Related
The following code gives a log ending with
Epoch 19/20
1/1 [==============================] - 0s 473ms/step - loss: 1.4018 - accuracy: 0.8750 - val_loss: 1.8656 - val_accuracy: 0.8900
Epoch 20/20
1/1 [==============================] - 0s 444ms/step - loss: 0.5904 - accuracy: 0.8750 - val_loss: 2.1255 - val_accuracy: 0.8700
get_dataset: validation
Found 1000 files belonging to 2 classes.
Using 100 files for validation.
4/4 [==============================] - 1s 81ms/step
eval acc: 0.81
My question is:
Why is the val_accuracy after the last epoch (0.87) different from the eval acc (0.81) after the fit?
In my code, I try to use the same dataset for the validation of each epoch during fit and the additional validation afterwards.
[Update 1, 2022-07-19:
Obviously, the two accuracy calculations don't really use the same data. How can I debug which data is actually used?
[Update 3, 2022-07-20: I have followed the data into TensorFlow. The last thing I see is that in Model.evaluate (during fit) and Model.predict the x.filenames are equal. I did not manage to debug much further, because soon in quick_execute the __inference_test_function_248219 resp. the __inference_predict_function_231438 are evaluated outside Python, and the arguments are tensors with dtype=resource, whose contents I cannot see.]
I have deliberately removed my class balancing code to keep my example small. I know that this makes the accuracies less useful, but I don't care about that for now.
Note that get_dataset('validation') is only called once at the beginning of the fit, not at each epoch.
I have now also set max_queue_size=0, use_multiprocessing=False, workers=0 (as seen here, found via this related SO question about TensorFlow 1), but this did not make the accuracies equal.
]
Code:
import tensorflow as tf
from sklearn.metrics import accuracy_score
from tensorflow.keras.models import Model
from tensorflow.keras.layers import Dense, Flatten
from tensorflow.keras.preprocessing import image_dataset_from_directory
inputs = tf.keras.Input(shape=(224, 224, 3))
base_model = tf.keras.applications.ResNet50(weights='imagenet', include_top=False)
base_output = base_model(inputs)
base_model.trainable = False
out = Flatten(name='flat')(base_output)
out = Dense(1, activation='sigmoid')(out)
model = Model(inputs=inputs, outputs=out)
model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])
def get_dataset(subset):
print('get_dataset:', subset)
return image_dataset_from_directory(
'data-nodup-1000',
labels="inferred",
label_mode='binary',
color_mode="rgb",
image_size=(224, 224),
shuffle=True,
seed=1,
validation_split=0.1,
subset=subset,
crop_to_aspect_ratio=False,
)
model.fit(
get_dataset('training'),
steps_per_epoch=1,
epochs=20,
validation_data=get_dataset('validation'),
max_queue_size=0,
use_multiprocessing=False,
workers=0,
)
val_dataset = get_dataset('validation')
true_class = tf.concat([y for x, y in val_dataset], axis=0)
pred = model.predict(val_dataset)
pred_class = pred >= .5
print('eval acc:', accuracy_score(true_class, pred_class))
[Update 2, 2022-07-19:
I can also reproduce the behavior with the deprecated ImageDataGenerator, using
from tensorflow.keras.applications.resnet50 import preprocess_input
from keras_preprocessing.image import ImageDataGenerator
datagen = ImageDataGenerator(
preprocessing_function=preprocess_input,
validation_split=0.1,
)
def get_dataset(subset):
print('get_dataset:', subset)
return datagen.flow_from_directory(
'data-nodup-1000',
class_mode='binary',
target_size=(224, 224),
shuffle=True,
seed=1,
subset=subset,
)
and
true_class = val_dataset.labels
]
[Update 4, 2022-07-21: Note that deactivating shuffling of validation data by setting shuffle=(subset == 'training') makes the two validation accuracies equal. This is not a workaround, however, because the validation set then consists only of class 1, since flow_from_directory doesn't do stratification.
]
My environment:
I am using all up-to-date libraries, like tensorflow 2.9.1 and sklearn 1.1.1 (via pip-compile -U).
The folder data-nodup-1000 contains one subfolder with 113 files of class 0, and one subfolder with 887 files of class 1.
I have now found out that in TensorFlow 2.9.1 model.predict uses the second iteration of the dataset, which is shuffled differently than the first iteration!
It even uses the second iteration when I directly call model.predict(get_dataset('validation'))!
Therefore, the entries of true_class and pred do not match.
Switching to TensorFlow 2.10.0-rc3 and its tf.keras.utils.split_dataset makes the accuracies equal.
Here's the updated code:
import tensorflow as tf
from sklearn.metrics import accuracy_score
from tensorflow.keras.models import Model
from tensorflow.keras.layers import Dense, Flatten
from tensorflow.keras.preprocessing import image_dataset_from_directory
inputs = tf.keras.Input(shape=(224, 224, 3))
base_model = tf.keras.applications.ResNet50(weights='imagenet', include_top=False)
base_output = base_model(inputs)
base_model.trainable = False
out = Flatten(name='flat')(base_output)
out = Dense(1, activation='sigmoid')(out)
model = Model(inputs=inputs, outputs=out)
model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])
dataset = image_dataset_from_directory(
'data-synthetic',
labels="inferred",
label_mode='binary',
color_mode="rgb",
image_size=(224, 224),
shuffle=True,
seed=1,
crop_to_aspect_ratio=False,
)
train_dataset, val_dataset = tf.keras.utils.split_dataset(dataset, right_size=0.1)
model.fit(
train_dataset,
steps_per_epoch=1,
epochs=20,
validation_data=val_dataset,
max_queue_size=0,
use_multiprocessing=False,
workers=0,
)
true_class = tf.concat([y for x, y in val_dataset], axis=0)
pred = model.predict(val_dataset)
pred_class = pred >= .5
print('eval acc:', accuracy_score(true_class, pred_class))
which correctly yields:
Epoch 19/20
1/1 [==============================] - 0s 438ms/step - loss: 0.4426 - accuracy: 0.9062 - val_loss: 0.4658 - val_accuracy: 0.8800
Epoch 20/20
1/1 [==============================] - 0s 444ms/step - loss: 2.1619 - accuracy: 0.8438 - val_loss: 0.5886 - val_accuracy: 0.8900
4/4 [==============================] - 1s 87ms/step
eval acc: 0.89
there are a few points about your data which causes this:
First, your data is highly imbalanced (8 to 1 label ratio) which makes the model rather overfit and the CV estimate inaccurate.
Second, in the get_dataset function, the shuffle is set to True so every time you call the get_dataset(), it shuffles your data, and because (1) Your validation set is very small and (2) your train/val split is not stratified over your labels, the validation metrics would vary a lot due to this shuffling.
Suggestions to solve this:
call the get_dataset() only once for train and val dataset before fitting the model and save them as variables. and if there is no sequential order in your data, maybe set shuffle=False.
(optional) If possible make your dataset more balanced by techniques such as data augmentation, over-/under-sampling, etc.
def get_dataset(subset):
return image_dataset_from_directory(
'data-nodup-1000',
labels="inferred",
label_mode='binary',
color_mode="rgb",
image_size=(224, 224),
shuffle=False,
seed=0,
validation_split=0.1,
subset=subset,
crop_to_aspect_ratio=False,
)
train_dataset = get_dataset('training')
val_dataset = get_dataset('validation')
model.fit(
train_dataset,
steps_per_epoch=1,
epochs=20,
validation_data=val_dataset,
)
true_class = tf.concat([y for x, y in val_dataset], axis=0)
pred = model.predict(val_dataset)
pred_class = pred >= .5
print('eval acc:', accuracy_score(true_class, pred_class))
At my job Interview yesterday, I was asked to build a neural network using TesnorFlow in python to classify images from the flowers images dataset.
But even though it should've worked theoretically, for some reason I couldn't increase the accuracy above 20s%.
Python Version: 3.8.13
TensorFlow Versioin: 2.4.1
The data preprocessing methods from the interviewer were given as follows:
# create datase
IMG_SIZE = 160
BATCH_SIZE = 32
AUTOTUNE = tf.data.experimental.AUTOTUNE
def _parse_data(x,y):
image = tf.io.read_file(x)
image = tf.image.decode_jpeg(image, channels=3)
image = tf.cast(image, dtype=tf.float32)
image = tf.math.l2_normalize(image)
image = tf.image.resize(image, (IMG_SIZE, IMG_SIZE))
return image,y
def _input_fn(x,y):
ds = tf.data.Dataset.from_tensor_slices((x,y))
ds = ds.map(_parse_data)
ds = ds.shuffle(buffer_size=data_size)
ds = ds.repeat()
ds = ds.batch(BATCH_SIZE)
ds = ds.prefetch(buffer_size=AUTOTUNE)
return ds
train_ds = _input_fn(x_train, y_train)
validation_ds = _input_fn(x_valid, y_valid)
With both training and validation datasets being
<PrefetchDataset shapes: ((None, 160, 160, 3), (None,)), types:
(tf.float32, tf.int32)>
With the network being as follows:
from tensorflow.keras import datasets, layers, models
model_seq = models.Sequential()
model_seq.add(layers.experimental.preprocessing.RandomFlip("horizontal",input_shape=(IMG_SIZE,IMG_SIZE,3)))
model_seq.add(layers.experimental.preprocessing.RandomRotation(0.2))
model_seq.add(layers.experimental.preprocessing.Rescaling(1./255))
model_seq.add(layers.Conv2D(16, 3, padding='same', activation='relu'))
model_seq.add(layers.MaxPooling2D())
model_seq.add(layers.Conv2D(32, 3, padding='same', activation='relu'))
model_seq.add(layers.MaxPooling2D())
model_seq.add(layers.Conv2D(64, 3, padding='same', activation='relu'))
model_seq.add(layers.MaxPooling2D())
model_seq.add(layers.Dropout(0.2))
model_seq.add(layers.Flatten())
model_seq.add(layers.Dense(128, activation='relu'))
model_seq.add(layers.Dense(len(label_names), activation='softmax'))
model_seq.summary()
The output layer being the only thing that isn't allowed to be change.
model_seq.add(layers.Dense(len(label_names), activation='softmax'))
(Please note I was for some reason asked to use model_seq.add(), and even though it could be triggering for some of you, please ignore it this once :) )
For compiling the model, I used the following:
model_seq.compile(optimizer="Adam",
loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
metrics=['accuracy'])
And for fitting the model:
history = model_seq.fit(train_ds,epochs=20,
validation_data = validation_ds,
steps_per_epoch=100,validation_steps=100)
The things I've tried:
Using different Augmentation methods (or removing the whole section
from the network).
Changing the Batch and Image sizes.
Using Dropout layers.
Using early stopping as follows:
callback = tf.keras.callbacks.EarlyStopping(
monitor='val_loss',
min_delta=0, patience=3, verbose=0,
mode='auto',baseline=None,
restore_best_weights=True)
history = model_seq.fit(train_ds,epochs=20,
validation_data = validation_ds,
steps_per_epoch=100,validation_steps=100,
callbacks = [callback])
Yet despite all of the above, I couldn't get any results. Since I couldn't find out what I did wrong exactly, I'm hoping someone here could tell me, so I could learn from this experience.
(Please take into consideration that I wasn't allowed to change the preprocessing functions, with the parameters IMG_SIZE and BATCH_SIZE being the only exception).
“TLDR: If you want to use their preprocessing part and don't change anything go to First Approach. If you want to augment images, Go to Second Approach and use ImageDataGenerator”.
First Approach
As you say: I had to use the preprocessing functions and don't change this and because I don't access your data, I use cifar10 dataset and use your preprocessing part. (only line of reading from file changed).
Because you shouldn't change IMG_SIZE=160 in the preprocessing part, I add this layer : tf.keras.layers.Lambda(lambda image: tf.image.resize(image, (32, 32)))) to the network because working with large images causes a crash.
You don't need a very large network, first check with a small network then step by step add parameters then add layers.
We can get a better result like the below: (On cifar10 with your network I get 10% accuracy like you.)
import tensorflow as tf
(X_train, y_train), (X_test, y_test) = tf.keras.datasets.cifar10.load_data()
# create datase
IMG_SIZE = 160
BATCH_SIZE = 32
data_size = 32
AUTOTUNE = tf.data.experimental.AUTOTUNE
def _parse_data(x,y):
# image = tf.io.read_file(x) <- because don't read from path
image = x
# image = tf.image.decode_jpeg(image, channels=3) <- because don't read from path and don't have jpeg
image = tf.cast(image, dtype=tf.float32)
image = tf.math.l2_normalize(image)
image = tf.image.resize(image, (IMG_SIZE, IMG_SIZE))
return image,y
def _input_fn(x,y):
ds = tf.data.Dataset.from_tensor_slices((x,y))
ds = ds.map(_parse_data)
ds = ds.shuffle(buffer_size=data_size)
ds = ds.repeat()
ds = ds.batch(BATCH_SIZE)
ds = ds.prefetch(buffer_size=AUTOTUNE)
return ds
train_ds = _input_fn(X_train, y_train)
validation_ds = _input_fn(X_test, y_test)
model = tf.keras.Sequential([
tf.keras.Input(shape=(160, 160, 3)),
tf.keras.layers.Lambda(lambda image: tf.image.resize(image, (32, 32))),
tf.keras.layers.Conv2D(filters=32,kernel_size=(3,3),activation='relu'),
tf.keras.layers.MaxPooling2D(2,2),
tf.keras.layers.Flatten(),
tf.keras.layers.Dense(50,activation='relu'),
tf.keras.layers.Dense(10,activation='softmax')
])
model.compile(optimizer="Adam",
loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False),
metrics=['accuracy'])
history = model.fit(train_ds,epochs=4,
validation_data = validation_ds,
steps_per_epoch=100,validation_steps=100)
Output:
Epoch 1/4
100/100 [==============================] - 8s 38ms/step - loss: 2.2445 - accuracy: 0.1375 - val_loss: 2.1406 - val_accuracy: 0.2138
Epoch 2/4
100/100 [==============================] - 3s 33ms/step - loss: 2.0552 - accuracy: 0.2688 - val_loss: 1.9764 - val_accuracy: 0.3250
Epoch 3/4
100/100 [==============================] - 4s 38ms/step - loss: 1.9468 - accuracy: 0.3022 - val_loss: 1.9014 - val_accuracy: 0.3200
Epoch 4/4
100/100 [==============================] - 4s 36ms/step - loss: 1.8936 - accuracy: 0.3341 - val_loss: 1.8883 - val_accuracy: 0.3419
Second Approach: Augment images with ImageDataGenerator:
import tensorflow as tf
flowers = tf.keras.utils.get_file(
'flower_photos',
'https://storage.googleapis.com/download.tensorflow.org/example_images/flower_photos.tgz',
untar=True)
data_gen = tf.keras.preprocessing.image.ImageDataGenerator(
rescale=1./255,
rotation_range = 10, # Degree range for random rotations.
horizontal_flip = True, # Randomly flip inputs horizontally.
vertical_flip = True, # Randomly flip inputs vertically.
)
imgs_dataset = data_gen.flow_from_directory(flowers, class_mode='categorical',
target_size=(160, 160), batch_size=32,
shuffle=True)
model = tf.keras.Sequential([
tf.keras.layers.Conv2D(filters=32,kernel_size=(3,3),input_shape=(160, 160, 3),activation='relu'),
tf.keras.layers.MaxPooling2D(2,2),
tf.keras.layers.Flatten(),
tf.keras.layers.Dense(50,activation='relu'),
tf.keras.layers.Dense(5,activation='softmax')
])
model.compile(optimizer='adam', loss='categorical_crossentropy',metrics=['accuracy'])
model.fit(imgs_dataset,epochs=5)
Output:
Found 3670 images belonging to 5 classes.
Epoch 1/5
115/115 [==============================] - 39s 311ms/step - loss: 1.7904 - accuracy: 0.4161
Epoch 2/5
115/115 [==============================] - 27s 236ms/step - loss: 1.0878 - accuracy: 0.5605
Epoch 3/5
115/115 [==============================] - 28s 244ms/step - loss: 1.0252 - accuracy: 0.6005
Epoch 4/5
115/115 [==============================] - 27s 233ms/step - loss: 0.9735 - accuracy: 0.6196
Epoch 5/5
115/115 [==============================] - 29s 248ms/step - loss: 0.9313 - accuracy: 0.6455
I'm trying to use the Cifar-10 dataset to practice my CNN skills.
If I do this it's ok:
(train_images, train_labels), (test_images, test_labels) = datasets.cifar10.load_data()
But I was trying to use tfds.load() and I don't understand how to do it.
With this I download it,
train_ds, test_ds = tfds.load('cifar10', split=['train','test'])
Now I tried this but is not working,
assert isinstance(train_ds, tf.data.Dataset)
assert isinstance(test_ds, tf.data.Dataset)
(train_images, train_labels) = tuple(zip(*train_ds))
(test_images, test_labels) = tuple(zip(*test_ds))
Can somebody show me the way to achieve it?
thank you!
You can do this as follows.
import tensorflow as tf
import tensorflow_datasets as tfds
train_ds, test_ds = tfds.load('cifar10', split=['train','test'], as_supervised=True)
These train_ds and test_ds are tf.data.Dataset objects and so you can use map, batch, and similar functions to each of those.
def normalize_resize(image, label):
image = tf.cast(image, tf.float32)
image = tf.divide(image, 255)
image = tf.image.resize(image, (28, 28))
return image, label
def augment(image, label):
image = tf.image.random_flip_left_right(image)
image = tf.image.random_saturation(image, 0.7, 1.3)
image = tf.image.random_contrast(image, 0.8, 1.2)
image = tf.image.random_brightness(image, 0.1)
return image, label
train = train_ds.map(normalize_resize).cache().map(augment).shuffle(100).batch(64).repeat()
test = test_ds.map(normalize_resize).cache().batch(64)
Now, we can pass train and test directly to model.fit.
model = tf.keras.models.Sequential(
[
tf.keras.layers.Flatten(input_shape=(28, 28, 3)),
tf.keras.layers.Dense(128, activation="relu"),
tf.keras.layers.Dropout(0.2),
tf.keras.layers.Dense(10, activation="softmax"),
]
)
model.compile(
optimizer="adam", loss="sparse_categorical_crossentropy", metrics=["accuracy"]
)
model.fit(
train,
epochs=5,
steps_per_epoch=60000 // 64,
validation_data=test, verbose=2
)
Epoch 1/5
17s 17ms/step - loss: 2.0848 - accuracy: 0.2318 - val_loss: 1.8175 - val_accuracy: 0.3411
Epoch 2/5
11s 12ms/step - loss: 1.8827 - accuracy: 0.3144 - val_loss: 1.7800 - val_accuracy: 0.3595
Epoch 3/5
11s 12ms/step - loss: 1.8383 - accuracy: 0.3272 - val_loss: 1.7152 - val_accuracy: 0.3904
Epoch 4/5
11s 11ms/step - loss: 1.8129 - accuracy: 0.3397 - val_loss: 1.6908 - val_accuracy: 0.4060
Epoch 5/5
11s 11ms/step - loss: 1.8022 - accuracy: 0.3461 - val_loss: 1.6801 - val_accuracy: 0.4081
You can also extract them like this:
train_ds, test_ds = tfds.load('cifar10', split=['train','test'],
as_supervised = True,
batch_size = -1)
To work with as_numpy() method, you need pass as_supervised and batch_size as shown. If you pass as_supervised = True then the dataset will have tuple structure that (inputs, labels) otherwise it will be a dictionary.
With them you simply call:
train_images, train_labels = tfds.as_numpy(train_ds)
Or another way is to iterate over it to obtain classes(assuming batch_size is not passed).
With as_supervised = False:
train_images, train_labels = [],[]
for images_labels in train_ds:
train_images.append(images_labels['image'])
train_labels.append(images_labels['label'])
With as_supervised = True:
for images, labels in train_ds:
train_images.append(images)
train_labels.append(labels)
I'm trying to do image classification with dicom images that have balanced classes using the pre-trained InceptionV3 model.
def convertDCM(PathDCM) :
data = []
for dirName, subdir, files in os.walk(PathDCM):
for filename in sorted(files):
ds = pydicom.dcmread(PathDCM +'/' + filename)
im = fromarray(ds.pixel_array)
im = keras.preprocessing.image.img_to_array(im)
im = cv2.resize(im,(299,299))
data.append(im)
return data
PathDCM = '/home/Desktop/FULL_BALANCED_COLOURED/'
data = convertDCM(PathDCM)
#scale the raw pixel intensities to the range [0,1]
data = np.array(data, dtype="float")/255.0
labels = np.array(labels,dtype ="int")
#splitting data into training and testing
#test_size is percentage to split into test/train data
(trainX, testX, trainY, testY) = train_test_split(
data,labels,
test_size=0.2,
random_state=42)
img_width, img_height = 299, 299 #InceptionV3 size
train_samples = 300
validation_samples = 50
epochs = 25
batch_size = 15
base_model = keras.applications.InceptionV3(
weights ='imagenet',
include_top=False,
input_shape = (img_width,img_height,3))
model_top = keras.models.Sequential()
model_top.add(keras.layers.GlobalAveragePooling2D(input_shape=base_model.output_shape[1:], data_format=None)),
model_top.add(keras.layers.Dense(300,activation='relu'))
model_top.add(keras.layers.Dropout(0.5))
model_top.add(keras.layers.Dense(1, activation = 'sigmoid'))
model = keras.models.Model(inputs = base_model.input, outputs = model_top(base_model.output))
#Compiling model
model.compile(optimizer = keras.optimizers.Adam(
lr=0.0001),
loss='binary_crossentropy',
metrics=['accuracy'])
#Image Processing and Augmentation
train_datagen = keras.preprocessing.image.ImageDataGenerator(
rescale = 1./255,
zoom_range = 0.1,
width_shift_range = 0.2,
height_shift_range = 0.2,
horizontal_flip = True,
fill_mode ='nearest')
val_datagen = keras.preprocessing.image.ImageDataGenerator()
train_generator = train_datagen.flow(
trainX,
trainY,
batch_size=batch_size,
shuffle=True)
validation_generator = train_datagen.flow(
testX,
testY,
batch_size=batch_size,
shuffle=True)
When I train the model, I always get a constant validation accuracy of 0.3889 with the validation loss fluctuating.
#Training the model
history = model.fit_generator(
train_generator,
steps_per_epoch = train_samples//batch_size,
epochs = epochs,
validation_data = validation_generator,
validation_steps = validation_samples//batch_size)
Epoch 1/25
20/20 [==============================]20/20
[==============================] - 195s 49s/step - loss: 0.7677 - acc: 0.4020 - val_loss: 0.7784 - val_acc: 0.3889
Epoch 2/25
20/20 [==============================]20/20
[==============================] - 187s 47s/step - loss: 0.7016 - acc: 0.4848 - val_loss: 0.7531 - val_acc: 0.3889
Epoch 3/25
20/20 [==============================]20/20
[==============================] - 191s 48s/step - loss: 0.6566 - acc: 0.6304 - val_loss: 0.7492 - val_acc: 0.3889
Epoch 4/25
20/20 [==============================]20/20
[==============================] - 175s 44s/step - loss: 0.6533 - acc: 0.5529 - val_loss: 0.7575 - val_acc: 0.3889
predictions= model.predict(testX)
print(predictions)
Predicting the model also only returns an array of one prediction per image:
[[0.457804 ]
[0.45051473]
[0.48343503]
[0.49180537]...
Why is it that the model only predicts one of the two classes? Does this have to do with the constant val accuracy or possibly overfitting?
If you have two classes, every image is in one or the other so probabilities for one class are enough to find everything because the sum of the probabilities for each image is supposed to make 1. So if you have the probabilitie p for 1 class, the probability for the other one is 1-p.
If you want to have the possibility of classifing images not in one of those two class, then you should create a third one.
Also, this line:
model_top.add(keras.layers.Dense(1, activation = 'sigmoid'))
means that the Output is a vector of shape(nb_sample,1) and has the same shape as your training labels
I am running an image classification model with images and my problem is that my validation accuracy is higher than my training accuracy.
The data (train/validation) is set up randomly. I am using the InceptionV3 as a pre-trained model. The ratio between accuracy and validation accuracy stays the same over 100 epochs.
I tried a lower learning rate and an additional batch normalization layer.
Does anyone have any ideas on what to look into? I'd appreciate some help, thank you!
base_model = InceptionV3(weights='imagenet', include_top=False)
# add a global spatial average pooling layer
x = base_model.output
x = GlobalAveragePooling2D()(x)
# add a fully-connected layer
x = Dense(468, activation='relu')(x)
x = Dropout(0.5)(x)
# and a logistic layer
predictions = Dense(468, activation='softmax')(x)
# this is the model we will train
model = Model(base_model.input,predictions)
# first: train only the top layers (which were randomly initialized)
# i.e. freeze all convolutional InceptionV3 layers
for layer in base_model.layers:
layer.trainable = False
# compile the model (should be done *after* setting layers to non-trainable)
adam = Adam(lr=0.0001, beta_1=0.9)
model.compile(optimizer=adam, loss='categorical_crossentropy', metrics=['accuracy'])
# train the model on the new data for a few epochs
batch_size = 64
epochs = 100
img_height = 224
img_width = 224
train_samples = 127647
val_samples = 27865
train_datagen = ImageDataGenerator(
rescale=1./255,
#shear_range=0.2,
zoom_range=0.2,
zca_whitening=True,
#rotation_range=0.5,
horizontal_flip=True)
test_datagen = ImageDataGenerator(rescale=1./255)
train_generator = train_datagen.flow_from_directory(
'AD/AutoDetect/',
target_size=(img_height, img_width),
batch_size=batch_size,
class_mode='categorical')
validation_generator = test_datagen.flow_from_directory(
'AD/validation/',
target_size=(img_height, img_width),
batch_size=batch_size,
class_mode='categorical')
# fine-tune the model
model.fit_generator(
train_generator,
samples_per_epoch=train_samples // batch_size,
nb_epoch=epochs,
validation_data=validation_generator,
nb_val_samples=val_samples // batch_size)
Found 127647 images belonging to 468 classes.
Found 27865 images belonging to 468 classes.
Epoch 1/100
2048/1994 [==============================] - 48s - loss: 6.2839 - acc: 0.0073 - val_loss: 5.8506 - val_acc: 0.0179
Epoch 2/100
2048/1994 [==============================] - 44s - loss: 5.8338 - acc: 0.0430 - val_loss: 5.4865 - val_acc: 0.1004
Epoch 3/100
2048/1994 [==============================] - 45s - loss: 5.5147 - acc: 0.0786 - val_loss: 5.1474 - val_acc: 0.1161
Epoch 4/100
2048/1994 [==============================] - 44s - loss: 5.1921 - acc: 0.1074 - val_loss: 4.8049 - val_acc: 0.1786
see this answer
This occours becauce you add a dropout layer in your model that prevents the accuracy from going to 1.0 during training.