我正在使用 opencv 和 imageai 来训练一个简单的对象检测模型。当我去推理时，我看到了很多Skipping loading of weights for layer ... due to mismatch in shape
我将该消息跟踪到此文件：miniforge3/lib/python3.9/site-packages/tensorflow/python/keras/saving/hdf5_format.py. 相关的代码块如下：
def load_weights_from_hdf5_group_by_name(
f, layers, skip_mismatch=False):
"""Implements name-based weight loading.
(instead of topological weight loading).
Layers that have no matching name are skipped.
Args:
f: A pointer to a HDF5 group.
layers: a list of target layers.
skip_mismatch: Boolean, whether to skip loading of layers
where there is a mismatch in the number of weights,
or a mismatch in the shape of the weights.
Raises:
ValueError: in case of mismatch between provided layers
and weights file and skip_match=False.
"""
if 'keras_version' in f.attrs:
original_keras_version = f.attrs['keras_version']
if hasattr(original_keras_version, 'decode'):
original_keras_version = original_keras_version.decode('utf8')
else:
original_keras_version = '1'
if 'backend' in f.attrs:
original_backend = f.attrs['backend']
if hasattr(original_backend, 'decode'):
original_backend = original_backend.decode('utf8')
else:
original_backend = None
# New file format.
layer_names = load_attributes_from_hdf5_group(f, 'layer_names')
# Reverse index of layer name to list of layers with name.
index = {}
for layer in layers:
if layer.name:
index.setdefault(layer.name, []).append(layer)
# We batch weight value assignments in a single backend call
# which provides a speedup in TensorFlow.
weight_value_tuples = []
for k, name in enumerate(layer_names):
g = f[name]
weight_names = load_attributes_from_hdf5_group(g, 'weight_names')
weight_values = [np.asarray(g[weight_name]) for weight_name in weight_names]
for layer in index.get(name, []):
symbolic_weights = _legacy_weights(layer)
weight_values = preprocess_weights_for_loading(
layer, weight_values, original_keras_version, original_backend)
print( 'layer name', name, 'sw', len(symbolic_weights), 'wv', len(weight_values) )
if len(weight_values) != len(symbolic_weights):
if skip_mismatch:
logging.warning('Skipping loading of weights for '
'layer {}'.format(layer.name) + ' due to mismatch '
'in number of weights ({} vs {}).'.format(
len(symbolic_weights), len(weight_values)))
continue
raise ValueError('Layer #' + str(k) + ' (named "' + layer.name +
'") expects ' + str(len(symbolic_weights)) +
' weight(s), but the saved weights' + ' have ' +
str(len(weight_values)) + ' element(s).')
# Set values.
for i in range(len(weight_values)):
if backend.int_shape(symbolic_weights[i]) != weight_values[i].shape:
if skip_mismatch:
logging.warning('Skipping loading of weights for '
'layer {}'.format(layer.name) + ' due to '
'mismatch in shape ({} vs {}).'.format(
symbolic_weights[i].shape,
weight_values[i].shape))
continue
raise ValueError('Layer #' + str(k) +' (named "' + layer.name +
'"), weight ' + str(symbolic_weights[i]) +
' has shape {}'.format(backend.int_shape(
symbolic_weights[i])) +
', but the saved weight has shape ' +
str(weight_values[i].shape) + '.')
else:
weight_value_tuples.append((symbolic_weights[i], weight_values[i]))
backend.batch_set_value(weight_value_tuples)
这条线让我感兴趣：
symbolic_weights = _legacy_weights(layer)
weight_values = preprocess_weights_for_loading(
layer, weight_values, original_keras_version, original_backend)
为什么两个重量不匹配？我使用的是预训练模型 (YOLOv3)，但如果我不使用预训练模型，也会出现此问题。
由于 1-71 范围内的不匹配而未跳过的唯一权重：
- 批处理规范化_59
- conv2d_62
- conv2d_63
- conv2d_64
- conv2d_68