I have a image dataset which have the following structure:
money_photo/
100/
50/
10/
1/
Each directory have inside 240 photos with the corresponding banknote value(100, 50, 10 and 1).
I'm splitting train and val datasets with keras.preprocessing.image_dataset_from_directory like in the following lines:
train_ds = tf.keras.preprocessing.image_dataset_from_directory(
data_dir,
validation_split=0.2,
subset="training",
seed=123,
image_size=(img_height, img_width),
batch_size=batch_size)
Found 960 files belonging to 4 classes.
Using 768 files for training.
val_ds = tf.keras.preprocessing.image_dataset_from_directory(
data_dir,
validation_split=0.2,
subset="validation",
seed=123,
image_size=(img_height, img_width),
batch_size=batch_size)
Found 960 files belonging to 4 classes.
Using 192 files for validation.
Every image is scalled to 180x180 pixels and its normalised (0..255 pixel values have corresponding values between 0<=value<=1)
Model is defined below:
num_classes = 4
model = tf.keras.Sequential([
layers.experimental.preprocessing.Rescaling(1./255),
layers.Conv2D(32, 3, activation='relu'),
layers.MaxPooling2D(),
layers.Conv2D(32, 3, activation='relu'),
layers.MaxPooling2D(),
layers.Conv2D(32, 3, activation='relu'),
layers.MaxPooling2D(),
layers.Flatten(),
layers.Dense(128, activation='relu'),
layers.Dense(num_classes),
layers.Activation('softmax')
])
After training I have the follwing results:
Epoch 3/3
24/24 [==============================] - 10s 425ms/step - loss: 0.3214 - accuracy: 0.8866 - val_loss: 0.2449 - val_accuracy: 0.9115
The way that I'm using the model to predict:
import tensorflow as tf
from PIL import Image
import numpy as np
from skimage import transform
def load(filename):
np_image = Image.open(filename)
np_image = np.array(np_image).astype('float32')/255
np_image = transform.resize(np_image, (180, 180, 3))
np_image = np.expand_dims(np_image, axis=0)
return np_image
image = load('abd.jpg')
prediction = model.predict(image)
print(class_names[np.argmax(prediction)])
Why I'm getting always the same predicted value?
Your model has a rescaling layer built into it so you should not rescale your input image. Just change
np_image = np.array(np_image).astype('float32')/255
to
np_image = np.array(np_image).astype('float32')
Related
Hello i need to build an ANN using binary_alpha_digits from tensorflow but i am unable to pass in the train data inside as it requires 'flatten_input' but I am passing in ['image','label'] dictionary. How do i solve this problem? Appreciate any help on this problem thanks.
from matplotlib import pyplot as plt
import tensorflow as tf
from tensorflow.keras import layers
train_ds, test_ds = tfds.load('BinaryAlphaDigits',
split=['train[:60%]', 'train[60%:]'])
model = tf.keras.Sequential()
model.add(layers.Flatten(input_shape=(28, 28)))
model.add(layers.Dense(10, activation=tf.nn.relu))
model.add(layers.Dense(10, activation=tf.nn.relu))
model.add(layers.Dense(10, activation=tf.nn.softmax))
model.compile(optimizer= tf.optimizers.Adam(),
loss='sparse_categorical_crossentropy',
metrics=['accuracy'])
epochs = 10
model.fit(train_ds, epochs=epochs)
as you feed images into model, so the input shape must have defined in shape (Height, Width, Channel) which refers to image dimensions and color mode and the second one is that you should preprocess dataset before fitting model on it.
Even notice the output layers units for multi-class classification is not set correctly for this dataset, while there are more than 10 labels, based on dataset it contains 39 labels and so the last layer units would be set to 39.
Here i would implement code which work correctly for you with preprocessing function for images and labels, And even notice the images of the dataset are in shape (20, 16, 1) so you could resize images to set it into (28, 28, 1) or just fed model with the images in their size.
After preprocessing, images are grouped by creating batches or mini-batches, and even shuffle training set to avoid high variance on testing set, so the operations below will be have done cause of that
from matplotlib import pyplot as plt
import tensorflow as tf
from tensorflow.keras import layers
import tensorflow_datasets as tfds
train_ds, test_ds = tfds.load('BinaryAlphaDigits', split=['train[:60%]', 'train[60%:]'])
def preprocess(data):
image = data['image']
image = tf.image.resize(image, (28, 28))
label = data['label']
return image, label
train_ds = train_ds.map(preprocess)
train_ds = train_ds.shuffle(1024)
train_ds = train_ds.batch(batch_size = 32)
test_ds = test_ds.map(preprocess)
test_ds = test_ds.batch(batch_size = 32)
model = tf.keras.Sequential()
model.add(layers.Flatten(input_shape=(28, 28, 1)))
model.add(layers.Dense(10, activation=tf.nn.relu))
model.add(layers.Dense(10, activation=tf.nn.relu))
model.add(layers.Dense(39, activation=tf.nn.softmax))
model.compile(optimizer= tf.optimizers.Adam(), loss='sparse_categorical_crossentropy', metrics=['accuracy'])
epochs = 10
model.fit(train_ds, epochs=epochs)
tfds.load by default gives a dictionary with image and label as the keys.
train_ds, test_ds = tfds.load('BinaryAlphaDigits',
split=['train[:60%]', 'train[60%:]'])
train_ds = train_ds.shuffle(1024).batch(4)
for x in train_ds.take(1):
print(type(x))
print(x['image'].shape, x['label'])
>>>
<class 'dict'>
(4, 20, 16, 1) tf.Tensor([ 6 32 6 12], shape=(4,), dtype=int64)
There is a setting called as_supervised that gives it as a proper dataset. Check docs here
If you use that setting and use proper input and output sizes, your model works
train_ds, test_ds = tfds.load('BinaryAlphaDigits',
split=['train[:60%]', 'train[60%:]'],as_supervised=True)
train_ds = train_ds.shuffle(1024).batch(4)
for x in train_ds.take(1):
print(type(x))
print(x[0].shape, x[1])
>>>
<class 'tuple'>
(4, 20, 16, 1) tf.Tensor([13 13 22 31], shape=(4,), dtype=int64)
model = tf.keras.Sequential()
model.add(layers.Flatten(input_shape=(20, 16,1)))
model.add(layers.Dense(10, activation=tf.nn.relu))
model.add(layers.Dense(10, activation=tf.nn.relu))
model.add(layers.Dense(36, activation=tf.nn.softmax))
model.compile(optimizer= tf.optimizers.Adam(),
loss='sparse_categorical_crossentropy',
metrics=['accuracy'])
epochs = 10
model.fit(train_ds, epochs=epochs)
>>>
Epoch 1/10
211/211 [==============================] - 1s 3ms/step - loss: 3.5428 - accuracy: 0.0629
Epoch 2/10
211/211 [==============================] - 0s 2ms/step - loss: 3.2828 - accuracy: 0.1105
I'm trying to work with a image classification model for gravity waves detection.
So I want to check if there is something I could do to lower validation loss %, or more importantly, increase validation accuracy %.
The dataset is about a total of 460 images, split into
300 images that belong to 2 classes
60 images belonging to 2 classes
100 images belonging to 2 classes
For context, this is the code for pre processing:
batch_size = 32
Data Augmentation:
train_datagen = ImageDataGenerator(
rescale=1./255,
shear_range=0.2,
horizontal_flip=True,
)
test_datagen = ImageDataGenerator(
rescale=1./255)
The generator that reads images to generate batches of augmented image data
train_generator = train_datagen.flow_from_directory(
'./train', target directory
target_size=(256, 256), images resized to 150x150
batch_size=batch_size,
# batch_size=40,
class_mode='binary')
validation_generator = train_datagen.flow_from_directory(
'./validation',
target_size=(256, 256),
batch_size=batch_size,
# batch_size=20,
class_mode='binary')
test_generator = test_datagen.flow_from_directory(
'./test',
target_size=(256, 256),
# batch_size=batch_size,
batch_size=batch_size,
#class_mode=None,
class_mode= None,
shuffle=False)
And this is the model used:
from tensorflow.keras.applications.inception_v3 import InceptionV3
import tensorflow as tf
from keras import regularizers
base_model = InceptionV3(input_shape = (256,256,3), include_top = False, weights = 'imagenet')
x = layers.Flatten()(base_model.output)
x = layers.Dense(1024, activation='relu')(x)
x = layers.Dropout(0.2)(x)
x = layers.Dense(1, activation='sigmoid')(x)
model = Model(base_model.input, x)
model.compile(optimizer = tf.keras.optimizers.SGD(learning_rate=0.001), loss = 'binary_crossentropy', metrics = ['accuracy'])
fitness = model.fit(
train_generator,
steps_per_epoch= 120,
epochs = 100,
validation_data=validation_generator,
validation_steps= 64)
So far the accuracy and loss % have been around:
Average training accuracy: 0.9237500047683715
Average training loss: 0.17309745135484264
Average validation accuracy: 0.6489999979734421
Average validation loss: 0.9121886402368545
The predicitons have been around:
validation predictions:
(24, 36)
test predictions:
(45, 55)
And the confusion matrix:
Confusion Matrix:
array([[12, 18],
[12, 18]])
I've been trying to train this CNN Model, It's a Tensorflow tutorial and I just changed the dataset ( I used fruit 360 dataset) without altering the core of the code. When it finishes training the accuracy stays constant at 0.8565 it doesn't change and when I try and test some images it almost always wrong.
What am I doing wrong?
Code output after executing
Here's the code I used
[enter image description here][1]import matplotlib.pyplot as plt
import numpy as np
import os
import PIL
import tensorflow as tf
import tarfile
from tensorflow import keras
from tensorflow.keras import layers
from tensorflow.keras.models import Sequential
from tensorflow.keras import datasets, layers, models
from tensorflow import keras
import pathlib
dataset_url = "https://file.io/z5JM3sYAWXv4"
data_dir = tf.keras.utils.get_file(origin=dataset_url,
fname='tomatos',
untar=True,
extract=True)
data_dir = pathlib.Path(data_dir)
print(data_dir)
file_count = sum(len(files) for _, _, files in os.walk(r'tomatos'))
print(file_count)
batch_size = 32
img_height = 180
img_width = 180
train_ds = tf.keras.utils.image_dataset_from_directory(
data_dir,
validation_split=0.2,
subset="training",
seed=123,
image_size=(img_height, img_width),
batch_size=batch_size)
val_ds = tf.keras.utils.image_dataset_from_directory(
data_dir,
validation_split=0.2,
subset="validation",
seed=123,
image_size=(img_height, img_width),
batch_size=batch_size)
class_names = train_ds.class_names
print(class_names)
AUTOTUNE = tf.data.AUTOTUNE
train_ds = train_ds.cache().shuffle(1000).prefetch(buffer_size=AUTOTUNE)
val_ds = val_ds.cache().prefetch(buffer_size=AUTOTUNE)
num_classes = len(class_names)
model = Sequential([
layers.Rescaling(1./255, input_shape=(img_height, img_width, 3)),
layers.Conv2D(16, 3, padding='same', activation='relu'),
layers.MaxPooling2D(),
layers.Conv2D(32, 3, padding='same', activation='relu'),
layers.MaxPooling2D(),
layers.Conv2D(64, 3, padding='same', activation='relu'),
layers.MaxPooling2D(),
layers.Flatten(),
layers.Dense(128, activation='relu'),
layers.Dense(num_classes)
])
model.compile(optimizer='adam',
loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
metrics=['accuracy'])
model.summary()
epochs=2
history = model.fit(
train_ds,
validation_data=val_ds,
epochs=epochs
)
data_augmentation = keras.Sequential(
[
layers.RandomFlip("horizontal",
input_shape=(img_height,
img_width,
3)),
layers.RandomRotation(0.1),
layers.RandomZoom(0.1),
]
)
model = Sequential([
data_augmentation,
layers.Rescaling(1./255),
layers.Conv2D(16, 3, padding='same', activation='relu'),
layers.MaxPooling2D(),
layers.Conv2D(32, 3, padding='same', activation='relu'),
layers.MaxPooling2D(),
layers.Conv2D(64, 3, padding='same', activation='relu'),
layers.MaxPooling2D(),
layers.Dropout(0.2),
layers.Flatten(),
layers.Dense(128, activation='relu'),
layers.Dense(num_classes)
])
model.compile(optimizer='adam',
loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
metrics=['accuracy'])
model.summary()
epochs = 4
history = model.fit(
train_ds,
validation_data=val_ds,
epochs=epochs
)
sunflower_url = "https://puffycarrot.com/wp-content/uploads/2017/04/Green-tomatoes.jpg"
sunflower_path = tf.keras.utils.get_file('tomato2', origin=sunflower_url)
img = tf.keras.utils.load_img(
sunflower_path, target_size=(img_height, img_width)
)
img_array = tf.keras.utils.img_to_array(img)
img_array = tf.expand_dims(img_array, 0) # Create a batch
predictions = model.predict(img_array)
score = tf.nn.softmax(predictions[0])
print(
"This image most likely belongs to {} with a {:.2f} percent confidence."
.format(class_names[np.argmax(score)], 100 * np.max(score))
)
#Yaman Tarawneh, I tried replicating your above mentioned code in Google colab (using TF 2.8) and in Pycharm (using TF 2.7) and did not find the error.
Please check the output image for Pycharm :
and got the same output in Google colab :
Total params: 3,988,898
Trainable params: 3,988,898
Non-trainable params: 0
_________________________________________________________________
Epoch 1/4
78/78 [==============================] - 8s 41ms/step - loss: 0.0309 - accuracy: 0.9835 - val_loss: 5.6374e-07 - val_accuracy: 1.0000
Epoch 2/4
78/78 [==============================] - 2s 25ms/step - loss: 5.7533e-07 - accuracy: 1.0000 - val_loss: 2.7360e-07 - val_accuracy: 1.0000
Epoch 3/4
78/78 [==============================] - 2s 25ms/step - loss: 3.0400e-07 - accuracy: 1.0000 - val_loss: 1.3978e-07 - val_accuracy: 1.0000
Epoch 4/4
78/78 [==============================] - 2s 25ms/step - loss: 1.7403e-07 - accuracy: 1.0000 - val_loss: 7.2102e-08 - val_accuracy: 1.0000
This image most likely belongs to Tomato not Ripened with a 100.00 percent confidence.
For further analysis if the issue still persists, Please let us know which Python and Tensorflow version are you using.
I am trying to make a simple autoencoder model for Image reconstruction along with MSNIT dataset.
Now if I run this model, it presents me with accuracy.
'60000/60000 [==============================] - 5s 83us/sample - loss: 0.0373 - accuracy: 0.2034 - val_loss: 0.0368 - val_accuracy: 0.217
'.
but I am not sure how its calculated given that the prediction results itself are an image.
I dug deep till function "sparse_categorical_accuracy" but was not able to reach any conclusion about the formula for accuracy.
latent_dim = 64
class Autoencoder(Model):
def __init__(self, latent_dim):
super(Autoencoder, self).__init__()
self.latent_dim = latent_dim
self.encoder = tf.keras.Sequential([
layers.Flatten(),
layers.Dense(latent_dim, activation='relu'),
])
self.decoder = tf.keras.Sequential([
layers.Dense(784, activation='sigmoid'),
layers.Reshape((28, 28))
])
def call(self, x):
encoded = self.encoder(x)
decoded = self.decoder(encoded)
return decoded
autoencoder = Autoencoder(latent_dim)
autoencoder.compile(optimizer='adam', loss=losses.MeanSquaredError(),
metrics=['accuracy'])
autoencoder.fit(x_train, x_train,
epochs=10,
shuffle=True,
validation_data=(x_test, x_test))
I made an image classifier using Tensorflow, Keras with the implementation of a CNN architecture, the model works pretty fine (at least for the images that I have tested on it ) and it has reached an accuracy of 78.87%, the only thing that I m facing is that I want to make the accuracy no less than 85%.
Please Note:
Dataset: 2 folders: [Train Folder===> 80 folders each has 110 images, Validation folder===> 80 folders each has 22 images] size of the images [240-260]x[40-60]
Below is the code I used to create, save and test my model:
from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.layers import Conv2D, MaxPooling2D
from keras.layers import Activation, Dropout, Flatten, Dense
from keras import backend as K
# dimensions of our images.
img_width, img_height = 251, 54
#img_width, img_height = 150, 33
train_data_dir = 'C:/Users/ADEM/Desktop/msi_youssef/PFE/test/numbers/data/train'
validation_data_dir = 'C:/Users/ADEM/Desktop/msi_youssef/PFE/test/numbers/data/valid'
nb_train_samples = 8800 #10435
nb_validation_samples = 1763 #2051
epochs = 30 #20 # how much time you want to train your model on the data
batch_size = 32 #16
if K.image_data_format() == 'channels_first':
input_shape = (3, img_width, img_height)
else:
input_shape = (img_width, img_height, 3)
model = Sequential()
model.add(Conv2D(32, (3, 3), input_shape=input_shape))
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(64))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(80)) #1
model.add(Activation('softmax')) #sigmoid
model.compile(loss='sparse_categorical_crossentropy',optimizer='rmsprop',metrics=['accuracy'])#categorical_crossentropy #binary_crossentropy
# this is the augmentation configuration we will use for training
train_datagen = ImageDataGenerator(
rescale=1. / 255,
shear_range=0.1,
zoom_range=0.05,
horizontal_flip=False)
# this is the augmentation configuration we will use for testing:
# only rescaling
test_datagen = ImageDataGenerator(rescale=1. / 255)
train_generator = train_datagen.flow_from_directory(
train_data_dir,
target_size=(img_width, img_height),
batch_size=batch_size,
class_mode='binary')
validation_generator = test_datagen.flow_from_directory(
validation_data_dir,
target_size=(img_width, img_height),
batch_size=batch_size,
class_mode='binary')
model.fit_generator(
train_generator,
steps_per_epoch=nb_train_samples // batch_size,
epochs=epochs,
validation_data=validation_generator,
validation_steps=nb_validation_samples // batch_size)
model.save('testX_2.h5') #first_try
last epoche resulat
Epoch 30/30
275/275 [==============================] - 38s 137ms/step - loss: 0.9406 - acc: 0.7562 - val_loss: 0.1268 - val_acc: 0.9688
how I tested my model:
from keras.models import load_model
from keras.preprocessing import image
import matplotlib.pyplot as plt
import numpy as np
import os
result = {"0":"0", "1":"0.25", "2":"0.5", "3":"0.75", "4":"1", "5":"1.25", "6":"1.5", "7":"1.75",
"47":"2", "48":"2.25", "49":"2.5", "50":"2.75", "52":"3","53":"3.25", "54":"3.5", "55":"3.75", "56":"4", "57":"4.25", "58":"4.5",
"59":"4.75","60":"5", "61":"5.25", "62":"5.5", "63":"5.75", "64":"6", "65":"6.25","66":"6.5", "67":"6.75", "68":"7", "69":"7.25",
"70":"7.5", "71":"7.75", "72":"8", "73":"8.25", "74":"8.5", "75":"8.75", "76":"9", "77":"9.25", "78":"9.5", "79":"9.75", "8":"10",
"9":"10.25", "10":"10.5", "11":"10.75", "12":"11", "13":"11.25", "14":"11.5", "15":"11.75", "16":"12","17":"12.25", "18":"12.5",
"19":"12.75", "20":"13", "21":"13.25", "22":"13.5", "23":"13.75","24":"14", "25":"14.25", "26":"14.5", "27":"14.75", "28":"15",
"29":"15.25", "30":"15.5", "31":"15.75", "32":"16", "33":"16.25", "34":"16.5", "35":"16.75", "36":"17", "37":"17.25", "38":"17.5",
"39":"17.75", "40":"18", "41":"18.25", "42":"18.5", "43":"18.75", "44":"19", "45":"19.25", "46":"19.5", "51":"20"}
def load_image(img_path, show=False):
img = image.load_img(img_path, target_size=(251, 54))
img_tensor = image.img_to_array(img) # (height, width, channels)
img_tensor = np.expand_dims(img_tensor, axis=0) # (1, height, width, channels), add a dimension because the model expects this shape: (batch_size, height, width, channels)
img_tensor /= 255. # imshow expects values in the range [0, 1]
if show:
plt.imshow(img_tensor[0])
plt.axis('off')
plt.show()
return img_tensor
if __name__ == "__main__":
# load model
model = load_model('C:/Users/ADEM/Desktop/msi_youssef/PFE/other_shit/testX_2.h5')
# image path
img_path = 'C:/Users/ADEM/Desktop/msi_youssef/PFE/dataset/5.75/a.png'
# load a single image
new_image = load_image(img_path)
# check prediction
#pred = model.predict(new_image)
pred = model.predict_classes(new_image)
#print(pred[0])
print(result[str(pred[0])])
Taking all the information about dataset and considering your CNN model already has around 80% accuracy you can start with training the model for a higher number of epochs (typically > 100 epochs). That should give the required boost to your model.
If that alone does not work you can implement:
Transformation/augmentation:
perform transformation/augmentation on the images before feeding into the model.
Tweak Model:
make changes to model layers and do hyperparameter tuning.
You can follow this article to learn more.