I see improving training accuracies after each iteration, but testing accuracy stays fixed at exactly 0.7545 after each epoch. I understand hitting a ceiling on accuracy at some point but don't understand why I don't at least see slight variations in accuracies (up or down). I'm training on about 800 images total.
Things I've tried:
- Switch to SGD optimizer.
- Start with learning rate of 0.01 and reduce until 0.00000001.
- Remove regularization layers.
#PARAMS
dropout_prob = 0.2
activation_function = 'relu'
loss_function = 'categorical_crossentropy'
verbose_level = 1
convolutional_batches = 32
convolutional_epochs = 10
inp_shape = X_train.shape[1:]
num_classes = 3
opt = SGD(lr=0.00001)
opt2 = 'adam'
def train_convolutional_neural():
y_train_cat = np_utils.to_categorical(y_train, 3)
y_test_cat = np_utils.to_categorical(y_test, 3)
model = Sequential()
model.add(Conv2D(filters=16, kernel_size=(3, 3), input_shape=inp_shape))
model.add(Conv2D(filters=32, kernel_size=(3, 3)))
model.add(MaxPooling2D(pool_size = (2,2)))
model.add(Dropout(rate=dropout_prob))
model.add(Flatten())
#model.add(Dense(64,activation=activation_function))
model.add(Dropout(rate=dropout_prob))
model.add(Dense(32,activation=activation_function))
model.add(Dense(num_classes,activation='softmax'))
model.summary()
model.compile(loss=loss_function, optimizer=opt, metrics=['accuracy'])
history = model.fit(X_train, y_train_cat, batch_size=convolutional_batches, epochs = convolutional_epochs, verbose = verbose_level, validation_data=(X_test, y_test_cat))
model.save('./models/convolutional_model.h5')
Related
Can anyone help me to reduce val_loss and increase val_accuracy?
Below is the code of my Inception-V3 model. I added two dense layers with 1024 nodes with ReLU activation function, 1 GlobalAverage2D and 1 Dropout layer. And 1 last fully-connected layer with softmax activation for classification purpose.
To increase val_accuracy and reduce val_loss. Do i need to remove any one of the following layers?
pretrained_model = tf.keras.applications.InceptionV3(
input_shape=(224, 224, 3),
include_top=False,
weights='imagenet'
)
pretrained_model.trainable = False
inputs = pretrained_model.input
x = GlobalAveragePooling2D()(pretrained_model.output)
x = tf.keras.layers.Dense(1024, activation='relu')(x)
x = tf.keras.layers.Dense(1024, activation='relu')(x)
x = Dropout(0.5)(x)
outputs = tf.keras.layers.Dense(5, activation='softmax')(x)
model = tf.keras.Model(inputs=inputs, outputs=outputs)
model.compile(
optimizer=Adam(learning_rate=0.0001),
loss='categorical_crossentropy',
metrics=['accuracy','AUC']
)
history = model.fit(
train_images,
validation_data=val_images,
batch_size = 64,
epochs=20,
callbacks=[
tf.keras.callbacks.EarlyStopping(
monitor='val_loss',
patience=5,
restore_best_weights=True
)
]
)
Below graphs shows the accuracy and loss obtained from the trained inception-V3 model.
accuracy
loss
I've been training a CNN with keras. A binary classificator where it says if a depth image has a manhole or not. I've manually labeled the datasets with 0 (no manhole) and 1 (it has a manhole). I have 2 datasets 1 with 45k images to train the CNN and one with 26k images to test the CNN.
Both datasets are unbalanced double of negatives images than positives.
This is the code:
# dimensions of our images.
img_width, img_height = 80, 60
n_positives_img, n_negatives_img = 17874, 26308
n_total_img = 44182
#Labeled arrays for datasets
arrayceros = np.zeros(n_negatives_img)
arrayunos = np.ones(n_positives_img)
#Reshaping of datasets to convert separate them
arraynegativos= ds_negatives.reshape(( n_negatives_img, img_height, img_width,1))
arraypositivos= ds_positives.reshape((n_positives_img, img_height, img_width,1))
#Labeling datasets with the arrays
ds_negatives_target = tf.data.Dataset.from_tensor_slices((arraynegativos, arrayceros))
ds_positives_target = tf.data.Dataset.from_tensor_slices((arraypositivos, arrayunos))
#Concatenate 2 datasets and shuffle them
ds_concatenate = ds_negatives_target.concatenate(ds_positives_target)
datasetfinal = ds_concatenate.shuffle(n_total_img)
Then I have the same for the second dataset for testing.
#Adding batch dimension to datasets 4dim
valid_ds = datasetfinal2.batch(12)
train_ds = datasetfinal.batch(12)
#Defining model
model = Sequential()
model.add(Conv2D(5, kernel_size=(5, 5),activation='relu',input_shape=(60,80,1),padding='same'))
model.add(BatchNormalization())
model.add(MaxPooling2D((5, 5),padding='same'))
model.add(Dropout(0.3))
model.add(Conv2D(5, (5, 5), activation='relu',padding='same'))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2, 2),padding='same'))
model.add(Dropout(0.3))
model.add(Conv2D(5, (5, 5), activation='relu',padding='same'))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2, 2),padding='same'))
model.add(Dropout(0.3))
model.add(Conv2D(5, (5, 5), activation='relu',padding='same'))
model.add(BatchNormalization())
model.add(Flatten())
model.add(Dropout(0.5))
model.add(Dense(100, activation='relu'))
model.add(Dropout(0.2))
model.add(Dense(50, activation='relu'))
model.add(Dropout(0.2))
model.add(Dense(1, activation='sigmoid'))
#Compiling model
model.summary()
initial_learning_rate = 0.001
lr_schedule = keras.optimizers.schedules.ExponentialDecay(
initial_learning_rate, decay_steps=100000, decay_rate=0.96, staircase=True
)
model.compile(
loss="binary_crossentropy",
optimizer=keras.optimizers.Adam(learning_rate=lr_schedule),
metrics=["acc"],
)
# Define callbacks.
checkpoint_cb = keras.callbacks.ModelCheckpoint(
"2d_image_classification.h5", save_best_only=True
)
early_stopping_cb = keras.callbacks.EarlyStopping(monitor="val_acc", patience=15)
#Fitting the model
history= model.fit(train_ds, validation_data=valid_ds, batch_size=100, epochs=5,callbacks=[checkpoint_cb, early_stopping_cb])
This gives me 99% of acc in train dataset and 95% in test dataset.
But when i do this it gives me 60% precision for negatives images and 45% for positives:
#Get the real labels of valid dataset
valid_labels = list(valid_ds.flat_map(lambda x, y: tf.data.Dataset.from_tensor_slices((x, y))).as_numpy_iterator())
valid_labels = [y for x, y in valid_labels]
y_pred = model.predict(valid_ds)
y_pred = (y_pred > 0.5).astype(float)
from sklearn.metrics import classification_report
print(classification_report(valid_labels, y_pred))
Why this? I have printed both predicted labels and true labels and it look likes its random. It has no sense.
https://colab.research.google.com/drive/1bhrntDItqoeT0KLb-aKp0W8cV6LOQOtP?usp=sharing
If u need more information, just ask me.
Thanks!!!!
I am trying to use a custom loss function for my model. I am scaling y values previously and in my loss function I inverse scale them.(Using the answer from scaling back data in customized keras training loss function) After a random amount of epochs the loss starts to come as NaN also mean_absolute_error val_mean_absolute_error and val_loss are all NaN. Heres my model and custom loss function:
model = Sequential()
model.add(LSTM(units=512, activation="tanh", return_sequences=True, input_shape=(X_train.shape[1],X_train.shape[2])))
model.add(Dropout(0.2))
model.add(LSTM(units=256, activation="tanh", return_sequences=True))
model.add(Dropout(0.2))
model.add(LSTM(units=128, activation="tanh", return_sequences=True))
model.add(Dropout(0.2))
model.add(LSTM(units=64, activation="tanh"))
model.add(Dropout(0.2))
model.add(Dense(units = 2))
model.compile(optimizer = "Adam", loss = my_loss_function , metrics=['mean_absolute_error'])
model.summary()
I have 2 outputs as you can see.
def my_loss_function(y_actual, y_predicted):
y_actual = (y_actual - K.constant(y_scaler.min_)) / K.constant(y_scaler.scale_)
y_predicted = (y_predicted - K.constant(y_scaler.min_)) / K.constant(y_scaler.scale_)
a_loss = abs(y_actual[0]-y_predicted[0])*128000
b_loss = abs(y_actual[1]-y_predicted[1])*27000
loss= tf.math.sqrt(tf.square(a_loss) + tf.square(b_loss))
return loss
y_scaler is used earlier:
y_scaler = MinMaxScaler(feature_range = (0, 1))
y_scaler.fit(y_data)
y_data=y_scaler.transform(y_data)
y_testdata=y_scaler.transform(y_testdata)
Can anyone help?
When I use MSE, MAE etc. it works fine
I am learning Keras using audio classification, Actually, I am implementing the code with modification from https://github.com/deepsound-project/genre-recognition/blob/master/train_model.py using Keras.
The shape of the dataset is
X_train shape = (800, 32, 1)
y_train shape = (800, 10)
X_test shape = (200, 32, 1)
y_test shape = (200, 10)
The model
model = Sequential()
model.add(Conv1D(filters=256, kernel_size=5, input_shape=(32,1), activation="relu"))
model.add(BatchNormalization(momentum=0.9))
model.add(MaxPooling1D(2))
model.add(Dropout(0.5))
model.add(Conv1D(filters=256, kernel_size=5, activation="relu"))
model.add(BatchNormalization(momentum=0.9))
model.add(MaxPooling1D(2))
model.add(Dropout(0.5))
model.add(Flatten())
model.add(Dense(128, activation="relu", ))
model.add(Dense(10, activation='softmax'))
model.compile(
loss='categorical_crossentropy',
optimizer = Adam(lr=0.001),
metrics = ['accuracy'],
)
model.summary()
red_lr= ReduceLROnPlateau(monitor='val_loss',patience=2,verbose=2,factor=0.5,min_delta=0.01)
check=ModelCheckpoint(filepath=r'/content/drive/My Drive/Colab Notebooks/gen/cnn.hdf5', verbose=1, save_best_only = True)
History = model.fit(X_train,
y_train,
epochs=100,
#batch_size=512,
validation_data = (X_test, y_test),
verbose = 2,
callbacks=[check, red_lr],
shuffle=True )
The accuracy graph
Loss graph
I do not understand, Why the val_acc is in the range of 70%. I tried to modify the model architecture including optimizer, but no improvement.
And, Is it good to have a lot of difference between loss and val_loss.
how to improve the accuracy above 80... any help...
Thank you
I found it, I use concatenate function from Keras to concatenate all convolution layers and, it gives the best performance.
I am generating at most 4 digits captchas with the following method:
def genData(n=30000, max_digs=4, width=150):
capgen = ImageCaptcha()
data = []
target = []
for i in range(n):
x = np.random.randint(0, 10 ** max_digs)
img = misc.imread(capgen.generate(str(x)))
img = np.mean(img, axis=2)[:, :width]
data.append(img.flatten())
target.append(x)
return np.array(data), np.array(target)
Then I am processing data like following
train_data, train_target = genData()
test_data, test_target = genData(1000)
train_data = train_data.reshape(train_data.shape[0], 1, 150, 60)
test_data = test_data.reshape(test_data.shape[0], 1, 150, 60)
train_data = train_data.astype('float32')
test_data = test_data.astype('float32')
train_data /= 255
test_data /= 255
My model structure is as follows:
def get_model():
# create model
model = Sequential()
model.add(Conv2D(30, (5, 5), input_shape=(1, 150, 60), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(15, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.2))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dense(50, activation='relu'))
model.add(Dense(10 ** 4, activation='softmax'))
# Compile model
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
return model
Then I am training the model
model = get_model()
# Fit the model
model.fit(train_data, train_target, validation_data=(test_data, test_target), epochs=10, batch_size=200)
# Final evaluation of the model
scores = model.evaluate(test_data, test_target, verbose=0)
print("Large CNN Error: %.2f%%" % (100 - scores[1] * 100))
I don't know which part that I am doing wrong but my accuracy cannot reach even %1.
You have 10000(!) classes. How long do you train? How much training data do you have per class?
Your approach is almost certainly the problem. While you can solve problems "brute force" like this, it is a very bad way to do so. You should first try to detect single digits and then classify each digit with a 10-class classifier.