def download_imagenet(self) -> str:
filename = 'resnet-101.h5'
resource = 'https://github.com/exemai/sf-retinanet/releases/download/0.0.1/resnet101-keras.h5'
md5sum = '05dc86924389e5b401a9ea0348a3213c'
model_path = get_file(filename,
resource,
cache_subdir='models',
md5_hash=md5sum)
return model_path
def download_imagenet(self) -> str:
filename = 'resnet-152.h5'
resource = 'https://github.com/exemai/sf-retinanet/releases/download/0.0.1/resnet152-keras.h5'
md5sum = '6ee11ef2b135592f8031058820bb9e71'
model_path = get_file(filename,
resource,
cache_subdir='models',
md5_hash=md5sum)
return model_path
def download_imagenet(self) -> str:
filename = 'resnet-50.h5'
resource = 'https://github.com/exemai/sf-retinanet/releases/download/0.0.1/resnet50-keras.h5'
md5sum = '3e9f4e4f77bbe2c9bec13b53ee1c2319'
model_path = get_file(filename,
resource,
cache_subdir='models',
md5_hash=md5sum)
return model_path
def download_imagenet(backbone):
filename = resnet_filename.format(backbone[6:])
resource = resnet_resource.format(backbone[6:])
if backbone == 'resnet50':
checksum = '3e9f4e4f77bbe2c9bec13b53ee1c2319'
elif backbone == 'resnet101':
checksum = '05dc86924389e5b401a9ea0348a3213c'
elif backbone == 'resnet152':
checksum = '6ee11ef2b135592f8031058820bb9e71'
else:
raise ValueError("Il backbone '{}' non รจ riconosciuto.".format(backbone))
return imagenet_utils.get_file(
filename,
resource,
cache_subdir='models',
md5_hash=checksum
)
def download_imagenet(self):
""" Downloads ImageNet weights and returns path to weights file.
"""
resnet_filename = 'ResNet-{}-model.keras.h5'
resnet_resource = 'https://github.com/fizyr/keras-models/releases/download/v0.0.1/{}'.format(
resnet_filename)
depth = int(self.backbone.replace('resnet', ''))
filename = resnet_filename.format(depth)
resource = resnet_resource.format(depth)
if depth == 50:
checksum = '3e9f4e4f77bbe2c9bec13b53ee1c2319'
elif depth == 101:
checksum = '05dc86924389e5b401a9ea0348a3213c'
elif depth == 152:
checksum = '6ee11ef2b135592f8031058820bb9e71'
return imagenet_utils.get_file(filename,
resource,
cache_subdir='models',
md5_hash=checksum)
from keras_retinanet.models import ResNet50RetinaNet
from keras_retinanet.preprocessing import PascalVocIterator
def create_model():
image = keras.layers.Input((512, 512, 3))
im_info = keras.layers.Input((3,))
gt_boxes = keras.layers.Input((None, 5))
return ResNet50RetinaNet([image, im_info, gt_boxes])
if __name__=='__main__':
# create the model
model = create_model()
# load pretrained weights
weights_path = get_file('resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5', WEIGHTS_PATH_NO_TOP, cache_subdir='models', md5_hash='a268eb855778b3df3c7506639542a6af')
model.load_weights(weights_path, by_name=True)
# compile model (note: set loss to None since loss is added inside layer)
model.compile(loss=None, optimizer='adam')
# print model summary
print(model.summary())
# create an image data generator object
image_data_generator = keras.preprocessing.image.ImageDataGenerator(
rescale=1/255
)
# create a generator for training data
train_generator = PascalVocIterator(
def ResNet152(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000):
"""Instantiates the ResNet152 architecture.
Optionally loads weights pre-trained
on ImageNet. Note that when using TensorFlow,
for best performance you should set
`image_data_format='channels_last'` in your Keras config
at ~/.keras/keras.json.
The model and the weights are compatible with both
TensorFlow and Theano. The data format
convention used by the model is the one
specified in your Keras config file.
# Arguments
include_top: whether to include the fully-connected
layer at the top of the network.
weights: one of `None` (random initialization),
'imagenet' (pre-training on ImageNet),
or the path to the weights file to be loaded.
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(224, 224, 3)` (with `channels_last` data format)
or `(3, 224, 224)` (with `channels_first` data format).
It should have exactly 3 inputs channels,
and width and height should be no smaller than 197.
E.g. `(200, 200, 3)` would be one valid value.
pooling: Optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` means that the output of the model will be
the 4D tensor output of the
last convolutional layer.
- `avg` means that global average pooling
will be applied to the output of the
last convolutional layer, and thus
the output of the model will be a 2D tensor.
- `max` means that global max pooling will
be applied.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
# Returns
A Keras model instance.
# Raises
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
"""
WEIGHTS_PATH = None
if not (weights in {'imagenet', None} or os.path.exists(weights)):
raise ValueError('The `weights` argument should be either '
'`None` (random initialization), `imagenet` '
'(pre-training on ImageNet), '
'or the path to the weights file to be loaded.')
if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError('If using `weights` as imagenet with `include_top`'
' as true, `classes` should be 1000')
# Determine proper input shape
input_shape = _obtain_input_shape(input_shape,
default_size=224,
min_size=197,
data_format=K.image_data_format(),
require_flatten=include_top,
weights=weights)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
if K.image_data_format() == 'channels_last':
bn_axis = 3
else:
bn_axis = 1
x = Conv2D(64, (7, 7), strides=(2, 2), padding='same',
name='conv1')(img_input)
x = BatchNormalization(axis=bn_axis, name='bn_conv1')(x)
x = Activation('relu')(x)
x = MaxPool2D((3, 3), strides=(2, 2))(x)
x = conv_block(x, 3, [64, 64, 256], stage=2, block='a', strides=(1, 1))
x = identity_block(x, 3, [64, 64, 256], stage=2, block='b')
x = identity_block(x, 3, [64, 64, 256], stage=2, block='c')
x = conv_block(x, 3, [128, 128, 512], stage=3, block='a')
for i in range(1, 8):
x = identity_block(x, 3, [128, 128, 512], stage=3, block='b' + str(i))
x = conv_block(x, 3, [256, 256, 1024], stage=4, block='a')
for i in range(1, 36):
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='b' + str(i))
x = conv_block(x, 3, [512, 512, 2048], stage=5, block='a')
x = identity_block(x, 3, [512, 512, 2048], stage=5, block='b')
x = identity_block(x, 3, [512, 512, 2048], stage=5, block='c')
x = AvgPool2D((7, 7), name='avg_pool')(x)
if include_top:
x = Flatten()(x)
x = Dense(classes, activation='softmax', name='fc1000')(x)
else:
if pooling == 'avg':
x = GlobalAvgPool2D()(x)
elif pooling == 'max':
x = GlobalMaxPool2D()(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = Model(inputs, x, name='resnet152')
# load weights
if weights == 'imagenet':
weights_path = get_file('resnet152_weights_tf.h5',
WEIGHTS_PATH,
cache_subdir='models')
if include_top:
model.load_weights(weights_path)
else:
f = h5py.File(weights_path)
layer_names = [name for name in f.attrs['layer_names']]
for i, layer in enumerate(model.layers):
g = f[layer_names[i]]
weights = [g[name] for name in g.attrs['weight_names']]
layer.set_weights(weights)
if K.backend() == 'theano':
layer_utils.convert_all_kernels_in_model(model)
if include_top:
maxpool = model.get_layer(name='avg_pool')
shape = maxpool.output_shape[1:]
dense = model.get_layer(name='fc1000')
layer_utils.convert_dense_weights_data_format(
dense, shape, 'channels_first')
if K.image_data_format() == 'channels_first' and K.backend(
) == 'tensorflow':
warnings.warn('You are using the TensorFlow backend, yet you '
'are using the Theano '
'image data format convention '
'(`image_data_format="channels_first"`). '
'For best performance, set '
'`image_data_format="channels_last"` in '
'your Keras config '
'at ~/.keras/keras.json.')
elif weights is not None:
model.load_weights(weights)
return model