TensorFlow：在我自己的图像上训练

Question

I am new to TensorFlow. I am looking for the help on the image recognition where I can train my own image dataset.

Is there any example for training the new dataset?

Answer 1

If you are interested in how to input your own data in TensorFlow, you can look at this tutorial .
I've also written a guide with best practices for CS230 at Stanford here .

---

New answer (with tf.data ) and with labels

With the introduction of tf.data in r1.4 , we can create a batch of images without placeholders and without queues. The steps are the following:

1. Create a list containing the filenames of the images and a corresponding list of labels
2. Create a tf.data.Dataset reading these filenames and labels
3. Preprocess the data
4. Create an iterator from the tf.data.Dataset which will yield the next batch

The code is:

# step 1
filenames = tf.constant(['im_01.jpg', 'im_02.jpg', 'im_03.jpg', 'im_04.jpg'])
labels = tf.constant([0, 1, 0, 1])

# step 2: create a dataset returning slices of `filenames`
dataset = tf.data.Dataset.from_tensor_slices((filenames, labels))

# step 3: parse every image in the dataset using `map`
def _parse_function(filename, label):
    image_string = tf.read_file(filename)
    image_decoded = tf.image.decode_jpeg(image_string, channels=3)
    image = tf.cast(image_decoded, tf.float32)
    return image, label

dataset = dataset.map(_parse_function)
dataset = dataset.batch(2)

# step 4: create iterator and final input tensor
iterator = dataset.make_one_shot_iterator()
images, labels = iterator.get_next()

Now we can run directly sess.run([images, labels]) without feeding any data through placeholders.

---

Old answer (with TensorFlow queues)

To sum it up you have multiple steps:

1. Create a list of filenames (ex: the paths to your images)
2. Create a TensorFlow filename queue
3. Read and decode each image, resize them to a fixed size (necessary for batching)
4. Output a batch of these images

---

The simplest code would be:

# step 1
filenames = ['im_01.jpg', 'im_02.jpg', 'im_03.jpg', 'im_04.jpg']

# step 2
filename_queue = tf.train.string_input_producer(filenames)

# step 3: read, decode and resize images
reader = tf.WholeFileReader()
filename, content = reader.read(filename_queue)
image = tf.image.decode_jpeg(content, channels=3)
image = tf.cast(image, tf.float32)
resized_image = tf.image.resize_images(image, [224, 224])

# step 4: Batching
image_batch = tf.train.batch([resized_image], batch_size=8)

Answer 2

Based on @olivier-moindrot's answer, but for Tensorflow 2.0+:

# step 1
filenames = tf.constant(['im_01.jpg', 'im_02.jpg', 'im_03.jpg', 'im_04.jpg'])
labels = tf.constant([0, 1, 0, 1])

# step 2: create a dataset returning slices of `filenames`
dataset = tf.data.Dataset.from_tensor_slices((filenames, labels))

def im_file_to_tensor(file, label):
    def _im_file_to_tensor(file, label):
        path = f"../foo/bar/{file.numpy().decode()}"
        im = tf.image.decode_jpeg(tf.io.read_file(path), channels=3)
        im = tf.cast(image_decoded, tf.float32) / 255.0
        return im, label
    return tf.py_function(_im_file_to_tensor, 
                          inp=(file, label), 
                          Tout=(tf.float32, tf.uint8))

dataset = dataset.map(im_file_to_tensor)

If you are hitting an issue similar to:

ValueError: Cannot take the length of Shape with unknown rank

when passing tf.data.Dataset tensors to model.fit, then take a look at https://github.com/tensorflow/tensorflow/issues/24520 . A fix for the code snippet above would be:

def im_file_to_tensor(file, label):
    def _im_file_to_tensor(file, label):
        path = f"../foo/bar/{file.numpy().decode()}"
        im = tf.image.decode_jpeg(tf.io.read_file(path), channels=3)
        im = tf.cast(image_decoded, tf.float32) / 255.0
        return im, label

    file, label = tf.py_function(_im_file_to_tensor, 
                                 inp=(file, label), 
                                 Tout=(tf.float32, tf.uint8))
    file.set_shape([192, 192, 3])
    label.set_shape([])
    return (file, label)

Answer 3

2.0 Compatible Answer using Tensorflow Hub : Tensorflow Hub is a Provision/Product Offered by Tensorflow , which comprises the Models developed by Google, for Text and Image Datasets.

It saves Thousands of Hours of Training Time and Computational Effort , as it reuses the Existing Pre-Trained Model.

If we have an Image Dataset, we can take the Existing Pre-Trained Models from TF Hub and can adopt it to our Dataset.

Code for Re-Training our Image Dataset using the Pre-Trained Model, MobileNet, is shown below:

import itertools
import os

import matplotlib.pylab as plt
import numpy as np

import tensorflow as tf
import tensorflow_hub as hub

module_selection = ("mobilenet_v2_100_224", 224) #@param ["(\"mobilenet_v2_100_224\", 224)", "(\"inception_v3\", 299)"] {type:"raw", allow-input: true}
handle_base, pixels = module_selection
MODULE_HANDLE ="https://tfhub.dev/google/imagenet/{}/feature_vector/4".format(handle_base)
IMAGE_SIZE = (pixels, pixels)
print("Using {} with input size {}".format(MODULE_HANDLE, IMAGE_SIZE))

BATCH_SIZE = 32 #@param {type:"integer"}

#Here we need to Pass our Dataset

data_dir = tf.keras.utils.get_file(
    'flower_photos',
    'https://storage.googleapis.com/download.tensorflow.org/example_images/flower_photos.tgz',
    untar=True)

model = tf.keras.Sequential([
    hub.KerasLayer(MODULE_HANDLE, trainable=do_fine_tuning),
    tf.keras.layers.Dropout(rate=0.2),
    tf.keras.layers.Dense(train_generator.num_classes, activation='softmax',
                          kernel_regularizer=tf.keras.regularizers.l2(0.0001))
])
model.build((None,)+IMAGE_SIZE+(3,))
model.summary()

Complete Code for Image Retraining Tutorial can be found in this Github Link .

More information about Tensorflow Hub can be found in this TF Blog .

The Pre-Trained Modules related to Images can be found in this TF Hub Link .

All the Pre-Trained Modules, related to Images, Text, Videos, etc.. can be found in this TF HUB Modules Link .

Finally, this is the Basic Page for Tensorflow Hub .

Answer 4

If your dataset consists of subfolders, you can use ImageDataGenerator it has flow_from_directory it helps to load data from a directory,

train_batches = ImageDataGenerator().flow_from_directory(
    directory=train_path, target_size=(img_height,img_weight), batch_size=32 ,color_mode="grayscale")

The structure of the folder hierarchy can be as follows,

train 
    -- cat
    -- dog
    -- moneky