keras读取h5文件load_weights、load代码操作

import keras
from keras.preprocessing import image
import numpy as np

from network.resnet50 import ResNet50
#修改过，不加载权重（默认官方加载亦可）
model = ResNet50() 

# 参数默认 by_name = Fasle， 否则只读取匹配的权重
# 这里h5的层和权重文件中层名是对应的（除input层）
model.load_weights(r'\models\resnet50_weights_tf_dim_ordering_tf_kernels_v2.h5') 

def load_weights(self, filepath, by_name=False, skip_mismatch=False, reshape=False):
 if h5py is None:
  raise ImportError('`load_weights` requires h5py.')
 with h5py.File(filepath, mode='r') as f:
  if 'layer_names' not in f.attrs and 'model_weights' in f:
   f = f['model_weights']
  if by_name:
   saving.load_weights_from_hdf5_group_by_name(
    f, self.layers, skip_mismatch=skip_mismatch,reshape=reshape)
  else:
   saving.load_weights_from_hdf5_group(f, self.layers, reshape=reshape)

def load_weights_from_hdf5_group(f, layers, reshape=False):
 # keras模型resnet50的model.layers的过滤
 # 仅保留layer.weights不为空的层，过滤掉无学习参数的层
 filtered_layers = []
 for layer in layers:
  weights = layer.weights
  if weights:
   filtered_layers.append(layer)

>>> f
<HDF5 file "resnet50_weights_tf_dim_ordering_tf_kernels_v2.h5" (mode r)>

>>> f.filename
'E:\\DeepLearning\\keras_test\\models\\resnet50_weights_tf_dim_ordering_tf_kernels_v2.h5'

>>> f.name  
'/'

>>> f.attrs.keys()   # f属性列表 #
<KeysViewHDF5 ['layer_names']>

>>> f.keys() #无顺序
<KeysViewHDF5 ['activation_1', 'activation_10', 'activation_11', 'activation_12', 
...,'activation_8', 'activation_9', 'avg_pool', 'bn2a_branch1', 'bn2a_branch2a', 
...,'res5c_branch2a', 'res5c_branch2b', 'res5c_branch2c', 'zeropadding2d_1']>

>>> f.attrs['layer_names']  #*** 有顺序, 和summary()对应 ****
array([b'input_1', b'zeropadding2d_1', b'conv1', b'bn_conv1',
  b'activation_1', b'maxpooling2d_1', b'res2a_branch2a',
  ..., b'res2a_branch1', b'bn2a_branch2c', b'bn2a_branch1', 
  b'merge_1', b'activation_47', b'res5c_branch2b', b'bn5c_branch2b',
  ..., b'activation_48', b'res5c_branch2c', b'bn5c_branch2c', 
  b'merge_16', b'activation_49', b'avg_pool', b'flatten_1', b'fc1000'],
  dtype='|S15')

>>> f['input_1']
<HDF5 group "/input_1" (0 members)>

>>> f['input_1'].attrs.keys() # 在keras中，每一个层都有‘weight_names'属性 #
<KeysViewHDF5 ['weight_names']>

>>> f['input_1'].attrs['weight_names'] # input层无权重 #
array([], dtype=float64)

>>> f['conv1']
<HDF5 group "/conv1" (2 members)>

>>> f['conv1'].attrs.keys()
<KeysViewHDF5 ['weight_names']>

>>> f['conv1'].attrs['weight_names'] # conv层有权重w、b #
array([b'conv1_W:0', b'conv1_b:0'], dtype='|S9')

 # 获取后hdf5文本文件中层的名字，顺序对应
 layer_names = load_attributes_from_hdf5_group(f, 'layer_names')
 #上一句实现 layer_names = [n.decode('utf8') for n in f.attrs['layer_names']]
 filtered_layer_names = []
 for name in layer_names:
  g = f[name]
  weight_names = load_attributes_from_hdf5_group(g, 'weight_names')
  #上一句实现 weight_names = [n.decode('utf8') for n in f[name].attrs['weight_names']]
  #保留有权重层的名字
  if weight_names:
   filtered_layer_names.append(name)
 layer_names = filtered_layer_names
 # 验证模型中有有权重tensor的层 与 从h5中读取有权重层名字的 数量 保持一致。
 if len(layer_names) != len(filtered_layers):
  raise ValueError('You are trying to load a weight file '
       'containing ' + str(len(layer_names)) +
       ' layers into a model with ' +
       str(len(filtered_layers)) + ' layers.')

>>> f['conv1']['conv1_W:0'] # conv1_W:0 权重数据数据集
<HDF5 dataset "conv1_W:0": shape (7, 7, 3, 64), type "<f4">

>>> f['conv1']['conv1_W:0'].value # conv1_W:0 权重数据的值， 是一个标准的4d array
array([[[[ 2.82526277e-02, -1.18737184e-02, 1.51488732e-03, ...,
   -1.07003953e-02, -5.27982824e-02, -1.36667420e-03],
   [ 5.86827798e-03, 5.04415408e-02, 3.46324709e-03, ...,
   1.01423981e-02, 1.39493728e-02, 1.67549420e-02],
   [-2.44090753e-03, -4.86173332e-02, 2.69966386e-03, ...,
   -3.44439060e-04, 3.48098315e-02, 6.28910400e-03]],
  [[ 1.81872323e-02, -7.20698107e-03, 4.80302610e-03, ...,
 …. ]]]])

>>> conv1_w = np.asarray(f['conv1']['conv1_W:0']) # 直接转换成numpy格式 
>>> conv1_w.shape
(7, 7, 3, 64)

# 卷积层
>>> filtered_layers[0]
<keras.layers.convolutional.Conv2D object at 0x000001F7487C0E10>

>>> filtered_layers[0].name
'conv1'

>>> filtered_layers[0].input
<tf.Tensor 'conv1_pad/Pad:0' shape=(?, 230, 230, 3) dtype=float32>

#卷积层权重数据
>>> filtered_layers[0].weights
[<tf.Variable 'conv1/kernel:0' shape=(7, 7, 3, 64) dtype=float32_ref>, 
 <tf.Variable 'conv1/bias:0' shape=(64,) dtype=float32_ref>]

weight_value_tuples = []
# 枚举过滤后的层
for k, name in enumerate(layer_names):
 g = f[name]
 weight_names = load_attributes_from_hdf5_group(g, 'weight_names')
 # 获取文件中当前层的权重数据list， 数据类型转换为numpy array 
 weight_values = [np.asarray(g[weight_name]) for weight_name in weight_names]
 # 获取keras模型中层具有的权重数据tf.Variable个数
 layer = filtered_layers[k]
 symbolic_weights = layer.weights
 # 权重数据预处理
 weight_values = preprocess_weights_for_loading(layer, weight_values,
       original_keras_version, original_backend,reshape=reshape)
 # 验证权重数据、tf.Variable数据是否相同
 if len(weight_values) != len(symbolic_weights):
  raise ValueError('Layer #' + str(k) + '(named "' + layer.name + 
    '" in the current model) was found to correspond to layer ' + name + 
    ' in the save file. However the new layer ' + layer.name + ' expects ' + 
    str(len(symbolic_weights)) + 'weights, but the saved weights have ' + 
    str(len(weight_values)) + ' elements.')
 # tf.Variable 和 权重数据 打包
 weight_value_tuples += zip(symbolic_weights, weight_values)

def batch_set_value(tuples):
 if tuples:
  assign_ops = []
  feed_dict = {}
  for x, value in tuples: 
   # 获取权重数据类型  
   value = np.asarray(value, dtype=dtype(x))
   tf_dtype = tf.as_dtype(x.dtype.name.split('_')[0])
   if hasattr(x, '_assign_placeholder'):
    assign_placeholder = x._assign_placeholder
    assign_op = x._assign_op
   else:
    # 权重的tf.placeholder
    assign_placeholder = tf.placeholder(tf_dtype, shape=value.shape)
    # 对权重变量Tensor的赋值 assign的operation
    assign_op = x.assign(assign_placeholder)
    x._assign_placeholder = assign_placeholder # 用处?
    x._assign_op = assign_op     # 用处?
   assign_ops.append(assign_op)
   feed_dict[assign_placeholder] = value
  # 利用tensorflow的tf.Session().run()对tensor进行assign批次赋值
  get_session().run(assign_ops, feed_dict=feed_dict)

>>> ff
<HDF5 file "res50_model.h5" (mode r)>

>>> ff.attrs.keys()
<KeysViewHDF5 ['backend', 'keras_version', 'model_config']>

>>> ff.keys()
<KeysViewHDF5 ['model_weights']>

>>> ff['model_weights'].attrs.keys() ## ff['model_weights']有三个属性
<KeysViewHDF5 ['backend', 'keras_version', 'layer_names']>

>>> ff['model_weights'].keys() ## 无顺序
<KeysViewHDF5 ['activation_1', 'activation_10', 'activation_11', 'activation_12', 
 …, 'avg_pool', 'bn2a_branch1', 'bn2a_branch2a', 'bn2a_branch2b', 
 …, 'bn5c_branch2c', 'bn_conv1', 'conv1', 'conv1_pad', 'fc1000', 'input_1', 
 …, 'c_branch2a', 'res5c_branch2b', 'res5c_branch2c']>

>>> ff['model_weights'].attrs['layer_names'] ## 有顺序
array([b'input_1', b'conv1_pad', b'conv1', b'bn_conv1', b'activation_1',
  b'pool1_pad', b'max_pooling2d_1', b'res2a_branch2a',
  b'bn2a_branch2a', b'activation_2', b'res2a_branch2b',
 ... 省略
  b'activation_48', b'res5c_branch2c', b'bn5c_branch2c', b'add_16',
  b'activation_49', b'avg_pool', b'fc1000'], dtype='|S15')

def load_model(filepath, custom_objects=None, compile=True):
 if h5py is None:
  raise ImportError('`load_model` requires h5py.')
 model = None
 opened_new_file = not isinstance(filepath, h5py.Group)
 # h5加载后转换为一个 h5dict 类，编译通过键取值
 f = h5dict(filepath, 'r')
 try:
  # 序列化并compile
  model = _deserialize_model(f, custom_objects, compile)
 finally:
  if opened_new_file:
   f.close()
 return model

# 从h5中读取网络结构的json描述字符串
model_config = f['model_config']
model_config = json.loads(model_config.decode('utf-8'))
# 根据json构建网络模型结构
model = model_from_config(model_config, custom_objects=custom_objects)

# 获取有顺序的网络层名, 网络层
model_weights_group = f['model_weights']
layer_names = model_weights_group['layer_names'] 
layers = model.layers
# 过滤 有权重Tensor的层
for layer in layers:
 weights = layer.weights
 if weights:
  filtered_layers.append(layer)
# 过滤有权重的数据
filtered_layer_names = []
for name in layer_names:
 layer_weights = model_weights_group[name]
 weight_names = layer_weights['weight_names']
 if weight_names:
  filtered_layer_names.append(name)
# 打包数据 weight_value_tuples
weight_value_tuples = []
for k, name in enumerate(layer_names):
 layer_weights = model_weights_group[name]
 weight_names = layer_weights['weight_names']
 weight_values = [layer_weights[weight_name] for weight_name in weight_names]
 layer = filtered_layers[k]
 symbolic_weights = layer.weights
 weight_values = preprocess_weights_for_loading(...)
 weight_value_tuples += zip(symbolic_weights, weight_values) 
# 批写入 
K.batch_set_value(weight_value_tuples)

if compile:
 training_config = f.get('training_config')
 if training_config is None:
 warnings.warn('No training configuration found in save file: '
     'the model was *not* compiled. Compile it manually.')
  return model
 training_config = json.loads(training_config.decode('utf-8'))
 optimizer_config = training_config['optimizer_config']
 optimizer = optimizers.deserialize(optimizer_config, custom_objects=custom_objects)
 # Recover loss functions and metrics.
 loss = convert_custom_objects(training_config['loss'])
 metrics = convert_custom_objects(training_config['metrics'])
 sample_weight_mode = training_config['sample_weight_mode']
 loss_weights = training_config['loss_weights']
 # Compile model.
 model.compile(optimizer=optimizer, loss=loss, metrics=metrics,
   loss_weights=loss_weights, sample_weight_mode=sample_weight_mode)
 # Set optimizer weights.
 if 'optimizer_weights' in f:
  # Build train function (to get weight updates).
  model._make_train_function()
  optimizer_weights_group = f['optimizer_weights']
  optimizer_weight_names = [ 
   n.decode('utf8') for n in ptimizer_weights_group['weight_names']]
  optimizer_weight_values = [
   optimizer_weights_group[n] for n in optimizer_weight_names]
  try:
   model.optimizer.set_weights(optimizer_weight_values)
  except ValueError:
   warnings.warn('Error in loading the saved optimizer state. As a result,'
    'your model is starting with a freshly initialized optimizer.')