
              indices can be obtained via the attribute `class_indices`.
        class_mode: One of "categorical", "binary", "sparse",
            "input", or None. Default: "categorical".
            Determines the type of label arrays that are returned: -
              "categorical" will be 2D one-hot encoded labels, - "binary" will
              be 1D binary labels, "sparse" will be 1D integer labels, - "input"
              will be images identical to input images (mainly used to work with
              autoencoders). - If None, no labels are returned (the generator
              will only yield batches of image data, which is useful to use with
              `model.predict_generator()`). Please note that in case of
              class_mode None, the data still needs to reside in a subdirectory
              of `directory` for it to work correctly.
        batch_size: Size of the batches of data (default: 32).
        shuffle: Whether to shuffle the data (default: True) If set to False,
          sorts the data in alphanumeric order.
        seed: Optional random seed for shuffling and transformations.
        save_to_dir: None or str (default: None). This allows you to optionally
          specify a directory to which to save the augmented pictures being
          generated (useful for visualizing what you are doing).
        save_prefix: Str. Prefix to use for filenames of saved pictures (only
          relevant if `save_to_dir` is set).
        save_format: One of "png", "jpeg"
            (only relevant if `save_to_dir` is set). Default: "png".
        follow_links: Whether to follow symlinks inside
            class subdirectories (default: False).
        subset: Subset of data (`"training"` or `"validation"`) if
          `validation_split` is set in `ImageDataGenerator`.
        interpolation: Interpolation method used to resample the image if the
          target size is different from that of the loaded image. Supported
          methods are `"nearest"`, `"bilinear"`, and `"bicubic"`. If PIL version
          1.1.3 or newer is installed, `"lanczos"` is also supported. If PIL
          version 3.4.0 or newer is installed, `"box"` and `"hamming"` are also
          supported. By default, `"nearest"` is used.
    
    Returns:
        A `DirectoryIterator` yielding tuples of `(x, y)`
            where `x` is a numpy array containing a batch
            of images with shape `(batch_size, *target_size, channels)`
            and `y` is a numpy array of corresponding labels.

In [40]:

batch_size = 32

In [163]:

print('Processing training images')
train_image_gen = image_gen.flow_from_directory(train_path,
                                               target_size=(250,250),
                                                color_mode='rgb',
                                               batch_size=batch_size,
                                               class_mode='binary')
print('Processing testing images')
test_image_gen = image_gen.flow_from_directory(test_path,
                                               target_size=(250,250),
                                               color_mode='rgb',
                                               batch_size=batch_size,
                                               class_mode='binary',shuffle=False)
Processing training images
Found 8000 images belonging to 2 classes.
Processing testing images
Found 2000 images belonging to 2 classes.

In [44]:

train_image_gen.class_indices

Out[44]:

{'cats': 0, 'dogs': 1}

In [45]:

import warnings
warnings.filterwarnings('ignore')

In [165]:

results = model.fit(train_image_gen,epochs=50,
                              validation_data=test_image_gen,
                             callbacks=[early_stop])
  2/250 [..............................] - ETA: 1:41 - loss: 0.4023 - accuracy: 0.8281WARNING:tensorflow:Callbacks method `on_train_batch_end` is slow compared to the batch time (batch time: 0.1609s vs `on_train_batch_end` time: 0.6566s). Check your callbacks.
250/250 [==============================] - 237s 949ms/step - loss: 0.2625 - accuracy: 0.8880 - val_loss: 0.3633 - val_accuracy: 0.8530

In [192]:

from tensorflow.keras.models import load_model

In [194]:

model = load_model('cat_dog_detector.h5')

Evaluating the Model

In [ ]:

losses = pd.DataFrame(model.history.history)

In [ ]:

losses = pd.DataFrame(model.history.history)
losses[['loss','val_loss']].plot();

In [197]:

model.metrics_names

Out[197]:

['loss', 'accuracy']

In [198]:

model.evaluate_generator(test_image_gen)

Out[198]:

[0.3479582965373993, 0.859000027179718]

In [52]:

from tensorflow.keras.preprocessing import image

In [53]:

# https://datascience.stackexchange.com/questions/13894/how-to-get-predictions-with-predict-generator-on-streaming-test-data-in-keras
pred_probabilities = model.predict(test_image_gen)
WARNING:tensorflow:From <ipython-input-53-f14b427af105>:2: Model.predict_generator (from tensorflow.python.keras.engine.training) is deprecated and will be removed in a future version.
Instructions for updating:
Please use Model.predict, which supports generators.

In [54]:

pred_probabilities

Out[54]:

array([[0.99614197],
       [0.16947518],
       [0.01064979],
       ...,
       [0.00906021],
       [0.63585776],
       [0.9997241 ]], dtype=float32)

In [55]:

test_image_gen.classes

Out[55]:

array([0, 0, 0, ..., 1, 1, 1])

In [56]:

predictions = pred_probabilities > 0.5

In [57]:

# Numpy can treat this as True/False for us
predictions

Out[57]:

array([[ True],
       [False],
       [False],
       ...,
       [False],
       [ True],
       [ True]])

In [58]:

from sklearn.metrics import classification_report,confusion_matrix

In [59]:

print(classification_report(test_image_gen.classes,predictions))
              precision    recall  f1-score   support

           0       0.87      0.83      0.85      1000
           1       0.84      0.88      0.86      1000

    accuracy                           0.85      2000
   macro avg       0.86      0.85      0.85      2000
weighted avg       0.86      0.85      0.85      2000

In [166]:

confusion_matrix(test_image_gen.classes,predictions)

Out[166]:

array([[831, 169],
       [121, 879]], dtype=int64)

Predicting on an Image

In [206]:

# Your file path will likely be different!
dog_cell = 'datasetsingle_predictioncat_or_dog_1.jpg'
cat_cell = 'datasetsingle_predictioncat_or_dog_2.jpg'
my_image_a = image.load_img(dog_cell,target_size=image_shape)
my_image_b = image.load_img(cat_cell,target_size=image_shape)

In [207]:

my_image_a = image.load_img(dog_cell,target_size=image_shape)
my_image_b = image.load_img(cat_cell,target_size=image_shape)

In [208]:

my_image_a

Out[208]:

In [209]:

my_image_b

Out[209]:

In [ ]:

train_image_gen.class_indices

In [ ]:

print(type(my_image_a))
my_image_a = image.img_to_array(my_image_a)
print(type(my_image_a))
print(my_image_a.shape)
my_image_a = np.expand_dims(my_image_a, axis=0)
print(my_image_a.shape)
model.predict(my_image_a)

In [ ]:

print(type(my_image_b))
my_image_b = image.img_to_array(my_image_b)
print(type(my_image_b))
print(my_image_b.shape)
my_image_b = np.expand_dims(my_image_b, axis=0)
print(my_image_b.shape)
model.predict(my_image_b)

Done!

You may also like

2 comments

Rupert Jones February 7, 2022 - 16:37

What does the in [] and out [] mean??

Reply
Ivan Ocampo February 8, 2022 - 07:56

hi Rupert, thank you for your comment. the in [] and out [] comments are merely leftovers from my copy/paste from Jupyter Notebook. You may ignore these when re-creating the project!

Reply

Leave a Reply

[script_16]