def _preprocess_symbolic_input(x, data_format, mode, **kwargs):
"""Preprocesses a tensor encoding a batch of images.
# Arguments
x: Input tensor, 3D or 4D.
data_format: Data format of the image tensor.
mode: One of "caffe", "tf" or "torch".
- caffe: will convert the images from RGB to BGR,
then will zero-center each color channel with
respect to the ImageNet dataset,
without scaling.
- tf: will scale pixels between -1 and 1,
sample-wise.
- torch: will scale pixels between 0 and 1 and then
will normalize each channel with respect to the
ImageNet dataset.
# Returns
Preprocessed tensor.
"""
global _IMAGENET_MEAN
backend, _, _, _ = get_submodules_from_kwargs(kwargs)
if mode == 'tf':
x /= 127.5
x -= 1.
return x
if mode == 'torch':
x /= 255.
mean = [0.485, 0.456, 0.406]
std = [0.229, 0.224, 0.225]
else:
if data_format == 'channels_first':
# 'RGB'->'BGR'
if backend.ndim(x) == 3:
x = x[::-1, ...]
else:
x = x[:, ::-1, ...]
else:
# 'RGB'->'BGR'
x = x[..., ::-1]
mean = [103.939, 116.779, 123.68]
std = None
if _IMAGENET_MEAN is None:
_IMAGENET_MEAN = backend.constant(-np.array(mean))
# Zero-center by mean pixel
if backend.dtype(x) != backend.dtype(_IMAGENET_MEAN):
x = backend.bias_add(
x, backend.cast(_IMAGENET_MEAN, backend.dtype(x)),
data_format=data_format)
else:
x = backend.bias_add(x, _IMAGENET_MEAN, data_format)
if std is not None:
x /= std
return x
def decode_predictions(preds, top=5, **kwargs):
"""Decodes the prediction of an ImageNet model.
# Arguments
preds: Numpy tensor encoding a batch of predictions.
top: Integer, how many top-guesses to return.
# Returns
A list of lists of top class prediction tuples
`(class_name, class_description, score)`.
One list of tuples per sample in batch input.
# Raises
ValueError: In case of invalid shape of the `pred` array
(must be 2D).
"""
global CLASS_INDEX
backend, _, _, keras_utils = get_submodules_from_kwargs(kwargs)
if len(preds.shape) != 2 or preds.shape[1] != 1000:
raise ValueError('`decode_predictions` expects '
'a batch of predictions '
'(i.e. a 2D array of shape (samples, 1000)). '
'Found array with shape: ' + str(preds.shape))
if CLASS_INDEX is None:
fpath = keras_utils.get_file(
'imagenet_class_index.json',
CLASS_INDEX_PATH,
cache_subdir='models',
file_hash='c2c37ea517e94d9795004a39431a14cb')
with open(fpath) as f:
CLASS_INDEX = json.load(f)
results = []
for pred in preds:
top_indices = pred.argsort()[-top:][::-1]
result = [tuple(CLASS_INDEX[str(i)]) + (pred[i],) for i in top_indices]
result.sort(key=lambda x: x[2], reverse=True)
results.append(result)
return results
def preprocess_input(x, data_format=None, mode='caffe', **kwargs):
"""Preprocesses a tensor or Numpy array encoding a batch of images.
# Arguments
x: Input Numpy or symbolic tensor, 3D or 4D.
The preprocessed data is written over the input data
if the data types are compatible. To avoid this
behaviour, `numpy.copy(x)` can be used.
data_format: Data format of the image tensor/array.
mode: One of "caffe", "tf" or "torch".
- caffe: will convert the images from RGB to BGR,
then will zero-center each color channel with
respect to the ImageNet dataset,
without scaling.
- tf: will scale pixels between -1 and 1,
sample-wise.
- torch: will scale pixels between 0 and 1 and then
will normalize each channel with respect to the
ImageNet dataset.
# Returns
Preprocessed tensor or Numpy array.
# Raises
ValueError: In case of unknown `data_format` argument.
"""
backend, _, _, _ = get_submodules_from_kwargs(kwargs)
if data_format is None:
data_format = backend.image_data_format()
if data_format not in {'channels_first', 'channels_last'}:
raise ValueError('Unknown data_format ' + str(data_format))
if isinstance(x, np.ndarray):
return _preprocess_numpy_input(x, data_format=data_format,
mode=mode, **kwargs)
else:
return _preprocess_symbolic_input(x, data_format=data_format,
mode=mode, **kwargs)
def ResNet50(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000,
**kwargs):
"""Instantiates the ResNet50 architecture.
Optionally loads weights pre-trained on ImageNet.
Note that the data format convention used by the model is
the one specified in your Keras config at `~/.keras/keras.json`.
# 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.
"""
global backend, layers, models, keras_utils
backend, layers, models, keras_utils = get_submodules_from_kwargs(kwargs)
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=32,
# data_format=backend.image_data_format(),
# require_flatten=include_top,
# weights=weights)
if input_tensor is None:
img_input = layers.Input(shape=input_shape)
else:
if not backend.is_keras_tensor(input_tensor):
img_input = layers.Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
if backend.image_data_format() == 'channels_last':
bn_axis = 3
else:
bn_axis = 1
x = layers.Reshape((224, 224, 6))(img_input)
x = layers.ZeroPadding2D(padding=(3, 3), name='conv1_pad')(x)
x = layers.Conv2D(64, (7, 7),
strides=(2, 2),
padding='valid',
kernel_initializer='he_normal',
name='conv1')(x)
x = layers.BatchNormalization(axis=bn_axis, name='bn_conv1')(x)
x = layers.Activation('relu')(x)
x = layers.ZeroPadding2D(padding=(1, 1), name='pool1_pad')(x)
x = layers.MaxPooling2D((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')
x = identity_block(x, 3, [128, 128, 512], stage=3, block='b')
x = identity_block(x, 3, [128, 128, 512], stage=3, block='c')
x = identity_block(x, 3, [128, 128, 512], stage=3, block='d')
x = conv_block(x, 3, [256, 256, 1024], stage=4, block='a')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='b')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='c')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='d')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='e')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='f')
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')
if include_top:
x = layers.GlobalAveragePooling2D(name='avg_pool')(x)
x = layers.Dense(classes, activation='softmax', name='fc1000')(x)
else:
if pooling == 'avg':
x = layers.GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = layers.GlobalMaxPooling2D()(x)
else:
warnings.warn('The output shape of `ResNet50(include_top=False)` '
'has been changed since Keras 2.2.0.')
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = keras_utils.get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = models.Model(inputs, x, name='resnet50')
# Load weights.
if weights == 'imagenet':
if include_top:
weights_path = keras_utils.get_file(
'resnet50_weights_tf_dim_ordering_tf_kernels.h5',
WEIGHTS_PATH,
cache_subdir='models',
md5_hash='a7b3fe01876f51b976af0dea6bc144eb')
else:
weights_path = keras_utils.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)
if backend.backend() == 'theano':
keras_utils.convert_all_kernels_in_model(model)
elif weights is not None:
model.load_weights(weights)
return model
def _preprocess_numpy_input(x, data_format, mode, **kwargs):
"""Preprocesses a Numpy array encoding a batch of images.
# Arguments
x: Input array, 3D or 4D.
data_format: Data format of the image array.
mode: One of "caffe", "tf" or "torch".
- caffe: will convert the images from RGB to BGR,
then will zero-center each color channel with
respect to the ImageNet dataset,
without scaling.
- tf: will scale pixels between -1 and 1,
sample-wise.
- torch: will scale pixels between 0 and 1 and then
will normalize each channel with respect to the
ImageNet dataset.
# Returns
Preprocessed Numpy array.
"""
backend, _, _, _ = get_submodules_from_kwargs(kwargs)
if not issubclass(x.dtype.type, np.floating):
x = x.astype(backend.floatx(), copy=False)
if mode == 'tf':
x /= 127.5
x -= 1.
return x
if mode == 'torch':
x /= 255.
mean = [0.485, 0.456, 0.406]
std = [0.229, 0.224, 0.225]
else:
if data_format == 'channels_first':
# 'RGB'->'BGR'
if x.ndim == 3:
x = x[::-1, ...]
else:
x = x[:, ::-1, ...]
else:
# 'RGB'->'BGR'
x = x[..., ::-1]
mean = [103.939, 116.779, 123.68]
std = None
# Zero-center by mean pixel
if data_format == 'channels_first':
if x.ndim == 3:
x[0, :, :] -= mean[0]
x[1, :, :] -= mean[1]
x[2, :, :] -= mean[2]
if std is not None:
x[0, :, :] /= std[0]
x[1, :, :] /= std[1]
x[2, :, :] /= std[2]
else:
x[:, 0, :, :] -= mean[0]
x[:, 1, :, :] -= mean[1]
x[:, 2, :, :] -= mean[2]
if std is not None:
x[:, 0, :, :] /= std[0]
x[:, 1, :, :] /= std[1]
x[:, 2, :, :] /= std[2]
else:
x[..., 0] -= mean[0]
x[..., 1] -= mean[1]
x[..., 2] -= mean[2]
if std is not None:
x[..., 0] /= std[0]
x[..., 1] /= std[1]
x[..., 2] /= std[2]
return x