Resnet-152 pre-trained model in Keras

readme.md

ResNet-152 in Keras

This is an Keras implementation of ResNet-152 with ImageNet pre-trained weights. I converted the weights from Caffe provided by the authors of the paper. The implementation supports both Theano and TensorFlow backends. Just in case you are curious about how the conversion is done, you can visit my blog post for more details.

ResNet Paper:

Deep Residual Learning for Image Recognition.
Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun
arXiv:1512.03385

Fine-tuning

Check this out to see example of fine-tuning ResNet-152 with your own dataset.

Contents

model and usage demo: resnet-152_keras.py

Weights (Theano): resnet152_weights_th.h5

Weights (TensorFlow): resnet152_weights_tf.h5

resnet-152_keras.py

# -*- coding: utf-8 -*-

import cv2
import numpy as np
import copy

from keras.layers import Input, Dense, Convolution2D, MaxPooling2D, AveragePooling2D, ZeroPadding2D, Dropout, Flatten, merge, Reshape, Activation, Lambda, GlobalAveragePooling2D, Merge
from keras.optimizers import SGD
from keras.layers.normalization import BatchNormalization
from keras.models import Model
from keras import initializations
from keras.engine import Layer, InputSpec
from keras import backend as K

import sys
sys.setrecursionlimit(3000)

class Scale(Layer):
    '''Custom Layer for ResNet used for BatchNormalization.
    
    Learns a set of weights and biases used for scaling the input data.
    the output consists simply in an element-wise multiplication of the input
    and a sum of a set of constants:

        out = in * gamma + beta,

    where 'gamma' and 'beta' are the weights and biases larned.

    # Arguments
        axis: integer, axis along which to normalize in mode 0. For instance,
            if your input tensor has shape (samples, channels, rows, cols),
            set axis to 1 to normalize per feature map (channels axis).
        momentum: momentum in the computation of the
            exponential average of the mean and standard deviation
            of the data, for feature-wise normalization.
        weights: Initialization weights.
            List of 2 Numpy arrays, with shapes:
            `[(input_shape,), (input_shape,)]`
        beta_init: name of initialization function for shift parameter
            (see [initializations](../initializations.md)), or alternatively,
            Theano/TensorFlow function to use for weights initialization.
            This parameter is only relevant if you don't pass a `weights` argument.
        gamma_init: name of initialization function for scale parameter (see
            [initializations](../initializations.md)), or alternatively,
            Theano/TensorFlow function to use for weights initialization.
            This parameter is only relevant if you don't pass a `weights` argument.
    '''
    def __init__(self, weights=None, axis=-1, momentum = 0.9, beta_init='zero', gamma_init='one', **kwargs):
        self.momentum = momentum
        self.axis = axis
        self.beta_init = initializations.get(beta_init)
        self.gamma_init = initializations.get(gamma_init)
        self.initial_weights = weights
        super(Scale, self).__init__(**kwargs)

    def build(self, input_shape):
        self.input_spec = [InputSpec(shape=input_shape)]
        shape = (int(input_shape[self.axis]),)

        self.gamma = self.gamma_init(shape, name='{}_gamma'.format(self.name))
        self.beta = self.beta_init(shape, name='{}_beta'.format(self.name))
        self.trainable_weights = [self.gamma, self.beta]

        if self.initial_weights is not None:
            self.set_weights(self.initial_weights)
            del self.initial_weights

    def call(self, x, mask=None):
        input_shape = self.input_spec[0].shape
        broadcast_shape = [1] * len(input_shape)
        broadcast_shape[self.axis] = input_shape[self.axis]

        out = K.reshape(self.gamma, broadcast_shape) * x + K.reshape(self.beta, broadcast_shape)
        return out

    def get_config(self):
        config = {"momentum": self.momentum, "axis": self.axis}
        base_config = super(Scale, self).get_config()
        return dict(list(base_config.items()) + list(config.items()))

def identity_block(input_tensor, kernel_size, filters, stage, block):
    '''The identity_block is the block that has no conv layer at shortcut
    # Arguments
        input_tensor: input tensor
        kernel_size: defualt 3, the kernel size of middle conv layer at main path
        filters: list of integers, the nb_filters of 3 conv layer at main path
        stage: integer, current stage label, used for generating layer names
        block: 'a','b'..., current block label, used for generating layer names
    '''
    eps = 1.1e-5
    nb_filter1, nb_filter2, nb_filter3 = filters
    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'
    scale_name_base = 'scale' + str(stage) + block + '_branch'

    x = Convolution2D(nb_filter1, 1, 1, name=conv_name_base + '2a', bias=False)(input_tensor)
    x = BatchNormalization(epsilon=eps, axis=bn_axis, name=bn_name_base + '2a')(x)
    x = Scale(axis=bn_axis, name=scale_name_base + '2a')(x)
    x = Activation('relu', name=conv_name_base + '2a_relu')(x)

    x = ZeroPadding2D((1, 1), name=conv_name_base + '2b_zeropadding')(x)
    x = Convolution2D(nb_filter2, kernel_size, kernel_size,
                      name=conv_name_base + '2b', bias=False)(x)
    x = BatchNormalization(epsilon=eps, axis=bn_axis, name=bn_name_base + '2b')(x)
    x = Scale(axis=bn_axis, name=scale_name_base + '2b')(x)
    x = Activation('relu', name=conv_name_base + '2b_relu')(x)

    x = Convolution2D(nb_filter3, 1, 1, name=conv_name_base + '2c', bias=False)(x)
    x = BatchNormalization(epsilon=eps, axis=bn_axis, name=bn_name_base + '2c')(x)
    x = Scale(axis=bn_axis, name=scale_name_base + '2c')(x)

    x = merge([x, input_tensor], mode='sum', name='res' + str(stage) + block)
    x = Activation('relu', name='res' + str(stage) + block + '_relu')(x)
    return x

def conv_block(input_tensor, kernel_size, filters, stage, block, strides=(2, 2)):
    '''conv_block is the block that has a conv layer at shortcut
    # Arguments
        input_tensor: input tensor
        kernel_size: defualt 3, the kernel size of middle conv layer at main path
        filters: list of integers, the nb_filters of 3 conv layer at main path
        stage: integer, current stage label, used for generating layer names
        block: 'a','b'..., current block label, used for generating layer names
    Note that from stage 3, the first conv layer at main path is with subsample=(2,2)
    And the shortcut should have subsample=(2,2) as well
    '''
    eps = 1.1e-5
    nb_filter1, nb_filter2, nb_filter3 = filters
    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'
    scale_name_base = 'scale' + str(stage) + block + '_branch'

    x = Convolution2D(nb_filter1, 1, 1, subsample=strides,
                      name=conv_name_base + '2a', bias=False)(input_tensor)
    x = BatchNormalization(epsilon=eps, axis=bn_axis, name=bn_name_base + '2a')(x)
    x = Scale(axis=bn_axis, name=scale_name_base + '2a')(x)
    x = Activation('relu', name=conv_name_base + '2a_relu')(x)

    x = ZeroPadding2D((1, 1), name=conv_name_base + '2b_zeropadding')(x)
    x = Convolution2D(nb_filter2, kernel_size, kernel_size,
                      name=conv_name_base + '2b', bias=False)(x)
    x = BatchNormalization(epsilon=eps, axis=bn_axis, name=bn_name_base + '2b')(x)
    x = Scale(axis=bn_axis, name=scale_name_base + '2b')(x)
    x = Activation('relu', name=conv_name_base + '2b_relu')(x)

    x = Convolution2D(nb_filter3, 1, 1, name=conv_name_base + '2c', bias=False)(x)
    x = BatchNormalization(epsilon=eps, axis=bn_axis, name=bn_name_base + '2c')(x)
    x = Scale(axis=bn_axis, name=scale_name_base + '2c')(x)

    shortcut = Convolution2D(nb_filter3, 1, 1, subsample=strides,
                             name=conv_name_base + '1', bias=False)(input_tensor)
    shortcut = BatchNormalization(epsilon=eps, axis=bn_axis, name=bn_name_base + '1')(shortcut)
    shortcut = Scale(axis=bn_axis, name=scale_name_base + '1')(shortcut)

    x = merge([x, shortcut], mode='sum', name='res' + str(stage) + block)
    x = Activation('relu', name='res' + str(stage) + block + '_relu')(x)
    return x

def resnet152_model(weights_path=None):
    '''Instantiate the ResNet152 architecture,
    # Arguments
        weights_path: path to pretrained weight file
    # Returns
        A Keras model instance.
    '''
    eps = 1.1e-5

    # Handle Dimension Ordering for different backends
    global bn_axis
    if K.image_dim_ordering() == 'tf':
      bn_axis = 3
      img_input = Input(shape=(224, 224, 3), name='data')
    else:
      bn_axis = 1
      img_input = Input(shape=(3, 224, 224), name='data')
            
    x = ZeroPadding2D((3, 3), name='conv1_zeropadding')(img_input)
    x = Convolution2D(64, 7, 7, subsample=(2, 2), name='conv1', bias=False)(x)
    x = BatchNormalization(epsilon=eps, axis=bn_axis, name='bn_conv1')(x)
    x = Scale(axis=bn_axis, name='scale_conv1')(x)
    x = Activation('relu', name='conv1_relu')(x)
    x = MaxPooling2D((3, 3), strides=(2, 2), name='pool1')(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_fc = AveragePooling2D((7, 7), name='avg_pool')(x)
    x_fc = Flatten()(x_fc)
    x_fc = Dense(1000, activation='softmax', name='fc1000')(x_fc)

    model = Model(img_input, x_fc)

    # load weights
    if weights_path:
      model.load_weights(weights_path, by_name=True)

    return model

if __name__ == '__main__':

  im = cv2.resize(cv2.imread('cat.jpg'), (224, 224)).astype(np.float32)

  # Remove train image mean
  im[:,:,0] -= 103.939
  im[:,:,1] -= 116.779
  im[:,:,2] -= 123.68

  if K.image_dim_ordering() == 'th':
    # Transpose image dimensions (Theano uses the channels as the 1st dimension)
    im = im.transpose((2,0,1))

    # Use pre-trained weights for Theano backend
    weights_path = 'resnet152_weights_th.h5'
  else:
    # Use pre-trained weights for Tensorflow backend
    weights_path = 'resnet152_weights_tf.h5'

  # Insert a new dimension for the batch_size
  im = np.expand_dims(im, axis=0)

  # Test pretrained model
  model = resnet152_model(weights_path)
  sgd = SGD(lr=1e-2, decay=1e-6, momentum=0.9, nesterov=True)
  model.compile(optimizer=sgd, loss='categorical_crossentropy', metrics=['accuracy'])

  out = model.predict(im)
  print np.argmax(out)

Modified version working with Keras 2.0 API
https://gist.github.com/mvoelk/ef4fc7fb905be7191cc2beb1421da37c

Great work, man!!! Many thanks for sharing the weights

Thanks for sharing weights!

I am getting this error while running the code in python3 version.

Hello! I have the same error information:

Do you have solved the problem?

learned
https://gist.github.com/flyyufelix/7e2eafb149f72f4d38dd661882c554a6#file-resnet-152_keras-py-L27

anyone solved "TypeError: call() got an unexpected keyword argument 'name'"??

Could you please time what the configuration that required to run a pre-trained ResNet152? Does one TitanX enough to handle it? Thanks.

Replace the build definition in Class Scale by the following: It will solve the problem(It is just in latest Keras format.)

def build(self, input_shape):

    self.input_spec = [InputSpec(shape=input_shape)]
    shape = (int(input_shape[self.axis]),)
    self.gamma = K.variable(self.gamma_init(shape), name='%s_gamma'%self.name)
    self.beta = K.variable(self.beta_init(shape), name='%s_beta'%self.name)
    self.trainable_weights = [self.gamma, self.beta]
    if self.initial_weights is not None:
        self.set_weights(self.initial_weights)
        del self.initial_weights

If you use cv2 to load images, then it stores as BGR. I wonder know which data format you used when you train the model.

how can I correctly load this model after saving it? I'm having problems with Scale custom-layer.

with CustomObjectScope({'Scale': Scale}):
NameError: name 'Scale' is not defined

@flyyufelix
Hi! Thanks for sharing weights!
By any chance, do you have the weights with no top? Would you mind to share it too?

thanks for share this knowledge

I load the model, but it has some error information:
Layer #24 (named "res2b_branch2a"), weight <tf.Variable 'res2b_branch2a/kernel:0' shape=(1, 1, 512, 64) dtype=float32_ref> has shape (1, 1, 512, 64), but the saved weight has shape (64, 256, 1, 1).

Hi! @flyyufelix @hellottdan
I am getting the exact same error as mentioned by @hellottdan, when I try to run the fine-tuning code. Can anybody help about this? Thanks.

Hi! @BhagyashreeGaikwad @flyyufelix @hellottdan

Did you ever figured out the issue?

Hi

I got the following error while running the code

File "C:\Users\Harrison\Anaconda3\lib\site-packages\tensorflow\python\pywrap_tensorflow.py", line 74, in
raise ImportError( msg )

ImportError: Traceback (most recent call last):
File "C:\Users\Harrison\Anaconda3\lib\site-packages\tensorflow\python\pywrap_tensorflow.py", line 58, in
from tensorflow.python.pywrap_tensorflow_internal import *
File "C:\Users\Harrison\Anaconda3\lib\site-packages\tensorflow\python\pywrap_tensorflow_internal.py", line 28, in
_pywrap_tensorflow_internal = swig_import_helper()
File "C:\Users\Harrison\Anaconda3\lib\site-packages\tensorflow\python\pywrap_tensorflow_internal.py", line 24, in swig_import_helper
_mod = imp.load_module('_pywrap_tensorflow_internal', fp, pathname, description)
File "C:\Users\Harrison\Anaconda3\lib\imp.py", line 243, in load_module
return load_dynamic(name, filename, file)
File "C:\Users\Harrison\Anaconda3\lib\imp.py", line 343, in load_dynamic
return _load(spec)
ImportError: DLL load failed: No se puede encontrar el módulo especificado.

Failed to load the native TensorFlow runtime.

friend please, how can I fix it?

It has the following errow while loading the weights.

AttributeError: Can't set the attribute "trainable_weights", likely because
it conflicts with an existing read-only @Property of the object. Please choose
a different name.
-self.trainable_weights = [self.gamma, self.beta]
self.train_weights = [self.gamma, self.beta]

Error Message

loading ResNet-152 model...Traceback (most recent call last):
File "resnet152_test.py", line 26, in
model = ResNet152()
File "/home/mike/Documents/keras_resnet_v1/resnet152.py", line 326, in ResNet152
model.load_weights(weights_path)
File "/home/mike/miniconda3/lib/python3.7/site-packages/tensorflow/python/keras/engine/training.py", line 250, in load_weights
return super(Model, self).load_weights(filepath, by_name, skip_mismatch)
File "/home/mike/miniconda3/lib/python3.7/site-packages/tensorflow/python/keras/engine/network.py", line 1266, in load_weights
hdf5_format.load_weights_from_hdf5_group(f, self.layers)
File "/home/mike/miniconda3/lib/python3.7/site-packages/tensorflow/python/keras/saving/hdf5_format.py", line 707, in load_weights_from_hdf5_group
K.batch_set_value(weight_value_tuples)
File "/home/mike/miniconda3/lib/python3.7/site-packages/tensorflow/python/keras/backend.py", line 3384, in batch_set_value
x.assign(np.asarray(value, dtype=dtype(x)))
File "/home/mike/miniconda3/lib/python3.7/site-packages/tensorflow/python/ops/resource_variable_ops.py", line 846, in assign
self._shape.assert_is_compatible_with(value_tensor.shape)
File "/home/mike/miniconda3/lib/python3.7/site-packages/tensorflow/python/framework/tensor_shape.py", line 1117, in assert_is_compatible_with
raise ValueError("Shapes %s and %s are incompatible" % (self, other))
ValueError: Shapes (112,) and (64,) are incompatible

Thanks, I have already gotten the the weights of resnet152_weights_tf.h5. I can run the script by adding the following new section of code to avoid the error of "CUDA_ERROR_OUT_OF_MEMORY"

However, there is no the weights of WEIGHTS_PATH_NO_TOP, I could not call the model with "include_top = False"

# Set the GPU limitation 
gpus = tf.config.experimental.list_physical_devices('GPU')
if gpus:
  # Restrict TensorFlow to only allocate 4GB of memory on the first GPU
  try:
    tf.config.experimental.set_virtual_device_configuration(
        gpus[0],
        [tf.config.experimental.VirtualDeviceConfiguration(memory_limit=4096)])
    logical_gpus = tf.config.experimental.list_logical_devices('GPU')
    print(len(gpus), "Physical GPUs,", len(logical_gpus), "Logical GPUs")
  except RuntimeError as e:
    # Virtual devices must be set before GPUs have been initialized
    print(e)

Where do the magic numbers come from?

im[:,:,0] -= 103.939
im[:,:,1] -= 116.779
im[:,:,2] -= 123.68

Hi, I have this error and I think I need the weight files are needed, but the files need access to google drive.

Traceback (most recent call last): File "train.py", line 21, in <module> model = resnet152_model(img_height, img_width, num_channels, num_classes) File "C:\Users\Mirzaei 09369109795\Desktop\VehDetect\CarRecognition\Car-Recognition\resnet_152.py", line 157, in resnet152_model model.load_weights(weights_path, by_name=True) File "C:\ProgramData\Anaconda3\lib\site-packages\keras\utils\traceback_utils.py", line 67, in error_handler raise e.with_traceback(filtered_tb) from None File "C:\ProgramData\Anaconda3\lib\site-packages\h5py\_hl\files.py", line 406, in __init__ fid = make_fid(name, mode, userblock_size, File "C:\ProgramData\Anaconda3\lib\site-packages\h5py\_hl\files.py", line 173, in make_fid fid = h5f.open(name, flags, fapl=fapl) File "h5py\_objects.pyx", line 54, in h5py._objects.with_phil.wrapper File "h5py\_objects.pyx", line 55, in h5py._objects.with_phil.wrapper File "h5py\h5f.pyx", line 88, in h5py.h5f.open OSError: Unable to open file (unable to open file: name = 'models/resnet152_weights_tf.h5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0)

what should I do?