I have finetuned a BertForSequenceClassification model externally usnig PyTorch. I have then exported and saved the model following the documentation of SparkNLP. The problem that I am facing is that before converting it to a SparkNLP model, it was predicting the classes correctly but after the conversion the model is making a lot of misclassification errors.
The below code is where I am loading my fine tuned PyTorch model and converting it into a TF model for SparkNLP.
from transformers import TFBertForSequenceClassification, BertTokenizer, BertConfig
tokenizer = BertTokenizer.from_pretrained("model/tokenizer", do_lower_case=True)
tokenizer.save_pretrained('spark_nlp/tokenizer')
model = TFBertForSequenceClassification.from_pretrained("model/base_model", num_labels=31, from_pt=True)
model = TFBertForSequenceClassification.from_pretrained("model/fine_tuned_model/finetuned_bert.model", from_pt=True, config=model.config)
model.save_pretrained("spark_nlp/tf_model", saved_model=True)
Related
so im facing a problem about deployment my custom sign-language recognition model. I converted my_ssd_mobnet with exporter_main_v2.py to saved_model.pb and then i tried to use the tensorflowjs convertor with this code:
from tensorflow import keras
import tensorflowjs as tfjs
def importModel(modelPath):
model = tf.keras.models.load_model(modelPath)
tfjs.converters.save_tf_model(model, "tfjsmodel")
importModel("saved_model")
#importModel("modelDirectory")
then i got an error like this..
ValueError: Unable to create a Keras model from this SavedModel. This SavedModel was created with tf.saved_model.save, and lacks the Keras metadata.Please save your Keras model by calling model.saveor tf.keras.models.save_model.
Finally i decide to convert my model to h5, but.. i don't know how.
How can i convert my_ssd_mobnet model to h5?
Thanks!
If you're creating a custom Keras layer in python and wanting to export it to tfjs for the browser to predict, then you'll most likely encounter "Unknown layer" and will have to implement them yourself in JS.
Instead of exporting the layers, it's best to export a graph since you're only using it for prediction and not training in the browser.
tf.saved_model.save(model, 'saved_model')
This will save the files in the saved_model folder and contains the .pb file.
Use the tensorflowjs_converter tool to convert the model into a graph tfjs model.
tensorflow_converter --input_format=tf_saved_model saved_model model
This will convert your saved model into the browser-compatible tfjs model without the custom layer. (The Keras layers will be built in.)
Move this folder to your website's public folder.
In the browser:
const model = await tf.loadGraphModel('/model/model.json')
const img = tf.browser.fromPixels(imageData, 3) // imageElement, videoElement, ImageData
.toFloat().resizeBilinear([224, 224]) // mobilenet dims
.div(tf.scalar(255)) // mobilenet [0,1] normalization
.expandDims()
const { values, indices } = model.predict(img).topk()
const label = indices.dataSync()[0]
const confidence = values.dataSync()[0]
NOTE: The .bin files will end up in the 10's of MB so put this inside a webworker. You can send a buffered data from the main thread to the worker thread for processing.
First and foremost, if you have used "exporter_main_v2.py" script to export the model, you will only get the model format in tensorflow model. This way of exporting is mainly used to make inference on the trained model. So the main problem in your code is that you are trying to import a "keras model" with that tf.keras.models.load_model() function. Instead of using "exporter_main_v2.py" you have to use tf.keras.models.save_model() function to export/save your model.
I am also giving you a simple video explanation link to clarify a few things for you
https://www.youtube.com/watch?v=Lx7OCFXPG8o
After watching the video you might want to checkout the following colab notebook
https://colab.research.google.com/github/tensorflow/examples/blob/master/courses/udacity_intro_to_tensorflow_for_deep_learning/l07c01_saving_and_loading_models.ipynb
This is a material provided by Udacity from its introduction to tensorflow training course. That should be very helpful in your case to understand the difference between tensorflow model file and keras model file.
Have a nice day.
Edit:
HDF5 format
Keras provides a basic save format using the HDF5 standard.
Create and train a new model instance.
model = create_model()
model.fit(train_images, train_labels, epochs=5)
Save the entire model to a HDF5 file.
The '.h5' extension indicates that the model should be saved to HDF5.
model.save('my_model.h5')
You should add '.h5' extension to filename when calling model.save function, by this way the model will be saved in h5 format.
How can I remove certain layers AND be able to save it as a new model in tensorflow?
I have the following code for removing top-N layers in tensorflow and it works:
reconstructed_model = tf.keras.models.load_model(model_path)
embedding = Model(reconstructed_model.input,
reconstructed_model.layers[-4].output)
However, when I am trying to save it with either of these two methods:
tf.keras.models.save_model(model=embedding, model_path)
embedding.save(model_path)
I am encountering the following error:
KeyError: "Failed to add concrete function 'b'__inference_model_3_layer_call_fn_286241'' to object-based SavedModel as it captures tensor <tf.Tensor: shape=(), dtype=resource, value=<Resource Tensor>> which is unsupported or not reachable from root. One reason could be that a stateful object or a variable that the function depends on is not assigned to an attribute of the serialized trackable object (see SaveTest.test_captures_unreachable_variable)."
The pretrained model that I am using is a fine-tuned efficientnetv2 from the tensorflow applications api
from tensorflow.keras.applications import EfficientNetB0
and I was able to save and reuse it here, just don't know how to save a modified one after reloading.
I tried using EfficientNetB0 and constructed a model truncating the last four layers, just as you did.
from tensorflow.keras.applications import EfficientNetB0
import tensorflow as tf
efficientnet = EfficientNetB0( include_top=False )
embedding = tf.keras.models.Model(
efficientnet.input ,
efficientnet.layers[ -4 ].output
)
embedding.summary()
embedding.save( 'embedding_model.h5' )
And then loading the model, using tf.keras.models.load_model,
model = tf.keras.models.load_model( 'embedding_model.h5' )
model.summary()
I could load the model without any problems. Maybe there's some problem with the reconstructed_model.
I have keras pretrained model(model.h5). And I want to prune that model with tensorflow Magnitude-based weight pruning with Keras. One curious things is that my pretrained model is built with original keras model > I mean that is not from tensorflow.keras. Inside tensorflow Magnitude-based weight pruning with Keras example, they show how to do with tensorflow.keras model. I want to ask is that can I use their tool to prune my original keras pretrained model?
inside their weight pruning toolkit ,there is two way. one is pruned the model layer by layer while training and second is pruned the whole model. I tried the second way to prune the whole pretrained model. below is my code.
inside their weight pruning toolkit ,there is two way. one is pruned the model layer by layer while training and second is pruned the whole model. I tried the second way to prune the whole pretrained model. below is my code.
For my original pretrained model, I load the weight from model.h5 and can call model.summary() after I apply prune_low_magnitude() none of the method from model cannot call including model.summary() method. And show the error like AttributeError: 'NoneType' object has no attribute 'summary'
model = get_training_model(weight_decay)
model.load_weights('model/keras/model.h5')
model.summary()
epochs = 1
end_step = np.ceil(1.0 * 100 / 2).astype(np.int32) * epochs
print(end_step)
new_pruning_params = {
'pruning_schedule': tfm.sparsity.keras.PolynomialDecay(initial_sparsity=0.1,
final_sparsity=0.90,
begin_step=40,
end_step=end_step,
frequency=30)
}
new_pruned_model = tfm.sparsity.keras.prune_low_magnitude(model, **new_pruning_params)
print(new_pruned_model.summary())
Inside their weight pruning toolkit
enter link description here ,there is two way. one is pruned the model layer by layer while training and second is pruned the whole model. I tried the second way to prune the whole pretrained model. below is my code.
For my original pretrained model, I load the weight from model.h5 and can call model.summary() after I apply prune_low_magnitude() none of the method from model cannot call including model.summary() method. And show the error like
AttributeError: 'NoneType' object has no attribute 'summary'
I hope this answer still helps, but I recently had the same issue that prune_low_magnitude() returns an object of type 'None'. Also new_pruned_model.compile() would not work.
The model I had been using was a pretrained model that could be imported from tensorflow.python.keras.applications.
For me this worked:
(0) Import the libraries:
from tensorflow_model_optimization.python.core.api.sparsity import keras as sparsity
from tensorflow.python.keras.applications.<network_type> import <network_type>
(1) Define the pretrained model architecture
# define model architecture
loaded_model = <model_type>()
loaded_model.summary()
(2) Compile the model architecture and load the pretrained weights
# compile model
opt = SGD(lr=learn_rate, momentum=momentum)
loaded_model.compile(optimizer=opt, loss='categorical_crossentropy', metrics=['accuracy'])
loaded_model.load_weights('weight_file.h5')
(3) set pruning parameters and assign pruning schedule
# set pruning parameters
pruning_params = {
'pruning_schedule': sparsity.PolynomialDecay(...)
}
# assign pruning schedule
model_pruned = sparsity.prune_low_magnitude(loaded_model, **pruning_params)
(4) compile model and show summary
# compile model
model_pruned.compile(
loss=tf.keras.losses.categorical_crossentropy,
optimizer='SGD',
metrics=['accuracy'])
model_pruned.summary()
It was important to import the libraries specifically from tensorflow.python.keras and use this keras model from the TensorFlow library.
Also, it was important to use the TensorFlow Beta Release (pip install tensorflow==2.0.0b1), otherwise still an object with type 'None' would be returned by prune_low_magnitude.
I am using PyCharm 2019.1.3 (x64) as IDE. Here is the link that led me to this solution: https://github.com/tensorflow/model-optimization/issues/12#issuecomment-526338458
I have repurposed an Inception V3 network using the transfer learning method, following this article.
For that, I removed the final network layer, and fed hundreds of images of my face into the network.
A new model was then sucessfully generated: inceptionv3-ft.model
Now I would like to load this model and use its fixed weights to apply my face as a 'theme' on a input image, like google-dream.
For that I am using a keras program, which loads models like so:
from keras.applications import inception_v3
# Build the InceptionV3 network with our placeholder.
# The model will be loaded with pre-trained ImageNet weights.
model = inception_v3.InceptionV3(weights='imagenet',
include_top=False)
dream = model.input
Full code here: https://github.com/keras-team/keras/blob/master/examples/deep_dream.py
So, how do I load and pass not a pre-trained but rather my RE-trained model weights?
simply:
from keras.models import load_model
model = load_model('inceptionv3-ft.model')
dream = model.input
I'm working on facial expression recognition using CNN. I'm using Keras and Tensorflow as backend. My model is saved to h5 format.
I want to retrain my network, and fine-tune my model with the VGG model.
How can I do that with keras ?
Save your models architecture and weights:
json_string = model.to_json()
model.save_weights('model_weights.h5')
Load model architecture and weights:
from keras.models import model_from_json
model = model_from_json(json_string)
model.load_weights('model_weights.h5')
Start training again from here for finetuning. I hope this helps.
You can use the Keras model.save(filepath) function.
Details for the various Keras saving and loading techniques are discussed with examples in this YouTube video: Save and load a Keras model
model.save(filepath)saves:
The architecture of the model, allowing to re-create the model.
The weights of the model.
The training configuration (loss, optimizer).
The state of the optimizer, allowing to resume training exactly where you left off.
To load this saved model, you would use the following:
from keras.models import load_model
new_model = load_model(filepath)
If you used model.to_json(), you would only be saving the architecture of the model. Additionally, if you used model.save_weights(), you would only be saving the weights of the model. With both of these alternative saving techniques, you would not be saving the training configuration (loss, optimizer), nor would you be saving the state of the optimizer.