I'm building a model using tf.keras.models.Sequential and saving it as a SavedModel object which contains a saved_model.pb file. The model is then going to be used in a C# service using ML.net.
Here is the code (pulled and adapted from docs)
(train_images, train_labels), (test_images, test_labels) = tf.keras.datasets.mnist.load_data()
train_labels = train_labels[:1000]
test_labels = test_labels[:1000]
train_images = train_images[:1000].reshape(-1, 28 * 28) / 255.0
test_images = test_images[:1000].reshape(-1, 28 * 28) / 255.0
# Define a simple sequential model
def create_model():
model = tf.keras.models.Sequential([
keras.layers.Dense(512, activation='relu', input_shape=(784,)),
keras.layers.Dropout(0.2),
keras.layers.Dense(10)
])
model.compile(optimizer='adam',
loss=tf.losses.SparseCategoricalCrossentropy(from_logits=True),
metrics=['accuracy'])
return model
# Create a basic model instance
model = create_model()
model.fit(train_images, train_labels, epochs=5)
# Save model
#model.save('/Users/fco/Desktop/saved_model/test.h5', save_format='tf')
tf.saved_model.save(model, '/Users/fco/Desktop/saved_model')
# Load model
new_model = tf.keras.models.load_model('/Users/fco/Desktop/saved_model')
print(new_model.predict(test_images).shape)
When loading the saved_model.pb file in ML.NET I get the following exception.
TensorflowException: Invalid GraphDef
When I search for this error - it references freezing weights on model, but the solutions are for TF1. TF2 seems to have a more streamlined method of saving model, but I cannot understand what is wrong.
Does anyone know what I'm missing?
I don't know answer for you problem but you can save your model in .h5 format and load it easily.
Example:
save your model using
model.save('/content/saved_model.h5')
and load it using
loaded_model= models.load_model('/content/saved_model.h5')
Related
I am new to Tensorflow and Keras. I just started beginning my Deep learning Journey. I installed Tensorflow 2.4.3 as well as Keras. I was learning Tensorboard. I created a model for imdb dataset as follows
import tensorflow as tf
import keras
from tensorflow.keras import *
from tensorflow.keras.datasets import imdb
from tensorflow.keras.preprocessing import sequence
## model making
max_features = 2000
max_len = 500
(x_train, y_train), (x_test, y_test) = imdb.load_data(num_words=max_features)
x_train = sequence.pad_sequences(x_train, maxlen=max_len)
x_test = sequence.pad_sequences(x_test, maxlen=max_len)
model = models.Sequential()
model.add(layers.Embedding(max_features, 128,
input_length=max_len,
name='embed'))
model.add(layers.Conv1D(32, 7, activation='relu'))
model.add(layers.MaxPooling1D(5))
model.add(layers.Conv1D(32, 7, activation='relu'))
model.add(layers.GlobalMaxPooling1D())
model.add(layers.Dense(1))
model.summary()
model.compile(optimizer='rmsprop',
loss='binary_crossentropy',
metrics=['acc'])
I used the tensorboard callback here.
callbacks = [
keras.callbacks.TensorBoard(
log_dir='my_log_dir',
histogram_freq=1,
embeddings_freq=1,
)
]
history = model.fit(x_train, y_train,
epochs=3,
batch_size=128,
validation_split=0.2,
callbacks=callbacks)
Then I got the following warning.
C:\Users\ktripat\Anaconda3\envs\tf2\lib\site-packages\keras\callbacks\tensorboard_v2.py:102: UserWarning: The TensorBoard callback does not support embeddings display when using TensorFlow 2.0. Embeddings-related arguments are ignored.
warnings.warn('The TensorBoard callback does not support.'
Please find any solution if you guys have any. Thank you in advance!
You will need to follow this guide.
It describes how to save the weights of your embedding layer in a way that you can visualize it in TensorBoard:
# Set up a logs directory, so Tensorboard knows where to look for files.
log_dir='/logs/imdb-example/'
if not os.path.exists(log_dir):
os.makedirs(log_dir)
# Save Labels separately on a line-by-line manner.
with open(os.path.join(log_dir, 'metadata.tsv'), "w") as f:
for subwords in encoder.subwords:
f.write("{}\n".format(subwords))
# Fill in the rest of the labels with "unknown".
for unknown in range(1, encoder.vocab_size - len(encoder.subwords)):
f.write("unknown #{}\n".format(unknown))
# Save the weights we want to analyze as a variable. Note that the first
# value represents any unknown word, which is not in the metadata, here
# we will remove this value.
weights = tf.Variable(model.layers[0].get_weights()[0][1:])
# Create a checkpoint from embedding, the filename and key are the
# name of the tensor.
checkpoint = tf.train.Checkpoint(embedding=weights)
checkpoint.save(os.path.join(log_dir, "embedding.ckpt"))
# Set up config.
config = projector.ProjectorConfig()
embedding = config.embeddings.add()
# The name of the tensor will be suffixed by `/.ATTRIBUTES/VARIABLE_VALUE`.
embedding.tensor_name = "embedding/.ATTRIBUTES/VARIABLE_VALUE"
embedding.metadata_path = 'metadata.tsv'
projector.visualize_embeddings(log_dir, config)
If you want to visualize during training, you can call this code in a save callback during training every X episodes using this.
I saved a keras model using model.save(model_path). Now when I try to load it and apply model.summary() or model.get_weights() function I am getting following error:
AttributeError: '_UserObject' object has no attribute 'summary'
Tried printing the data type of the model and got following whereas it was a sequential keras model when I had saved it:
<class 'tensorflow.python.saved_model.load.Loader._recreate_base_user_object.<locals>._UserObject'>
I am using tensorflow 2.4.1(cpu). Below sample code can help recreating the error:
def save_model():
model = tf.keras.Sequential()
model_path = "https://tfhub.dev/google/universal-sentence-encoder/4"
hub_layer = hub.KerasLayer(model_path, input_shape=[], dtype=tf.string, trainable=False)
model.add(hub_layer)
model.save('/home/pcadmin/data/models/sentence_embedding/use-4-pre-trained/')
model = tf.keras.models.load_model(model_path)
print(model.summary())
model.get_weights()
The reproducible code above isn't complete I think. However, you need to change the code as follows to make it run. (I've tested on cpu/gpu with tf 2.4/2.7.)
model_path = "https://tfhub.dev/google/universal-sentence-encoder/4"
def save_model(model_path):
model = tf.keras.Sequential()
hub_layer = hub.KerasLayer(model_path,
input_shape=[],
dtype=tf.string, trainable=False)
model.add(hub_layer)
model.save('saved/')
save_model(model_path)
model = tf.keras.models.load_model('/content/saved')
model.summary() # OK
model.get_weights() # OK
I am following the official Keras transfer learning and fine-tuning tutorial. It consists of loading the Xception model with include_top=False, and adding a new classifier part on top.
I am then saving the model with model.save() and loading with load_model().
So this is what I see when I do model.summary()
My problem is that I would like to iterate through the layers, while now Xception layers are somehow folded (on the picture: xception(Functional)). Is there a way to somehow unfold it, to see all the layers (including those that are creating Xception)?
For model. summary(), you can unfold that as follows:
from tensorflow import keras
base_model = keras.applications.Xception(
weights='imagenet', # Load weights pre-trained on ImageNet.
input_shape=(150, 150, 3),
include_top=False) # Do not include the ImageNet classifier at the top.
inputs = keras.Input(shape=(150, 150, 3))
x = base_model(inputs, training=False)
x = keras.layers.GlobalAveragePooling2D()(x)
outputs = keras.layers.Dense(1)(x)
model = keras.Model(inputs, outputs)
model.summary() # full model
model.layers[1].summary() # only xception model
Note, you cal also see the layer using the plot_model utility.
keras.utils.plot_model(model, expand_nested=True)
I am using Anaconda Navigator, Jupyter to be precised.
import tensorflow as tf
from tensorflow import keras
print(tf.__version__)
>>> 1.14.0
This is my model
def create_model():
model = tf.keras.Sequential([
keras.layers.Dense(86, activation='relu', kernel_regularizer=keras.regularizers.l2(0.0001),input_shape=(129,)),
keras.layers.Dropout(0.2),
keras.layers.Dense(142, activation='relu', kernel_regularizer=keras.regularizers.l2(0.0001)),
keras.layers.Dropout(0.2),
keras.layers.Dense(4, activation='softmax')
])
return model
model = create_model()
# Display the model's architecture
model.summary()
After training,predicting and evaluating my model, I decided to save it using
model.save('/Users/Jennifer/myproject/my_model.h5')
I checked the directory and folder with the h5py file. And I decided to load it using
new_model1 = tf.keras.models.load_model('/Users/Jennifer/myproject/my_model.h5')
I got an Error
ValueError: Unknown entries in loss dictionary: ['class_name', 'config']. Only expected following keys: ['dense_17']
Please help me. What should I do? I have almost spent the whole day trying to solve this issue. Thanks
Here is a bit of a work around that just loads the weights:
#!/usr/bin/env python3
from tensorflow import keras
import os
def create_model():
model = keras.Sequential([
keras.layers.Dense(86, activation='relu', kernel_regularizer=keras.regularizers.l2(0.0001),input_shape=(129,)),
keras.layers.Dropout(0.2),
keras.layers.Dense(142, activation='relu', kernel_regularizer=keras.regularizers.l2(0.0001)),
keras.layers.Dropout(0.2),
keras.layers.Dense(4, activation='softmax')
])
return model
if os.path.exists("junk.h5"):
model = create_model()
model.load_weights("junk.h5")
else:
model = create_model()
model.compile(optimizer=keras.optimizers.Adam(0.0001), loss=keras.losses.CategoricalCrossentropy(from_logits=True), metrics=['accuracy'])
model.save("junk.h5")
Another workaround would be to save the model without the optimizer
model.save("junk.h5", include_optimizer=False)
It looks like the loss function you're using creates a dictionary that has invalid keys. This sounds like a bug in keras/tensorflow. That is why the colab one probably worked because it was using a newer version.
I followed this tutorial about building an encoder-decoder language translation model and built one for my native language.
Now I want to save it, deploy on cloud ML engine and make predictions with HTTP request.
I couldn't find a clear example on how to save this model,
I am new to ML and found TF save guide v confusing..
Is there a way to save this model using something like
tf.keras.models.save_model
Create the train saver after opening the session and after the training is done save the model:
with tf.Session() as sess:
saver = tf.train.Saver()
# Training of the model
save_path = saver.save(sess, "logs/encoder_decoder")
print(f"Model saved in path {save_path}")
You can save a Keras model in Keras's HDF5 format, see:
https://keras.io/getting-started/faq/#how-can-i-save-a-keras-model
You will want to do something like:
import tf.keras
model = tf.keras.Model(blah blah)
model.save('my_model.h5')
If you migrate to TF 2.0, it's more straightforward to build a model in tf.keras and deploy using the TF SavedModel format. This 2.0 tutorial shows using a pretrained tf.keras model, saving the model in SavedModel format, deploying to the cloud and then doing an HTTP request for a prediction:
https://www.tensorflow.org/beta/guide/saved_model
I know I am a little late but was having the same problem (see How do I save an encoder-decoder model with TensorFlow? for more details) and figured out a solution. It's a little hacky, but it works!
Step 1 - Saving your model
Save your tokenizer (if applicable). Then individually save the weights of the model you used to train your data (naming your layers helps here).
# Save the tokenizer
with open('tokenizer.pickle', 'wb') as handle:
pickle.dump(tokenizer, handle, protocol=pickle.HIGHEST_PROTOCOL)
# save the weights individually
for layer in model.layers:
weights = layer.get_weights()
if weights != []:
np.savez(f'{layer.name}.npz', weights)
Step 2 - reloading the weights
You will want to reload the tokenizer (as applicable) then load the weights you just saved. The loaded weights are in an npz format so can't be used directly, but the very short documentation will tell you everything you need to know about this file type https://numpy.org/doc/stable/reference/generated/numpy.savez.html
# load the tokenizer
with open('tokenizer.pickle', 'rb') as handle:
tokenizer = pickle.load(handle)
# load the weights
w_encoder_embeddings = np.load('encoder_embeddings.npz', allow_pickle=True)
w_decoder_embeddings = np.load('decoder_embeddings.npz', allow_pickle=True)
w_encoder_lstm = np.load('encoder_lstm.npz', allow_pickle=True)
w_decoder_lstm = np.load('decoder_lstm.npz', allow_pickle=True)
w_dense = np.load('dense.npz', allow_pickle=True)
Step 3 - Recreate the your training model and apply the weights
You'll want to re-run the code you used to create your model. In my case this was:
encoder_inputs = Input(shape=(None,), name="encoder_inputs")
encoder_embeddings = Embedding(vocab_size, embedding_size, mask_zero=True, name="encoder_embeddings")(encoder_inputs)
# Encoder lstm
encoder_lstm = LSTM(512, return_state=True, name="encoder_lstm")
encoder_outputs, state_h, state_c = encoder_lstm(encoder_embeddings)
# discard `encoder_outputs` and only keep the states.
encoder_states = [state_h, state_c]
# Set up the decoder, using `encoder_states` as initial state.
decoder_inputs = Input(shape=(None,), name="decoder_inputs")
# target word embeddings
decoder_embeddings = Embedding(vocab_size, embedding_size, mask_zero=True, name="decoder_embeddings")
training_decoder_embeddings = decoder_embeddings(decoder_inputs)
# decoder lstm
decoder_lstm = LSTM(512, return_sequences=True, return_state=True, name="decoder_lstm")
decoder_outputs, _, _ = decoder_lstm(training_decoder_embeddings,
initial_state=encoder_states)
decoder_dense = TimeDistributed(Dense(vocab_size, activation='softmax'), name="dense")
decoder_outputs = decoder_dense(decoder_outputs)
# While training, model takes input and traget words and outputs target strings
loaded_model = Model([encoder_inputs, decoder_inputs], decoder_outputs, name="training_model")
Now you can apply your saved weights to these layers! It takes a little bit of investigation which weight goes to which layer, but this is made a lot easier by naming your layers and inspecting your model layers with model.layers.
# set the weights of the model
loaded_model.layers[2].set_weights(w_encoder_embeddings['arr_0'])
loaded_model.layers[3].set_weights(w_decoder_embeddings['arr_0'])
loaded_model.layers[4].set_weights(w_encoder_lstm['arr_0'])
loaded_model.layers[5].set_weights(w_decoder_lstm['arr_0'])
loaded_model.layers[6].set_weights(w_dense['arr_0'])
Step 4 - Create the inference model
Finally, you can now create your inference model based on this training model! Again in my case this was:
encoder_model = Model(encoder_inputs, encoder_states)
# Redefine the decoder model with decoder will be getting below inputs from encoder while in prediction
decoder_state_input_h = Input(shape=(512,))
decoder_state_input_c = Input(shape=(512,))
decoder_states_inputs = [decoder_state_input_h, decoder_state_input_c]
inference_decoder_embeddings = decoder_embeddings(decoder_inputs)
decoder_outputs2, state_h2, state_c2 = decoder_lstm(inference_decoder_embeddings, initial_state=decoder_states_inputs)
decoder_states2 = [state_h2, state_c2]
decoder_outputs2 = decoder_dense(decoder_outputs2)
# sampling model will take encoder states and decoder_input(seed initially) and output the predictions(french word index) We dont care about decoder_states2
decoder_model = Model(
[decoder_inputs] + decoder_states_inputs,
[decoder_outputs2] + decoder_states2)
And voilà! You can now make inferences using the previously trained model!