Im deploying a keras model and sending the test data to the model via a flask api. I have two files:
First: My Flask App:
# Let's startup the Flask application
app = Flask(__name__)
# Model reload from jSON:
print('Load model...')
json_file = open('models/model_temp.json', 'r')
loaded_model_json = json_file.read()
json_file.close()
keras_model_loaded = model_from_json(loaded_model_json)
print('Model loaded...')
# Weights reloaded from .h5 inside the model
print('Load weights...')
keras_model_loaded.load_weights("models/Model_temp.h5")
print('Weights loaded...')
# URL that we'll use to make predictions using get and post
#app.route('/predict',methods=['GET','POST'])
def predict():
data = request.get_json(force=True)
predict_request = [data["month"],data["day"],data["hour"]]
predict_request = np.array(predict_request)
predict_request = predict_request.reshape(1,-1)
y_hat = keras_model_loaded.predict(predict_request, batch_size=1, verbose=1)
return jsonify({'prediction': str(y_hat)})
if __name__ == "__main__":
# Choose the port
port = int(os.environ.get('PORT', 9000))
# Run locally
app.run(host='127.0.0.1', port=port)
Second: The file Im using to send the json data sending to the api endpoint:
response = rq.get('api url has been removed')
data=response.json()
currentDT = datetime.datetime.now()
Month = currentDT.month
Day = currentDT.day
Hour = currentDT.hour
url= "http://127.0.0.1:9000/predict"
post_data = json.dumps({'month': month, 'day': day, 'hour': hour,})
r = rq.post(url,post_data)
Im getting this response from Flask regarding Tensorflow:
ValueError: Tensor Tensor("dense_6/BiasAdd:0", shape=(?, 1), dtype=float32) is not an element of this graph.
My keras model is a simple 6 dense layer model and trains with no errors.
Any ideas?
Flask uses multiple threads. The problem you are running into is because the tensorflow model is not loaded and used in the same thread. One workaround is to force tensorflow to use the gloabl default graph .
Add this after you load your model
global graph
graph = tf.get_default_graph()
And inside your predict
with graph.as_default():
y_hat = keras_model_loaded.predict(predict_request, batch_size=1, verbose=1)
It's so much simpler to wrap your keras model in a class and that class can keep track of it's own graph and session. This prevents the problems that having multiple threads/processes/models can cause which is almost certainly the cause of your issue. While other solutions will work this is by far the most general, scalable and catch all. Use this one:
import os
from keras.models import model_from_json
from keras import backend as K
import tensorflow as tf
import logging
logger = logging.getLogger('root')
class NeuralNetwork:
def __init__(self):
self.session = tf.Session()
self.graph = tf.get_default_graph()
# the folder in which the model and weights are stored
self.model_folder = os.path.join(os.path.abspath("src"), "static")
self.model = None
# for some reason in a flask app the graph/session needs to be used in the init else it hangs on other threads
with self.graph.as_default():
with self.session.as_default():
logging.info("neural network initialised")
def load(self, file_name=None):
"""
:param file_name: [model_file_name, weights_file_name]
:return:
"""
with self.graph.as_default():
with self.session.as_default():
try:
model_name = file_name[0]
weights_name = file_name[1]
if model_name is not None:
# load the model
json_file_path = os.path.join(self.model_folder, model_name)
json_file = open(json_file_path, 'r')
loaded_model_json = json_file.read()
json_file.close()
self.model = model_from_json(loaded_model_json)
if weights_name is not None:
# load the weights
weights_path = os.path.join(self.model_folder, weights_name)
self.model.load_weights(weights_path)
logging.info("Neural Network loaded: ")
logging.info('\t' + "Neural Network model: " + model_name)
logging.info('\t' + "Neural Network weights: " + weights_name)
return True
except Exception as e:
logging.exception(e)
return False
def predict(self, x):
with self.graph.as_default():
with self.session.as_default():
y = self.model.predict(x)
return y
Just after loading the model add model._make_predict_function()
`
# Model reload from jSON:
print('Load model...')
json_file = open('models/model_temp.json', 'r')
loaded_model_json = json_file.read()
json_file.close()
keras_model_loaded = model_from_json(loaded_model_json)
print('Model loaded...')
# Weights reloaded from .h5 inside the model
print('Load weights...')
keras_model_loaded.load_weights("models/Model_temp.h5")
print('Weights loaded...')
keras_model_loaded._make_predict_function()
It turns out this way does not need a clear_session call and is at the same time configuration friendly, using the graph object from configured session session = tf.Session(config=_config); self.graph = session.graph and the prediction by the created graph as default with self.graph.as_default(): offers a clean approach
from keras.backend.tensorflow_backend import set_session
...
def __init__(self):
config = self.keras_resource()
self.init_model(config)
def init_model(self, _config, *args):
session = tf.Session(config=_config)
self.graph = session.graph
#set configured session
set_session(session)
self.model = load_model(file_path)
def keras_resource(self):
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
return config
def predict_target(self, to_predict):
with self.graph.as_default():
predict = self.model.predict(to_predict)
return predict
I had the same problem. it was resolved by changing TensorFlow-1 version to TensorFlow-2.
just uninstall ver-1 and install ver-2.
Ya their is a bug when you predict from model with keras. Keras will not be able to build graph due to some error. Try to predict images from model with the help of tensor flow. Just replace this line of code
Keras code:
features = model_places.predict( img )
tensorflow code:
import tensorflow as tf
graph = tf.get_default_graph()
import this library in your code and replace.
with graph.as_default():
features = model_places.predict( img ).tolist()
If Problem still not solved :
if still problem not solved than try to refresh the graph.
As your code is fine, running with a clean environment should solve it.
Clear keras cache at ~/.keras/
Run on a new environment, with the right packages (can be done easily with anaconda)
Make sure you are on a fresh session, keras.backend.clear_session() should remove all existing tf graphs.
Keras Code:
keras.backend.clear_session()
features = model_places.predict( img )
TensorFlow Code:
import tensorflow as tf
with tf.Session() as sess:
tf.reset_default_graph()
Simplest solution is to use tensorflow 2.0. Run your code in Tensorflow 2.0 environment and it will work.
I was facing same issues while exposing a pre-trained model via REST server. I was loading the model at the server startup and later using the loaded model to make predictions via POST/GET request. While predicting it was generating error as session not saved between the predict call. Though when I was loading the model every time prediction is made it was working fine.
Then to avoid this issue with the session I just ran the code in TF=2.0 environment and it ran fine.
Related
I have the exact same problem as https://github.com/huggingface/transformers/issues/11243, except it only does not work in Jupyter lab. It does work in python in my shell. EDIT: It is now not working in shell either after I closed and reopened the shell.
I downloaded the cardiffnlp/twitter-roberta-base-emotion model using:
model_name = "cardiffnlp/twitter-roberta-base-emotion"
model = AutoModelForSequenceClassification.from_pretrained(model_name)
I saved the model with model.save_pretrained(model_name) and now I can't load the tokenizer. If I run:
tokenizer = AutoTokenizer.from_pretrained(model_name)
it gives the error:
OSError: Can't load tokenizer for 'cardiffnlp/twitter-roberta-base-emotion'. Make sure that:
- 'cardiffnlp/twitter-roberta-base-emotion' is a correct model identifier listed on 'https://huggingface.co/models'
(make sure 'cardiffnlp/twitter-roberta-base-emotion' is not a path to a local directory with something else, in that case)
- or 'cardiffnlp/twitter-roberta-base-emotion' is the correct path to a directory containing relevant tokenizer files
Because I saved the model and not the tokenizer yesterday, I can't load the tokenizer anymore. What can I do to fix this? I don't understand how to save the tokenizer if I can't load the tokenizer.
The model and tokenizer are two different things yet do share the same location to which you download them. You need to save both the tokenizer and the model. I wrote a simple utility to help.
import typing as t
from loguru import logger
from pathlib import Path
import torch
from transformers import PreTrainedModel
from transformers import PreTrainedTokenizer
class ModelLoader:
"""ModelLoader
Downloading and Loading Hugging FaceModels
Download occurs only when model is not located in the local model directory
If model exists in local directory, load.
"""
def __init__(
self,
model_name: str,
model_directory: str,
tokenizer_loader: PreTrainedTokenizer,
model_loader: PreTrainedModel,
):
self.model_name = Path(model_name)
self.model_directory = Path(model_directory)
self.model_loader = model_loader
self.tokenizer_loader = tokenizer_loader
self.save_path = self.model_directory / self.model_name
if not self.save_path.exists():
logger.debug(f"[+] {self.save_path} does not exit!")
self.save_path.mkdir(parents=True, exist_ok=True)
self.__download_model()
self.tokenizer, self.model = self.__load_model()
def __repr__(self):
return f"{self.__class__.__name__}(model={self.save_path})"
# Download model from HuggingFace
def __download_model(self) -> None:
logger.debug(f"[+] Downloading {self.model_name}")
tokenizer = self.tokenizer_loader.from_pretrained(f"{self.model_name}")
model = self.model_loader.from_pretrained(f"{self.model_name}")
logger.debug(f"[+] Saving {self.model_name} to {self.save_path}")
tokenizer.save_pretrained(f"{self.save_path}")
model.save_pretrained(f"{self.save_path}")
logger.debug("[+] Process completed")
# Load model
def __load_model(self) -> t.Tuple:
logger.debug(f"[+] Loading model from {self.save_path}")
tokenizer = self.tokenizer_loader.from_pretrained(f"{self.save_path}")
# Check if GPU is available
device = "cuda" if torch.cuda.is_available() else "cpu"
logger.info(f"[+] Model loaded in {device} complete")
model = self.model_loader.from_pretrained(f"{self.save_path}").to(device)
logger.debug("[+] Loading completed")
return tokenizer, model
def retrieve(self) -> t.Tuple:
"""Retriver
Returns:
Tuple: tokenizer, model
"""
return self.tokenizer, self.model
You can use it as
…
model_name = "cardiffnlp/twitter-roberta-base-emotion"
model_directory = "/tmp" # or where you want to store models
tokenizer_loader = AutoTokenizer
model_loader = AutoModelForSequenceClassification
get_model = ModelLoader(model_name=model_name, model_directory=model_directory, tokenizer_loader=tokenizer_loader, model_loader=model_loader)
model, tokenizer = get_model.retrieve()
I am following this tutorial for image detection using Matterport repo.
I tried following this guide and edited the code to
How can I edit the following code to visualize the tensorboard ?
import tensorflow as tf
import datetime
%load_ext tensorboard
sess = tf.Session()
file_writer = tf.summary.FileWriter('/path/to/logs', sess.graph)
And then in the model area
# prepare config
config = KangarooConfig()
config.display()
# define the model
model = MaskRCNN(mode='training', model_dir='./', config=config)
model.keras_model.metrics_tensors = []
# Tensorflow board
logdir = os.path.join(
"logs", datetime.datetime.now().strftime("%Y%m%d-%H%M%S"))
tensorboard_callback = tf.keras.callbacks.TensorBoard(logdir, histogram_freq=1)
# load weights (mscoco) and exclude the output layers
model.load_weights('mask_rcnn_coco.h5',
by_name=True,
exclude=[
"mrcnn_class_logits", "mrcnn_bbox_fc", "mrcnn_bbox",
"mrcnn_mask"
])
# train weights (output layers or 'heads')
model.train(train_set,
test_set,
learning_rate=config.LEARNING_RATE,
epochs=5,
layers='heads')
I am not sure where to callbacks=[tensorboard_callback] ?
In your model.train, if you look closely in the source code documentation, there is parameter called custom_callbacks, which defaults to None.
It is there where you need to write your code, so to train with a custom callback, you will need to add this line of code:
model.train(train_set,
test_set,
learning_rate=config.LEARNING_RATE,
custom_callbacks = [tensorboard_callback],
epochs=5,
layers='heads')
You only have to open Anaconda Prompt and write tensorboard --logdir= yourlogdirectory, where yourlogdirectory is the directory containing the model checkpoint.
It should look something like this: logs\xxxxxx20200528T1755, where xxxx stands for the name you give to your configuration.
This command will generate a web address, copy it in our browser of preference.
I have an inference script where the load model and prediction are in one script, how to separate them so i do not have to load the model every time i have to make a prediction
from keras.models import load_model
# load model
model = load_model('model.h5')
# prediction
result = model.predict(image)
keep the model as a global variable and predict as a function inside this module.
from keras.models import load_model
model = None
# load model
def load_model_weights():
model = load_model('model.h5')
def predict(image):
if(model is None):
load_model_weights()
else:
# prediction
result = model.predict(image)
return result
import the function predict from this module and use it in other modules.
I tried creating a model using tensorflow. When I tried executing it shows me
the other files are in this link------- github.com/llSourcell/tensorflow_chatbot
def train():
enc_train, dec_train=data_utils.prepare_custom_data(
gConfig['working_directory'])
train_set = read_data(enc_train,dec_train)
def seq2seq_f(encoder_inputs,decoder_inputs,do_decode):
return tf.nn.seq2seq.embedding_attention_seq2seq(
encoder_inputs,decoder_inputs, cell,
num_encoder_symbols=source_vocab_size,
num_decoder_symbols=target_vocab_size,
embedding_size=size,
output_projection=output_projection,
feed_previous=do_decode)
with tf.Session(config=config) as sess:
model = create_model(sess,False)
while True:
sess.run(model)
checkpoint_path = os.path.join(gConfig['working_directory'],'seq2seq.ckpt')
model.saver.save(sess, checkpoint_path, global_step=model.global_step)
other than this the other python files ive used are in the github link specified in the comments section below
this is the code defining create_model in the execute.py file
def create_model(session, forward_only):
"""Create model and initialize or load parameters"""
model = seq2seq_model.Seq2SeqModel( gConfig['enc_vocab_size'], gConfig['dec_vocab_size'], _buckets, gConfig['layer_size'], gConfig['num_layers'], gConfig['max_gradient_norm'], gConfig['batch_size'], gConfig['learning_rate'], gConfig['learning_rate_decay_factor'], forward_only=forward_only)
if 'pretrained_model' in gConfig:
model.saver.restore(session,gConfig['pretrained_model'])
return model
ckpt = tf.train.get_checkpoint_state(gConfig['working_directory'])
# the checkpoint filename has changed in recent versions of tensorflow
checkpoint_suffix = ""
if tf.__version__ > "0.12":
checkpoint_suffix = ".index"
if ckpt and tf.gfile.Exists(ckpt.model_checkpoint_path + checkpoint_suffix):
print("Reading model parameters from %s" % ckpt.model_checkpoint_path)
model.saver.restore(session, ckpt.model_checkpoint_path)
else:
print("Created model with fresh parameters.")
session.run(tf.initialize_all_variables())
return model
Okay, it seems like you have copied code but you did not structure it. If create_model() is defined in another file then you have to import it. Have you done that? (i.e. from file_with_methods import create_model). You should consider editing your post and adding more of your code, if you want us to help.
Alternative: You could also clone the github repository(that you shared in your comment) and just change whatever you want to change in the execution.py file. This way you can keep the "hierarchy" that the owner uses and you could add your own code where needed.
I'm trying to deploy a recently trained Keras model on Google Cloud ML Engine. I googled around to see what format the saved model needs to be for ML Engine and found this:
import keras.backend as K
import tensorflow as tf
from keras.models import load_model, Sequential
from tensorflow.python.saved_model import builder as saved_model_builder
from tensorflow.python.saved_model import tag_constants, signature_constants
from tensorflow.python.saved_model.signature_def_utils_impl import predict_signature_def
# reset session
K.clear_session()
sess = tf.Session()
K.set_session(sess)
# disable loading of learning nodes
K.set_learning_phase(0)
# load model
model = load_model('model.h5')
config = model.get_config()
weights = model.get_weights()
new_Model = Sequential.from_config(config)
new_Model.set_weights(weights)
# export saved model
export_path = 'YOUR_EXPORT_PATH' + '/export'
builder = saved_model_builder.SavedModelBuilder(export_path)
signature = predict_signature_def(inputs={'NAME_YOUR_INPUT': new_Model.input},
outputs={'NAME_YOUR_OUTPUT': new_Model.output})
with K.get_session() as sess:
builder.add_meta_graph_and_variables(sess=sess,
tags=[tag_constants.SERVING],
signature_def_map={
signature_constants.DEFAULT_SERVING_SIGNATURE_DEF_KEY: signature})
builder.save()
However, in Keras 2.1.3, keras.backend no longer seems to have clear_session(), set_session(), or get_session(). What's the modern way of handling this issue? Do those functions live elsewhere now?
Thanks!