Related
I'm trying to get VGG16 model to acceptable accuracy but I can't get it above .3
here's the model
def VGG16():
model = Sequential()
model.add(Conv2D(input_shape=(224,224,3),filters=64,kernel_size=(3,3),padding='same', activation='relu'))
model.add(Conv2D(filters=64,kernel_size=(3,3),padding='same', activation='relu'))
model.add(MaxPool2D(pool_size=(2,2),strides=(2,2)))
model.add(Conv2D(filters=128, kernel_size=(3,3), padding='same', activation='relu'))
model.add(Conv2D(filters=128, kernel_size=(3,3), padding='same', activation='relu'))
model.add(MaxPool2D(pool_size=(2,2),strides=(2,2)))
model.add(Conv2D(filters=256, kernel_size=(3,3), padding='same', activation='relu'))
model.add(Conv2D(filters=256, kernel_size=(3,3), padding='same', activation='relu'))
model.add(Conv2D(filters=256, kernel_size=(3,3), padding='same', activation='relu'))
model.add(MaxPool2D(pool_size=(2,2),strides=(2,2)))
model.add(Conv2D(filters=512, kernel_size=(3,3), padding='same', activation='relu'))
model.add(Conv2D(filters=512, kernel_size=(3,3), padding='same', activation='relu'))
model.add(Conv2D(filters=512, kernel_size=(3,3), padding='same', activation='relu'))
model.add(MaxPool2D(pool_size=(2,2),strides=(2,2)))
model.add(Conv2D(filters=512, kernel_size=(3,3), padding='same', activation='relu'))
model.add(Conv2D(filters=512, kernel_size=(3,3), padding='same', activation='relu'))
model.add(Conv2D(filters=512, kernel_size=(3,3), padding='same', activation='relu'))
model.add(MaxPool2D(pool_size=(2,2),strides=(2,2),name='vgg16'))
model.add(Flatten(name='flatten'))
model.add(Dense(4096, activation='relu', name='fc1'))
model.add(Dense(4096, activation='relu', name='fc2'))
model.add(Dense(9, activation='softmax', name='output'))
return model
opt = SGD(learning_rate=1e-6, momentum=0.9)
model.compile(loss='categorical_crossentropy', optimizer=opt, metrics=['accuracy'])
some answers here suggested changing the number of neurons in the fully connected layers to 4096 (originally used 256 and 128), using SGD instead of Adam, increasing the number of epochs (tried 50, 100 and 200) and the batch size (tried 64 and 128) but I can't get it above .3 and usually it's .2.
parameters I used in the best result are
fully connected neurons 4096
optimizer SGD
learning rate e-6
epochs 100
batch size 128
edit dataset used https://www.kaggle.com/datasets/nodoubttome/skin-cancer9-classesisic
you did not show the data for the model training but I suspect your model will be very prone to over fitting. You need to add some dropout layers and some regularization.
After your flatten layer type the following
model.add(BatchNormalization(axis=-1, momentum=0.99, epsilon=0.001 ))
model.add(Dense(256, kernel_regularizer = regularizers.l2(l = 0.016),activity_regularizer=regularizers.l1(0.006),
bias_regularizer=regularizers.l1(0.006) ,activation='relu') )
model.add(Dropout(rate=.4, seed=123), name='dropout'))
model.add(Dense(9, activation='softmax', name='output'))
it would be helpful if you provide the model training data as well
I am running a 3 class classification problem with around 7200 total images using CNN. I have used 80:20 split and the accuracy and loss curves are attached along with the code.
Can someone explain why the validation accuracy is higher then the training and similarly training loss is higher than the validation loss. Although the difference is marginal (around 1%), I am not sure if its acceptable or I need to improve the model.
Here is the model I am running with batch_size = 64
# define cnn model
def define_model():
model = Sequential()
model.add(Conv2D(32, (3, 3), activation='relu', kernel_initializer='he_uniform', padding='same', input_shape=(64, 64, 3)))
model.add(BatchNormalization())
model.add(MaxPooling2D((2, 2)))
model.add(Dropout(0.2))
model.add(Conv2D(64, (3, 3), activation='relu', kernel_initializer='he_uniform', padding='same'))
model.add(BatchNormalization())
model.add(MaxPooling2D((2, 2)))
model.add(Dropout(0.3))
model.add(Conv2D(128, (3, 3), activation='relu', kernel_initializer='he_uniform', padding='same'))
model.add(BatchNormalization())
model.add(MaxPooling2D((2, 2)))
model.add(Dropout(0.4))
model.add(Flatten())
model.add(Dense(128, activation='relu', kernel_initializer='he_uniform'))
model.add(BatchNormalization())
model.add(Dropout(0.5))
model.add(Dense(3, activation='softmax'))
# compile model
opt = SGD(lr=0.001, momentum=0.9)
model.compile(optimizer=opt, loss='categorical_crossentropy', metrics=['accuracy'])
return model
I tried various other models but the accuracy and loss curves didn't seem good. This one seems good but I was expecting the training accuracy to be higher than the validation accuracy
I am training a CNN model where,
Training data=687 , validation data=102 , testing data=79
The validation accuracy is higher than training accuracy
The test accuracy is very low compared to both validation accuracy and training accuracy.
Validation loss is lower than training loss.
code snippet:
train_datagen = ImageDataGenerator(
rescale=1./255,
# rotation_range=30,
zoom_range=0.1,
horizontal_flip=True,
# vertical_flip=True,
# fill_mode='nearest',
validation_split=.15) # set validation split
val_datagen = ImageDataGenerator(rescale=1./255, validation_split=0.15)
train_generator = train_datagen.flow_from_directory(
train_dir,
target_size=(height, width),
batch_size=batch_size,
class_mode='categorical',
seed=13
)
validation_generator = val_datagen.flow_from_directory(
train_dir, # same directory as training data
target_size=(height, width),
batch_size=batch_size,
class_mode='categorical',
seed=13,
subset='validation'
)
model = Sequential()
model.add(Conv2D(16,3,padding="same", activation="relu", input_shape=(height, width, 3)))
model.add(AveragePooling2D(strides=(2,2), padding="same"))
# model.add(Dropout(0.2))
model.add(Conv2D(32,3,padding="same", activation="relu"))
model.add(AveragePooling2D(strides=(2,2), padding="same"))
# model.add(Dropout(0.2))
model.add(Conv2D(32, 3, padding="same", activation="relu"))
model.add(AveragePooling2D(strides=(2,2), padding="same"))
# model.add(Dropout(0.2))
# model.add(Conv2D(32, 3, padding="same", activation="relu", kernel_regularizer=l2(0.0001)))
# model.add(AveragePooling2D(strides=(2,2), padding="same"))
# model.add(Dropout(0.4))
model.add(Conv2D(64, 3, padding="same", activation="relu"))
model.add(AveragePooling2D(strides=(2,2), padding="same",))
# model.add(Dropout(0.2))
model.add(Conv2D(64, 3, padding="same", activation="relu"))
model.add(AveragePooling2D(strides=(2,2), padding="same"))
# model.add(Dropout(0.2))
model.add(Conv2D(128, 3, padding="same", activation="relu"))
model.add(AveragePooling2D(strides=(2,2), padding="same"))
# model.add(Dropout(0.2))
model.add(Conv2D(128, 3, padding="same", activation="relu"))
model.add(AveragePooling2D(strides=(2,2), padding="same"))
# model.add(Dropout(0.2))
model.add(Conv2D(256, 3, padding="same", activation="relu"))
model.add(AveragePooling2D(strides=(2,2), padding="same"))
# model.add(Dropout(0.2))
model.add(Flatten())
model.add(Dense(256,activation="relu"))
model.add(Dropout(.5))
# model.add(Dense(256,activation="relu"))
# model.add(Dropout(.5))
model.add(Dense(4, activation="softmax"))
model.summary()
Adam(learning_rate=0.0001, name='Adam')
model.compile(optimizer = 'Adam',loss = 'categorical_crossentropy',metrics = ['accuracy'])
I've done few things to solve this problem:
I didn't used dropout layers between the conv layers
I decreased the range of the data augmentation.
I trained for longer period(the testing accuracy drops to 62% and the val_acc eventually reaches 100%).
What could be the cause of this issue and how can it be resolved?
How can I display test images in Python that have high levels of inaccuracy?
You need to add subset='training' in train_generator. Right now, you are training on both training and validation data.
train_generator = train_datagen.flow_from_directory(
train_dir,
target_size=(height, width),
batch_size=batch_size,
class_mode='categorical',
seed=13,
subset='training'
)
Recently I have been trying to build an automated car in gta v using a CNN model. I started out by collecting about 30k images from the game by driving around while capturing the scene and the key that was pressed at the current time. I also made sure to keep the dataset balanced by limiting the amount of data for each label to be equal.
An example of a random image in the dataset: IMAGE.
The labels are the basic driving inputs -LABELS.
Using this dataset on various models the accuracy never went above 50-60% on the validation test (test accuracy is even lower). Trying to fix this issue I tried cropping the images from the dataset to only include the center of the image which contains the road and drop the outlying data (scenery, buildings etc..). Also tried using RGB pictures as data instead of greyscale, also tested out collecting data from a specific location and testing it in the same place, different model architectures, different parameters and still no luck.
All the models were tested out in-game by constantly capturing the image of the road in-game and using it as an input to the model, then the output of the model would be the input for the game. All models seem to behave in the same general way which is basically outputting the same label – mostly ‘WA’, until it crashes into a wall.
I would love to get some tips on what I may be doing wrong or on what I can do to improve performance and let me know if you need any more information regarding this project to help out.
Thanks in advance.
TWO OF THE MODELS I TRIED:
model = Sequential()
model.add(Conv2D(filters=96, kernel_size=11, strides=4, activation='relu', input_shape=(IMAGE_HEIGHT, IMAGE_WIDTH, IMAGE_CHANNELS), padding='same'))
model.add(MaxPooling2D(pool_size=(3, 3), strides=2))
model.add(Conv2D(filters=256, kernel_size=5, activation='relu', padding='same'))
model.add(MaxPooling2D(pool_size=(3, 3), strides=2))
model.add(Conv2D(filters=384, kernel_size=3, activation='relu', padding='same'))
model.add(Conv2D(filters=384, kernel_size=3, activation='relu', padding='same'))
model.add(Conv2D(filters=256, kernel_size=3, activation='relu', padding='same'))
model.add(MaxPooling2D(pool_size=(3, 3), strides=2))
model.add(Dense(4096, activation='tanh'))
model.add(Dropout(0.5))
model.add(Dense(4096, activation='tanh'))
model.add(Dropout(0.5))
model.add(Flatten())
model.add(Dense(7, activation='sigmoid'))
model = Sequential()
model.add(Conv2D(filters=12, kernel_size=11, activation='relu', input_shape=(IMAGE_HEIGHT, IMAGE_WIDTH, IMAGE_CHANNELS), padding='same'))
model.add(MaxPooling2D(pool_size=(3,3)))
model.add(Conv2D(filters=256, kernel_size=5, activation='relu', padding='same'))
model.add(MaxPooling2D(pool_size=(3,3)))
model.add(Conv2D(filters=384, kernel_size=3, activation='relu', padding='same'))
model.add(Conv2D(filters=256, kernel_size=5, activation='relu', padding='same'))
model.add(MaxPooling2D(pool_size=(3,3)))
model.add(Flatten())
model.add(Dense(7, activation='sigmoid'))
The code:
filenames = os.listdir("dataset")
labels = []
for filename in filenames:
label = filename.split('.')[1]
labels.append(label)
df = pd.DataFrame({
'filename': filenames,
'category': labels
})
model = model1()
print(model.summary())
model.compile(loss='categorical_crossentropy', optimizer=Adam(learning_rate=0.001), metrics=['accuracy'])
train_df, validate_df = train_test_split(df, test_size=0.40, random_state=42)
train_df = train_df.reset_index(drop=True)
validate_df = validate_df.reset_index(drop=True)
total_train = train_df.shape[0]
total_validate = validate_df.shape[0]
batch_size=32
train_datagen = ImageDataGenerator(rescale=1./255)
train_generator = train_datagen.flow_from_dataframe(
train_df,
"dataset",
x_col='filename',
y_col='category',
target_size=IMAGE_SIZE,
class_mode='categorical',
batch_size=batch_size
)
validation_datagen = ImageDataGenerator( rescale=1./255,)
validation_generator = validation_datagen.flow_from_dataframe(
validate_df,
"dataset",
x_col='filename',
y_col='category',
target_size=IMAGE_SIZE,
class_mode='categorical',
batch_size=batch_size
)
epochs = 25
log_dir = "logs/fit/" + datetime.datetime.now().strftime("%Y%m%d-%H%M%S")
tensorboard_callback = tf.keras.callbacks.TensorBoard(log_dir=log_dir, histogram_freq=1)
history = model.fit(
train_generator,
epochs=epochs,
validation_data=validation_generator,
validation_steps=total_validate // batch_size,
steps_per_epoch=total_train // batch_size, shuffle=True, callbacks=[tensorboard_callback])
model.save("model.h5")
I have a cnn network, which I'm trying to test.
I'm getting errors about the input, and I can't figure why
model = Sequential()
model.add(Conv2D(32, kernel_size=(3, 3), activation='relu', input_shape=(99,13,1)))
model.add(Conv2D(64, kernel_size=(3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes, activation='softmax'))
model.compile(loss='categorical_crossentropy',optimizer='adam', metrics=['accuracy'])
print(model.summary())
model.fit(x_train, y_train, batch_size=4, epochs=10, verbose=1, validation_data=(x_test, y_test))
where:
x_train / test .shape = {tuple: 3}(30, 99, 13)
y_train / test shape = {tuple: 1}30
Error:
ValueError: Input 0 of layer sequential is incompatible with the layer: : expected min_ndim=4, found ndim=3. Full shape received: [None, 99, 13]
What's wrong and how can I fix it ?
model.add(Conv2D(32, kernel_size=(3, 3), activation='relu', input_shape=(99,13,1)))
Model waiting for shape [batch, (99,13,1)], you are trying to feed [batch, 99, 13].
I think you need change your input to input_shape=(99,13) in order to match train data
Conv2D requires 4D+ shape
Expand dimension of your data to batch,99,13,1