def _main(args):
config_path = os.path.expanduser(args.config_path)
weights_path = os.path.expanduser(args.weights_path)
assert config_path.endswith('.cfg'), '{} is not a .cfg file'.format(
config_path)
assert weights_path.endswith(
'.weights'), '{} is not a .weights file'.format(weights_path)
output_path = os.path.expanduser(args.output_path)
assert output_path.endswith(
'.h5'), 'output path {} is not a .h5 file'.format(output_path)
output_root = os.path.splitext(output_path)[0]
# Load weights and config.
print('Loading weights.')
weights_file = open(weights_path, 'rb')
major, minor, revision = np.ndarray(
shape=(3,), dtype='int32', buffer=weights_file.read(12))
if (major * 10 + minor) >= 2 and major < 1000 and minor < 1000:
seen = np.ndarray(shape=(1,), dtype='int64', buffer=weights_file.read(8))
else:
seen = np.ndarray(shape=(1,), dtype='int32', buffer=weights_file.read(4))
print('Weights Header: ', major, minor, revision, seen)
print('Parsing Darknet config.')
unique_config_file = unique_config_sections(config_path)
cfg_parser = configparser.ConfigParser()
cfg_parser.read_file(unique_config_file)
print('Creating Keras model.')
input_layer = Input(shape=(None, None, 3), name='image_input')
prev_layer = input_layer
all_layers = []
weight_decay = float(cfg_parser['net_0']['decay']
) if 'net_0' in cfg_parser.sections() else 5e-4
count = 0
out_index = []
for section in cfg_parser.sections():
print('Parsing section {}'.format(section))
if section.startswith('convolutional'):
filters = int(cfg_parser[section]['filters'])
size = int(cfg_parser[section]['size'])
stride = int(cfg_parser[section]['stride'])
pad = int(cfg_parser[section]['pad'])
activation = cfg_parser[section]['activation']
batch_normalize = 'batch_normalize' in cfg_parser[section]
padding = 'same' if pad == 1 and stride == 1 else 'valid'
# Setting weights.
# Darknet serializes convolutional weights as:
# [bias/beta, [gamma, mean, variance], conv_weights]
prev_layer_shape = K.int_shape(prev_layer)
weights_shape = (size, size, prev_layer_shape[-1], filters)
darknet_w_shape = (filters, weights_shape[2], size, size)
weights_size = np.product(weights_shape)
print('conv2d', 'bn' if batch_normalize else ' ', activation, weights_shape)
conv_bias = np.ndarray(
shape=(filters,),
dtype='float32',
buffer=weights_file.read(filters * 4))
count += filters
if batch_normalize:
bn_weights = np.ndarray(
shape=(3, filters),
dtype='float32',
buffer=weights_file.read(filters * 12))
count += 3 * filters
bn_weight_list = [
bn_weights[0], # scale gamma
conv_bias, # shift beta
bn_weights[1], # running mean
bn_weights[2] # running var
]
conv_weights = np.ndarray(
shape=darknet_w_shape,
dtype='float32',
buffer=weights_file.read(weights_size * 4))
count += weights_size
# DarkNet conv_weights are serialized Caffe-style:
# (out_dim, in_dim, height, width)
# We would like to set these to Tensorflow order:
# (height, width, in_dim, out_dim)
conv_weights = np.transpose(conv_weights, [2, 3, 1, 0])
conv_weights = [conv_weights] if batch_normalize else [
conv_weights, conv_bias
]
# Handle activation.
act_fn = None
if activation == 'leaky':
pass # Add advanced activation later.
elif activation == 'mish':
pass # Add advanced activation later.
elif activation != 'linear':
raise ValueError(
'Unknown activation function `{}` in section {}'.format(
activation, section))
# Create Conv2D layer
if stride > 1:
# Darknet uses left and top padding instead of 'same' mode
prev_layer = ZeroPadding2D(((1, 0), (1, 0)))(prev_layer)
conv_layer = (Conv2D(
filters, (size, size),
strides=(stride, stride),
kernel_regularizer=l2(weight_decay),
use_bias=not batch_normalize,
weights=conv_weights,
activation=act_fn,
padding=padding))(prev_layer)
if batch_normalize:
conv_layer = (BatchNormalization(
weights=bn_weight_list))(conv_layer)
prev_layer = conv_layer
if activation == 'linear':
all_layers.append(prev_layer)
# elif activation == 'mish':
# act_layer = Activation(mish)(prev_layer)
# prev_layer = act_layer
# all_layers.append(act_layer)
elif activation == 'leaky':
act_layer = LeakyReLU(alpha=0.1)(prev_layer)
prev_layer = act_layer
all_layers.append(act_layer)
elif section.startswith('route'):
ids = [int(i) for i in cfg_parser[section]['layers'].split(',')]
layers = [all_layers[i] for i in ids]
if len(layers) > 1:
print('Concatenating route layers:', layers)
concatenate_layer = Concatenate()(layers)
all_layers.append(concatenate_layer)
prev_layer = concatenate_layer
else:
skip_layer = layers[0] # only one layer to route
all_layers.append(skip_layer)
prev_layer = skip_layer
elif section.startswith('maxpool'):
size = int(cfg_parser[section]['size'])
stride = int(cfg_parser[section]['stride'])
all_layers.append(
MaxPooling2D(
pool_size=(size, size),
strides=(stride, stride),
padding='same')(prev_layer))
prev_layer = all_layers[-1]
elif section.startswith('avgpool'):
all_layers.append(
AveragePooling2D()(prev_layer))
prev_layer = all_layers[-1]
elif section.startswith('shortcut'):
index = int(cfg_parser[section]['from'])
activation = cfg_parser[section]['activation']
assert activation == 'linear', 'Only linear activation supported.'
all_layers.append(Add()([all_layers[index], prev_layer]))
prev_layer = all_layers[-1]
elif section.startswith('upsample'):
stride = int(cfg_parser[section]['stride'])
assert stride == 2, 'Only stride=2 supported.'
all_layers.append(UpSampling2D(stride)(prev_layer))
prev_layer = all_layers[-1]
elif section.startswith('reorg'):
block_size = int(cfg_parser[section]['stride'])
assert block_size == 2, 'Only reorg with stride 2 supported.'
all_layers.append(
Lambda(
# space_to_depth_x2,
# output_shape=space_to_depth_x2_output_shape,
lambda x: tf.nn.space_to_depth(x, block_size=2),
name='space_to_depth_x2')(prev_layer))
prev_layer = all_layers[-1]
elif section.startswith('region'):
with open('{}_anchors.txt'.format(output_root), 'w') as f:
print(cfg_parser[section]['anchors'], file=f)
elif section.startswith('yolo'):
out_index.append(len(all_layers) - 1)
all_layers.append(None)
prev_layer = all_layers[-1]
elif (section.startswith('net') or section.startswith('cost') or
section.startswith('softmax')):
pass
else:
raise ValueError(
'Unsupported section header type: {}'.format(section))
# Create and save model.
if len(out_index) == 0: out_index.append(len(all_layers) - 1)
if args.yolo4_reorder:
# reverse the output tensor index for YOLOv4 cfg & weights,
# since it use a different yolo outout order
out_index.reverse()
model = Model(inputs=input_layer, outputs=[all_layers[i] for i in out_index])
print(model.summary())
if args.weights_only:
model.save_weights('{}'.format(output_path))
print('Saved Keras weights to {}'.format(output_path))
else:
model.save('{}'.format(output_path))
print('Saved Keras model to {}'.format(output_path))
# Check to see if all weights have been read.
remaining_weights = len(weights_file.read()) / 4
weights_file.close()
print('Read {} of {} from Darknet weights.'.format(count, count +
remaining_weights))
if remaining_weights > 0:
print('Warning: {} unused weights'.format(remaining_weights))
if args.plot_model:
plot(model, to_file='{}.png'.format(output_root), show_shapes=True)
print('Saved model plot to {}.png'.format(output_root))
optimizer=Adam(lr=0.001,
beta_1=0.9,
beta_2=0.999,
epsilon=1e-08,
decay=0.0),
metrics=['accuracy'])
times = 50
while (True):
hist = model.fit(train_X,
train_Y,
batch_size=24,
epochs=times,
verbose=1,
validation_data=(test_X, test_Y))
a = input("continue?y/n")
if (a == "y"):
times = int(input("times:"))
else:
break
(loss, accuracy) = model.evaluate(test_X, test_Y, batch_size=8, verbose=1)
prediction = model.predict(test_X)
predict = np.argmax(prediction, axis=1)
print("Save Model?y/n")
a = input()
if (a == "y"):
print("Saving Model")
model.save("GORES888.h5", overwrite=True, include_optimizer=True)
else:
print("Over")
out = Dense(num_classes, activation="softmax", name="output")(last_layer)
model = Model(image_input, out)
for layer in model.layers[:-1]:
layer.trainable = False
model.summary()
model.compile(loss='sparse_categorical_crossentropy',
optimizer=Adam(lr=0.001,
beta_1=0.9,
beta_2=0.999,
epsilon=1e-08,
decay=0.0),
metrics=['accuracy'])
hist = model.fit(train_X,
train_Y,
batch_size=16,
epochs=30,
verbose=1,
validation_data=(test_X, test_Y))
(loss, accuracy) = model.evaluate(test_X, test_Y, batch_size=8, verbose=1)
prediction = model.predict(test_X)
predict = np.argmax(prediction, axis=1)
print("Save Model?y/n")
a = input()
if (a == "y"):
print("Saving Model")
model.save("RESRetry14.h5", overwrite=True, include_optimizer=True)
else:
print("Over")
def main(train_epochs):
print('Hello Lenin Welcome to Transfer Learning with VGG16')
# Reading images to form X vector
labels_name = {'benign': 0, 'malignant': 1}
img_data, img_labels = read_dataset('/data_roi_single/train',
labels_dict=labels_name)
print(np.unique(img_labels, return_counts=True))
# categories_names = ['benign', 'malignant']
num_classes = 2
# labels = labelling_outputs(num_classes, img_data.shape[0])
# labels = labelling_mammo(num_classes, img_data.shape[0])
# converting class labels to one-hot encoding
y_one_hot = to_categorical(img_labels, num_classes)
#Shuffle data
x, y = shuffle(img_data, y_one_hot, random_state=2)
# Dataset split
xtrain, xtest, ytrain, ytest = train_test_split(x,
y,
test_size=0.2,
random_state=2)
#########################################################################################
# Custom_vgg_model_1
# Training the classifier alone
image_input = Input(shape=(224, 224, 3))
model = VGG16(input_tensor=image_input,
include_top=True,
weights='imagenet')
model.summary()
last_layer = model.get_layer('fc2').output
out = Dense(num_classes, activation='sigmoid',
name='vgg16TL')(last_layer) # sigmoid insted of softmax
custom_vgg_model = Model(image_input, out)
custom_vgg_model.summary()
# until this point the custom model is retrainable at all layers
# Now we freeze all the layers up to the last one
for layer in custom_vgg_model.layers[:-1]:
layer.trainable = False
custom_vgg_model.summary()
# custom_vgg_model.layers[3].trainable
# custom_vgg_model.layers[-1].trainable
# Model compilation
custom_vgg_model.compile(
loss='binary_crossentropy', optimizer='rmsprop',
metrics=['accuracy']) # binary cross entropy instead of categorical
print('Transfer Learning Training...')
t = time.time()
num_of_epochs = train_epochs # User defines number of epochs
hist = custom_vgg_model.fit(xtrain,
ytrain,
batch_size=64,
epochs=num_of_epochs,
verbose=1,
validation_data=(xtest, ytest))
print('Training time: %s' % (time.time() - t))
# Model saving parameters
custom_vgg_model.save('vgg16_tf_bc.h5')
print('Evaluation...')
(loss, accuracy) = custom_vgg_model.evaluate(xtest,
ytest,
batch_size=10,
verbose=1)
print("[INFO] loss={:.4f}, accuracy: {:.4f}%".format(loss, accuracy * 100))
print("Finished")
# Model Training Graphics
# Visualizing losses and accuracy
train_loss = hist.history['loss']
val_loss = hist.history['val_loss']
train_acc = hist.history['acc']
val_acc = hist.history['val_acc']
xc = range(num_of_epochs) # Este valor esta anclado al numero de epocas
plt.figure(1, figsize=(7, 5))
plt.plot(xc, train_loss)
plt.plot(xc, val_loss)
plt.xlabel('num of epochs')
plt.ylabel('loss')
plt.title('train_loss vs val_loss')
plt.grid(True)
plt.legend(['train', 'val'])
plt.style.use(['classic']) # revisar que mas hay
plt.savefig('vgg16_train_val_loss.jpg')
plt.figure(2, figsize=(7, 5))
plt.plot(xc, train_acc)
plt.plot(xc, val_acc)
plt.xlabel('num of epochs')
plt.ylabel('accuracy')
plt.title('train_accuracy vs val_accuracy')
plt.grid(True)
plt.legend(['train', 'val'], loc=4)
plt.style.use(['classic']) # revisar que mas hay
plt.savefig('vgg16_train_val_acc.jpg')
plt.show()