时间戳

首页 > 解决方案 > Keras：load_model ValueError：轴与数组不匹配

python - Keras：load_model ValueError：轴与数组不匹配

问题描述

我正在用我自己的数据集使用keras-gan/wgan-gp示例研究 gan。我保存模型 wgan.generator.save('generator.h5')

wgan.critic.save('critic.h5')

并加载

model = load_model('generator.h5')

model = load_model('critic.h5')

但这仅在第一次运行时效果很好。当我在第二次训练后再次保存模型并运行时

model = load_model('generator.h5')

model = load_model('critic.h5')

再次出现错误：</p>

() ----> 1 model = load_model('generator.h5') 中的 ValueError Traceback (最近一次调用最后一次)

D:\keras\engine\saving.py in load_model(filepath, custom_objects, compile) 262 263 # set weights --> 264 load_weights_from_hdf5_group(f['model_weights'], model.layers) 265 266 if compile:

D:\keras\engine\saving.py in load_weights_from_hdf5_group(f, layers, reshape) 914 original_keras_version, 915 original_backend, --> 916 reshape=reshape) 917 if len(weight_values) != len(symbolic_weights): 918 raise ValueError( '图层#' + str(k) +

D:\keras\engine\saving.py 在 preprocess_weights_for_loading(layer, weights, original_keras_version, original_backend, reshape) 555 weights = convert_nested_time_distributed(weights) 556 elif 层。类。['Model', 'Sequential'] 中的名称：-> 557 weights = convert_nested_model(weights) 558 559 if original_keras_version == '1'：

D:\keras\engine\saving.py in convert_nested_model(weights) 543 weights=weights[:num_weights], 544 original_keras_version=original_keras_version, --> 545 original_backend=original_backend)) 546 weights = weights[num_weights:] 547 return new_weights

D:\keras\engine\saving.py 在 preprocess_weights_for_loading(layer, weights, original_keras_version, original_backend, reshape) 555 weights = convert_nested_time_distributed(weights) 556 elif 层。类。['Model', 'Sequential'] 中的名称：-> 557 weights = convert_nested_model(weights) 558 559 if original_keras_version == '1'：

D:\keras\engine\saving.py in convert_nested_model(weights) 531 weights=weights[:num_weights], 532 original_keras_version=original_keras_version, --> 533 original_backend=original_backend)) 534 weights = weights[num_weights:] 535

D:\keras\engine\saving.py 在 preprocess_weights_for_loading(layer, weights, original_keras_version, original_backend, reshape) 673 weights[0] = np.reshape(weights[0], layer_weights_shape) 674 elif layer_weights_shape != weights[0]。形状： --> 675 weights[0] = np.transpose(weights[0], (3, 2, 0, 1)) 676 if layer. 类。name == 'ConvLSTM2D': 677 个权重1 = np.transpose(weights 1 , (3, 2, 0, 1))

c:\users\administrator\appdata\local\programs\python\python35\lib\site-packages\numpy\core\fromnumeric.py in transpose(a, axes) 596 597 """ --> 598 return _wrapfunc(a ，'转置'，轴）599 600

c:\users\administrator\appdata\local\programs\python\python35\lib\site-packages\numpy\core\fromnumeric.py in _wrapfunc(obj, method, *args, **kwds) 49 def _wrapfunc(obj, method, *args, **kwds): 50 try: ---> 51 return getattr(obj, method)(*args, **kwds) 52 53 # 如果对象没有 AttributeError

ValueError：轴与数组不匹配`

我正在使用

Python 3.5.3

Keras 2.2.2

h5py 2.8.0

tensorflow-gpu 1.9.0

keras-contrib 2.0.8

Keras-Applications 1.0.4

Keras-Preprocessing 1.0.2

任何意见和建议将不胜感激。

标签： pythonkerasdeep-learning

解决方案

看起来像中描述的问题：

https://github.com/keras-team/keras/pull/11847

和

https://github.com/tensorflow/tensorflow/issues/27769

虽然该错误尚未修复，但仅当模型中同时存在可训练和不可训练权重时才会出现问题。如果您不需要进一步训练模型，您可以通过在保存之前冻结所有权重来解决此问题：

from keras import models

def freeze(model):
    """Freeze model weights in every layer."""
    for layer in model.layers:
        layer.trainable = False

        if isinstance(layer, models.Model):
            freeze(layer)

推荐阅读