属性错误：“嵌入”对象没有属性“嵌入” - TensorFlow 和 Keras

Question

好吧，我有一个 keras 模型，我完全运行了它，然后用这行代码保存了权重：

model.save_weights("rho_beta_true_tf", save_format="tf")

然后在另一个文件中，我仅构建模型，然后使用此行从上面运行的模型加载权重：

model_build.load_weights("rho_beta_true_tf")

当我去调用某些属性时，所有内容都会正确显示，除非我尝试运行此行：

model_build.stimuli.embeddings 

或

model_build.stimuli.embeddings.numpy()[0]

我收到属性错误：

AttributeError: 'Embedding' object has no attribute 'embeddings'

这条线应该返回一个张量，如果我到目前为止调用任何其他属性它会起作用，所以我不确定它是否只是找不到张量或者问题是否是其他问题。有人可以帮我弄清楚如何解决这个属性错误吗？

Answer 1

尝试使用

.get_weights()

:

model_build.stimuli.get_weights()

Answer 2

事实证明，因为我已将权重保存为 tf 格式，所以我必须遵循张量流文档中的此步骤：

对于继承自 tf.keras.Model 的用户定义类，必须将 Layer 实例分配给对象属性，通常在构造函数中。

那么接下来的路线

build_model.stimuli.embedding(put the directory path to your custom embedding layer here)

成功了！

Answer 3

import torch
import torch.nn as nn
import torch.nn.functional as F

# Definition of a basic neural network class
class SimpleBrokenModel(nn.Module):
    def __init__(self, config=MASTER_CONFIG):
        super(SimpleBrokenModel, self).__init__()  # Inherit from nn.Module
        # Rest of the code ...

    # Forward pass function for the base model
    def forward(self, idx, targets=None):
        # Embedding layer converts character indices to vectors
        x = self.embedding(idx)

        # Linear layers for modeling relationships between features
        a = self.linear(x)

        # Apply softmax activation to obtain probability distribution
        logits = F.softmax(a, dim=-1)

        # If targets are provided, calculate and return the cross-entropy loss
        if targets is not None:
            # Reshape logits and targets for cross-entropy calculation
            loss = F.cross_entropy(logits.view(-1, self.config['vocab_size']), targets.view(-1))
            return logits, loss
        # If targets are not provided, return the logits
        else:
            return logits

# Update MASTER_CONFIG with the dimension of linear layers (128)
MASTER_CONFIG.update({
    'd_model': 128,
})

# Instantiate the SimpleBrokenModel using the updated MASTER_CONFIG
model = SimpleBrokenModel(MASTER_CONFIG)

# Print the total number of parameters in the model
print("Total number of parameters in the Simple Neural Network Model:", sum([m.numel() for m in model.parameters()]))
for the above code im getting error please help me...

# Obtain batches for training using the specified batch size and context window
xs, ys = get_batches(dataset, 'train', MASTER_CONFIG['batch_size'], MASTER_CONFIG['context_window'])

# Calculate logits and loss using the model
logits, loss = model(xs, ys)`enter code here`