我现在第二次遇到了旧的Keras代码的某个问题，并且想知道如何正确解决这些问题。发生的情况是，旧的Keras模型无法再使用model.load_weights（）函数从h5文件中加载权重，我认为这可能是由于当今Keras中某些最后层的工作方式发生了一些变化
这是我正在谈论的实际错误，如果我对上述理论有误，请告诉我：
对于此应用程序https://github.com/manideep2510/eye-in-the-sky，当我运行https://github.com/manideep2510/eye-in-the-sky/blob/master/test_unet.py时出现此错误：
File "/home/user/neuralnets/ENV/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 1626, in _create_c_op
c_op = c_api.TF_FinishOperation(op_desc)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Dimension 0 in both shapes must be equal, but are 1 and 9. Shapes are [1,1,16,3] and [9,16,1,1]. for 'Assign_82' (op: 'Assign') with input shapes: [1,1,16,3], [9,16,1,1].
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "test_unet.py", line 438, in <module>
pred_train_13, Y_gt_train_13, pred_val_all, Y_gt_val = testing_diffsizes(model, x_train, y_train, x_val, y_val, weights_file = "model_onehot.h5")
File "test_unet.py", line 395, in testing_diffsizes
model.load_weights(weights_file)
File "/home/user/neuralnets/ENV/lib/python3.5/site-packages/keras/engine/network.py", line 1166, in load_weights
f, self.layers, reshape=reshape)
File "/home/user/neuralnets/ENV/lib/python3.5/site-packages/keras/engine/saving.py", line 1058, in load_weights_from_hdf5_group
K.batch_set_value(weight_value_tuples)
File "/home/user/neuralnets/ENV/lib/python3.5/site-packages/keras/backend/tensorflow_backend.py", line 2465, in batch_set_value
assign_op = x.assign(assign_placeholder)
File "/home/user/neuralnets/ENV/lib/python3.5/site-packages/tensorflow/python/ops/variables.py", line 1493, in assign
name=name)
File "/home/user/neuralnets/ENV/lib/python3.5/site-packages/tensorflow/python/ops/state_ops.py", line 221, in assign
validate_shape=validate_shape)
File "/home/user/neuralnets/ENV/lib/python3.5/site-packages/tensorflow/python/ops/gen_state_ops.py", line 61, in assign
use_locking=use_locking, name=name)
File "/home/user/neuralnets/ENV/lib/python3.5/site-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
op_def=op_def)
File "/home/user/neuralnets/ENV/lib/python3.5/site-packages/tensorflow/python/util/deprecation.py", line 488, in new_func
return func(*args, **kwargs)
File "/home/user/neuralnets/ENV/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 3272, in create_op
op_def=op_def)
File "/home/user/neuralnets/ENV/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 1790, in __init__
control_input_ops)
File "/home/user/neuralnets/ENV/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 1629, in _create_c_op
raise ValueError(str(e))
ValueError: Dimension 0 in both shapes must be equal, but are 1 and 9. Shapes are [1,1,16,3] and [9,16,1,1]. for 'Assign_82' (op: 'Assign') with input shapes: [1,1,16,3], [9,16,1,1].
如何在代码中编译模型：
def UNet(shape = (None,None,4)):
# Left side of the U-Net
inputs = Input(shape)
# in_shape = inputs.shape
# print(in_shape)
conv1 = Conv2D(64, 3, activation = 'relu', padding = 'same', kernel_initializer = 'random_normal')(inputs)
conv1 = Conv2D(64, 3, activation = 'relu', padding = 'same', kernel_initializer = 'random_normal')(conv1)
conv1 = BatchNormalization()(conv1)
pool1 = MaxPooling2D(pool_size=(2, 2))(conv1)
conv2 = Conv2D(128, 3, activation = 'relu', padding = 'same', kernel_initializer = 'random_normal')(pool1)
conv2 = Conv2D(128, 3, activation = 'relu', padding = 'same', kernel_initializer = 'random_normal')(conv2)
conv2 = BatchNormalization()(conv2)
pool2 = MaxPooling2D(pool_size=(2, 2))(conv2)
conv3 = Conv2D(256, 3, activation = 'relu', padding = 'same', kernel_initializer = 'random_normal')(pool2)
conv3 = Conv2D(256, 3, activation = 'relu', padding = 'same', kernel_initializer = 'random_normal')(conv3)
conv3 = BatchNormalization()(conv3)
pool3 = MaxPooling2D(pool_size=(2, 2))(conv3)
conv4 = Conv2D(512, 3, activation = 'relu', padding = 'same', kernel_initializer = 'random_normal')(pool3)
conv4 = Conv2D(512, 3, activation = 'relu', padding = 'same', kernel_initializer = 'random_normal')(conv4)
conv4 = BatchNormalization()(conv4)
drop4 = Dropout(0.5)(conv4)
pool4 = MaxPooling2D(pool_size=(2, 2))(drop4)
# Bottom of the U-Net
conv5 = Conv2D(1024, 3, activation = 'relu', padding = 'same', kernel_initializer = 'random_normal')(pool4)
conv5 = Conv2D(1024, 3, activation = 'relu', padding = 'same', kernel_initializer = 'random_normal')(conv5)
conv5 = BatchNormalization()(conv5)
drop5 = Dropout(0.5)(conv5)
# Upsampling Starts, right side of the U-Net
up6 = Conv2D(512, 2, activation = 'relu', padding = 'same', kernel_initializer = 'random_normal')(UpSampling2D(size = (2,2))(drop5))
merge6 = concatenate([drop4,up6], axis = 3)
conv6 = Conv2D(512, 3, activation = 'relu', padding = 'same', kernel_initializer = 'random_normal')(merge6)
conv6 = Conv2D(512, 3, activation = 'relu', padding = 'same', kernel_initializer = 'random_normal')(conv6)
conv6 = BatchNormalization()(conv6)
up7 = Conv2D(256, 2, activation = 'relu', padding = 'same', kernel_initializer = 'random_normal')(UpSampling2D(size = (2,2))(conv6))
merge7 = concatenate([conv3,up7], axis = 3)
conv7 = Conv2D(256, 3, activation = 'relu', padding = 'same', kernel_initializer = 'random_normal')(merge7)
conv7 = Conv2D(256, 3, activation = 'relu', padding = 'same', kernel_initializer = 'random_normal')(conv7)
conv7 = BatchNormalization()(conv7)
up8 = Conv2D(128, 2, activation = 'relu', padding = 'same', kernel_initializer = 'random_normal')(UpSampling2D(size = (2,2))(conv7))
merge8 = concatenate([conv2,up8], axis = 3)
conv8 = Conv2D(128, 3, activation = 'relu', padding = 'same', kernel_initializer = 'random_normal')(merge8)
conv8 = Conv2D(128, 3, activation = 'relu', padding = 'same', kernel_initializer = 'random_normal')(conv8)
conv8 = BatchNormalization()(conv8)
up9 = Conv2D(64, 2, activation = 'relu', padding = 'same', kernel_initializer = 'random_normal')(UpSampling2D(size = (2,2))(conv8))
merge9 = concatenate([conv1,up9], axis = 3)
conv9 = Conv2D(64, 3, activation = 'relu', padding = 'same', kernel_initializer = 'random_normal')(merge9)
conv9 = Conv2D(64, 3, activation = 'relu', padding = 'same', kernel_initializer = 'random_normal')(conv9)
conv9 = Conv2D(16, 3, activation = 'relu', padding = 'same', kernel_initializer = 'random_normal')(conv9)
conv9 = BatchNormalization()(conv9)
# Output layer of the U-Net with a softmax activation
conv10 = Conv2D(3, 1, activation = 'softmax')(conv9)
model = Model(input = inputs, output = conv10)
model.compile(optimizer = Adam(lr = 0.000001), loss = 'categorical_crossentropy', metrics = ['accuracy', iou])
model.summary()
#filelist_modelweights = sorted(glob.glob('*.h5'), key=numericalSort)
#if 'model_nocropping.h5' in filelist_modelweights:
# model.load_weights('model_nocropping.h5')
return model
对我来说，问题似乎是在conv层9之后出现的。有人可以告诉我如何修复此错误，以及是什么引起的吗？
感谢您的宝贵时间， -S