The saved keras model cannot be loaded. #19899
Assignees
Labels
type:support
User is asking for help / asking an implementation question. Stackoverflow would be better suited.
Comments
|
You can follow the instruction as error message suggested to register the custom objects. Here are the multiple ways of doing it https://keras.io/guides/serialization_and_saving/#custom-objects |
sachinprasadhs
added
type:support
I've tried everything possible, but I still can't load my saved model. I made a git repository. you can please visit my code to help me. code is here : |
|
You are writing your keras custom layer but you have keras passing its own arguments like trainable or non-trainable into its layers. so you should pass the **kwargs into all the layers and models because we don't know what arguments are passing during training either you give the arguments passed onto the custom functions from outside the create_model() like these to the custom_objects in the load_model's argument or you can give them in config Method 1: class TransformerBlock(layers.Layer):
def __init__(self, embed_dim, num_heads, ff_dim, rate=0.1,**kwargs): # pass the **kwargs which takes the training = True arguments when training and False when predicting
super().__init__(**kwargs) # pass it to super so it properly flows into the orginal keras.layers.Layer
self.att = layers.MultiHeadAttention(num_heads, embed_dim)
self.ffn = keras.Sequential(
[
layers.Dense(ff_dim, activation="relu"),
layers.Dense(embed_dim),
]
)
self.layernorm1 = layers.LayerNormalization(epsilon=1e-6)
self.layernorm2 = layers.LayerNormalization(epsilon=1e-6)
self.dropout1 = layers.Dropout(rate)
self.dropout2 = layers.Dropout(rate)
def call(self, inputs):
input_shape = ops.shape(inputs)
batch_size = input_shape[0]
seq_len = input_shape[1]
causal_mask = causal_attention_mask(batch_size, seq_len, seq_len, "bool")
attention_output = self.att(inputs, inputs, attention_mask=causal_mask)
attention_output = self.dropout1(attention_output)
out1 = self.layernorm1(inputs + attention_output)
ffn_output = self.ffn(out1)
ffn_output = self.dropout2(ffn_output)
return self.layernorm2(out1 + ffn_output)
# same with TokenAndPositionEmbedding
class TokenAndPositionEmbedding(layers.Layer):
def __init__(self, maxlen, vocab_size, embed_dim,**kwargs):
super().__init__(**kwargs)
self.token_emb = layers.Embedding(input_dim=vocab_size, output_dim=embed_dim)
self.pos_emb = layers.Embedding(input_dim=maxlen, output_dim=embed_dim)
def call(self, x):
maxlen = ops.shape(x)[-1]
positions = ops.arange(0, maxlen, 1)
positions = self.pos_emb(positions)
x = self.token_emb(x)
return x + positions
the while loading you gotta all the arguments into the custom objects in load model keras.models.load_model(
"br_model.keras",
custom_objects={
"vocab_size":20000,
"maxlen":80,
"embed_dim":256,
"num_heads":4,
"feed_forward_dim":256,
"TokenAndPositionEmbedding":TokenAndPositionEmbedding,
"TransformerBlock":TransformerBlock
}
)or you could do this and avoid it passing in custom_objects class TransformerBlock(layers.Layer):
def __init__(self, embed_dim, num_heads, ff_dim, rate=0.1,**kwargs):
super().__init__(**kwargs)
self.att = layers.MultiHeadAttention(num_heads, embed_dim)
self.ffn = keras.Sequential(
[
layers.Dense(ff_dim, activation="relu"),
layers.Dense(embed_dim),
]
)
self.layernorm1 = layers.LayerNormalization(epsilon=1e-6)
self.layernorm2 = layers.LayerNormalization(epsilon=1e-6)
self.dropout1 = layers.Dropout(rate)
self.dropout2 = layers.Dropout(rate)
def call(self, inputs):
input_shape = ops.shape(inputs)
batch_size = input_shape[0]
seq_len = input_shape[1]
causal_mask = causal_attention_mask(batch_size, seq_len, seq_len, "bool")
attention_output = self.att(inputs, inputs, attention_mask=causal_mask)
attention_output = self.dropout1(attention_output)
out1 = self.layernorm1(inputs + attention_output)
ffn_output = self.ffn(out1)
ffn_output = self.dropout2(ffn_output)
return self.layernorm2(out1 + ffn_output)
def get_config(self):
config = super().get_config().copy()
config.update(
{
"embed_dim":self.att.key_dim,
"num_heads": self.at.num_heads,
"ff_dim": self.ffn.layers[0].units,
"rate": self.dropout1.rate,
}
)
return config
@classmethod
def from_config(cls,config):
return cls(**config)
class TokenAndPositionEmbedding(layers.Layer):
def __init__(self, maxlen, vocab_size, embed_dim,**kwargs):
super().__init__(**kwargs)
self.token_emb = layers.Embedding(input_dim=vocab_size, output_dim=embed_dim)
self.pos_emb = layers.Embedding(input_dim=maxlen, output_dim=embed_dim)
def call(self, x):
maxlen = ops.shape(x)[-1]
positions = ops.arange(0, maxlen, 1)
positions = self.pos_emb(positions)
x = self.token_emb(x)
return x + positions
def get_config(self):
config = super().get_config().copy()
config.update(
{
"maxlen": self.pos_emb.input_dim,
"vocab_size": self.token_emb.input_dim,
"embed_dim": self.token_emb.output_dim
}
)
return config
@classmethod
def from_config(cls,config):
return cls(**config)and when loading model keras.models.load_model(
"br_model.keras",
custom_objects={
"TokenAndPositionEmbedding":TokenAndPositionEmbedding,
"TransformerBlock":TransformerBlock
}
)See whether this solves it |
Thank you very so much. It's working. |
|
brother close this as completed. Thank you. |
|
Is it possible to use the Keras register_serializable decorator here and avoid using the custom scope? |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
After training I saved my model. and I can't load. I tried everything, but it always gives me a
custom_objects errorI based myself on the GPT miniature code in the doc
code:
### Now, when i try to load my model:
I'm getting this errors:
version
The text was updated successfully, but these errors were encountered: