Jupyter Notebook kernel dies when i import model from Huggingface - python

Here is the code where I am loading a huggingface pre trained model , but my kernel dies. The model size in the description page is only 458 MB size. Why is it failing?
from transformers import TextClassificationPipeline, AutoModelForSequenceClassification, AutoTokenizer
model_name = "ElKulako/cryptobert"
tokenizer = AutoTokenizer.from_pretrained(model_name, use_fast=True)
model = AutoModelForSequenceClassification.from_pretrained(model_name, num_labels = 3)
pipe = TextClassificationPipeline(model=model, tokenizer=tokenizer, max_length=64, truncation=True, padding = 'max_length')
# post_1 & post_3 = bullish, post_2 = bearish
post_1 = " see y'all tomorrow and can't wait to see stock in the morning, i wonder what price it is going to be at. 😎🐂🤠💯😴,It is looking good go for it and flash by that 45k. "
df_posts = [post_1, post_2, post_3]
preds = pipe(df_posts)
print(preds)

Related

Weights and Biases error: The wandb backend process has shutdown

running the colab linked below, I get the following error:
"The wandb backend process has shutdown"
I see nothing suspicious in the way the colab uses wandb and I couldn't find anyone with the same problem. Any help is greatly appreciated. I am using the latest version of wandb in colab.
This is where I set up wandb:
if WANDB:
wandb.login()
and this is the part where I get the error:
#setup wandb if we're using it
if WANDB:
experiment_name = os.environ.get("EXPERIMENT_NAME")
group = experiment_name if experiment_name != "none" else wandb.util.generate_id()
cv_scores = []
oof_data_frame = pd.DataFrame()
for fold in range(1, config.folds + 1):
print(f"Fold {fold}/{config.folds}", end="\n"*2)
fold_directory = os.path.join(config.output_directory, f"fold_{fold}")
make_directory(fold_directory)
model_path = os.path.join(fold_directory, "model.pth")
model_config_path = os.path.join(fold_directory, "model_config.json")
checkpoints_directory = os.path.join(fold_directory, "checkpoints/")
make_directory(checkpoints_directory)
#Data collators are objects that will form a batch by using a list of dataset elements as input.
collator = Collator(tokenizer=tokenizer, max_length=config.max_length)
train_fold = train[~train["fold"].isin([fold])]
train_dataset = Dataset(texts=train_fold["anchor"].values,
pair_texts=train_fold["target"].values,
contexts=train_fold["title"].values,
targets=train_fold["score"].values,
max_length=config.max_length,
sep=tokenizer.sep_token,
tokenizer=tokenizer)
train_loader = DataLoader(dataset=train_dataset,
batch_size=config.batch_size,
num_workers=config.num_workers,
pin_memory=config.pin_memory,
collate_fn=collator,
shuffle=True,
drop_last=False)
print(f"Train samples: {len(train_dataset)}")
validation_fold = train[train["fold"].isin([fold])]
validation_dataset = Dataset(texts=validation_fold["anchor"].values,
pair_texts=validation_fold["target"].values,
contexts=validation_fold["title"].values,
targets=validation_fold["score"].values,
max_length=config.max_length,
sep=tokenizer.sep_token,
tokenizer=tokenizer)
validation_loader = DataLoader(dataset=validation_dataset,
batch_size=config.batch_size*2,
num_workers=config.num_workers,
pin_memory=config.pin_memory,
collate_fn=collator,
shuffle=True,
drop_last=False)
print(f"Validation samples: {len(validation_dataset)}")
model = Model(**config.model)
if not os.path.exists(model_config_path):
model.config.to_json_file(model_config_path)
model_parameters = model.parameters()
optimizer = get_optimizer(**config.optimizer, model_parameters=model_parameters)
training_steps = len(train_loader) * config.epochs
if "scheduler" in config:
config.scheduler.parameters.num_training_steps = training_steps
config.scheduler.parameters.num_warmup_steps = training_steps * config.get("warmup", 0)
scheduler = get_scheduler(**config.scheduler, optimizer=optimizer, from_transformers=True)
else:
scheduler = None
model_checkpoint = ModelCheckpoint(mode="min",
delta=config.delta,
directory=checkpoints_directory,
overwriting=True,
filename_format="checkpoint.pth",
num_candidates=1)
if WANDB:
wandb.init()
#wandb.init(group=group, name=f"fold_{fold}", config=config)
(train_loss, train_metrics), (validation_loss, validation_metrics, validation_outputs) = training_loop(model=model,
optimizer=optimizer,
scheduler=scheduler,
scheduling_after=config.scheduling_after,
train_loader=train_loader,
validation_loader=validation_loader,
epochs=config.epochs,
gradient_accumulation_steps=config.gradient_accumulation_steps,
gradient_scaling=config.gradient_scaling,
gradient_norm=config.gradient_norm,
validation_steps=config.validation_steps,
amp=config.amp,
debug=config.debug,
verbose=config.verbose,
device=config.device,
recalculate_metrics_at_end=True,
return_validation_outputs=True,
logger="tqdm")
if WANDB:
wandb.finish()
if config.save_model:
model_state = model.state_dict()
torch.save(model_state, model_path)
print(f"Model's path: {model_path}")
validation_fold["prediction"] = validation_outputs.to("cpu").numpy()
oof_data_frame = pd.concat([oof_data_frame, validation_fold])
cv_monitor_value = validation_loss if config.cv_monitor_value == "loss" else validation_metrics[config.cv_monitor_value]
cv_scores.append(cv_monitor_value)
del model, optimizer, validation_outputs, train_fold, validation_fold
torch.cuda.empty_cache()
gc.collect()
print(end="\n"*6)
TDLR; Check if the generated id is unique in the project space of wandb you are using.
Explanation
You can check the exact reason this happened in the log files under the wandb folder and specific run id. Had the same issue with Error communicating with wandb process and The wandb backend process has shutdown.
My problem was that I was assigning the run id to a specific instance which already existed, and rerunning the whole search space, but the run id have to be unique. Using name in init is generally a safer bet if you don't intend to continue the previous run (which is possible if you indicate so in the init method).
You can try running Wandb in offline mode, to see if this can help, and later on doing wandb sync.
Solution which worked for me is run !wandb login --relogin.

Using custom trained Keras model with Sagemaker endpoint results in "Session was not created with a graph before Run()" error while prediction

I have a trained a BERT text classification model using keras on spam vs ham dataset. I have deployed the model and got a Sagemaker endpoint. I want to use it for any prediction.
I am using a ml.t2.medium Sagemaker instance and my tensorflow version is 2.6.2 in the Sagemaker notebook
I am getting an error while using the Sagemaker endpoint for prediction. The error is Session was not created with a graph before Run()
This is my code for training the classifier
import tensorflow as tf
import tensorflow_hub as hub
import tensorflow_text as text
# In[2]:
import pandas as pd
df = pd.read_csv("spam.csv")
df.head(5)
# In[3]:
df.groupby('Category').describe()
# In[4]:
df['Category'].value_counts()
# In[5]:
df_spam = df[df['Category']=='spam']
df_spam.shape
# In[6]:
df_ham = df[df['Category']=='ham']
df_ham.shape
# In[7]:
df_ham_downsampled = df_ham.sample(df_spam.shape[0])
df_ham_downsampled.shape
# In[8]:
df_balanced = pd.concat([df_ham_downsampled, df_spam])
df_balanced.shape
# In[9]:
df_balanced['Category'].value_counts()
# In[10]:
df_balanced['spam']=df_balanced['Category'].apply(lambda x: 1 if x=='spam' else 0)
df_balanced.sample(5)
# In[11]:
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(df_balanced['Message'],df_balanced['spam'], stratify=df_balanced['spam'])
# In[12]:
bert_preprocess = hub.KerasLayer("https://tfhub.dev/tensorflow/bert_en_uncased_preprocess/3")
bert_encoder = hub.KerasLayer("https://tfhub.dev/tensorflow/bert_en_uncased_L-12_H-768_A-12/4")
# In[13]:
def get_sentence_embeding(sentences):
preprocessed_text = bert_preprocess(sentences)
return bert_encoder(preprocessed_text)['pooled_output']
get_sentence_embeding([
"500$ discount. hurry up",
"Bhavin, are you up for a volleybal game tomorrow?"]
)
# In[14]:
# Bert layers
text_input = tf.keras.layers.Input(shape=(), dtype=tf.string, name='text')
preprocessed_text = bert_preprocess(text_input)
outputs = bert_encoder(preprocessed_text)
# Neural network layers
l = tf.keras.layers.Dropout(0.1, name="dropout")(outputs['pooled_output'])
l = tf.keras.layers.Dense(1, activation='sigmoid', name="output")(l)
# Use inputs and outputs to construct a final model
model = tf.keras.Model(inputs=[text_input], outputs = [l])
# In[15]:
model.summary()
# In[16]:
METRICS = [
tf.keras.metrics.BinaryAccuracy(name='accuracy'),
tf.keras.metrics.Precision(name='precision'),
tf.keras.metrics.Recall(name='recall')
]
model.compile(optimizer='adam',
loss='binary_crossentropy',
metrics=METRICS)
# In[17]:
model.fit(X_train, y_train, epochs=1)
AND THIS PART IS USED FOR DEPLOYING THE MODEL
# In[18]:
model.save('saved_model/28dec1')
# In[3]:
model = tf.keras.models.load_model('saved_model/28dec1')
model.predict(["who is the spammer on here"])
array([[0.08218178]], dtype=float32)
# Check its architecture
model.summary()
# In[18]:
tf.compat.v1.enable_eager_execution()
print("pass")
# In[5]:
def convert_h5_to_aws(loaded_model):
"""
given a pre-trained keras model, this function converts it to a TF protobuf format
and saves it in the file structure which aws expects
"""
from tensorflow.python.saved_model import builder
from tensorflow.python.saved_model.signature_def_utils import predict_signature_def
from tensorflow.python.saved_model import tag_constants
# This is the file structure which AWS expects. Cannot be changed.
model_version = '1'
export_dir = 'export/Servo/' + model_version
# Build the Protocol Buffer SavedModel at 'export_dir'
builder = builder.SavedModelBuilder(export_dir)
# Create prediction signature to be used by TensorFlow Serving Predict API
signature = predict_signature_def(
inputs={"inputs": loaded_model.input}, outputs={"score": loaded_model.output})
from keras import backend as K
with K.get_session() as sess:
# Save the meta graph and variables
builder.add_meta_graph_and_variables(
sess=sess, tags=[tag_constants.SERVING], signature_def_map={"serving_default": signature})
builder.save()
#create a tarball/tar file and zip it
import tarfile
with tarfile.open('model.tar.gz', mode='w:gz') as archive:
archive.add('export', recursive=True)
convert_h5_to_aws(model)
# In[3]:
import sagemaker
sagemaker_session = sagemaker.Session()
inputs = sagemaker_session.upload_data(path='model.tar.gz', key_prefix='model')
# In[7]:
# where did it upload to?
print("Bucket name is:")
sagemaker_session.default_bucket()
# In[9]:
import boto3, re
from sagemaker import get_execution_role
# the (default) IAM role you created when creating this notebook
role = get_execution_role()
# Create a Sagemaker model (see AWS console>SageMaker>Models)
from sagemaker.tensorflow.model import TensorFlowModel
sagemaker_model = TensorFlowModel(model_data = 's3://' + sagemaker_session.default_bucket() + '/model/model.tar.gz',
role = role,
framework_version = '1.12',
entry_point = 'train.py')
# In[10]:
# Deploy a SageMaker to an endpoint
predictor = sagemaker_model.deploy(initial_instance_count=1,
instance_type='ml.m4.xlarge')
# In[5]:
import numpy as np
import sagemaker
from sagemaker.tensorflow.model import TensorFlowModel
endpoint = 'sagemaker-tensorflow-serving-2021-10-28-11-18-34-001' #get endpoint name from SageMaker > endpoints
predictor=sagemaker.tensorflow.model.TensorFlowPredictor(endpoint, sagemaker_session)
# .predict send the data to our endpoint
#data = np.asarray(["what the shit"]) #<-- update this to have inputs for your model
predictor.predict(["this is not a spam"])
And I am getting this error
ModelError: An error occurred (ModelError) when calling the InvokeEndpoint operation: Received client error (400) from primary with message "{ "error": "Session was not created with a graph before Run()!" }
Can someone please help me.
Instead of saving model as h5 use below method.
model.save("export/Servo/1/")
for some reason it expects exact format. Also, please remove if any hidden file is there in this folder.
This will save the model already in protobuf format.

Integrating a 2D Medical Imaging X-Ray classifier which was trained on jpegs with a script which receives DCM files to be able to diagnose dicom files

Below is the order of how I am going to present my problem:
First I will show you the script .py that I am using to run the web app in a local host(flask app). This web app is a classifier which shows you whether a person has either Viral Pneumonia, Bacterial Pneumonia or they are Normal. Thus there are three classes(Viral, Bacterial or Normal) looking from chest x-rays which are in jpeg format.
Second I will show you the differnt .py script for Binary Classification for Pneumonia which is taking in raw dicom files and converting them into numpy arrays before they are diagnosed.
So to achieve diagnosis I am trying to integrate my app.py script which takes in jpegs, with the Pneumonia binary classification which takes in dicom files so as to take advantage of the dicom processing function of the second script but using all of the information and weights of the Viral and Bacterial one that I have, so that it can be used in a clinical setup. Clinical setups use dicom files not jpegs, that is why I am trying to combine these two scripts to reach the goal.
Below is my app.py script for Viral and Bacterial Pneumonia Classification which takes in jpegs, which I am trying to integrate on the other script that I am going to attach further below:
#::: Import modules and packages :::
# Flask utils
from flask import Flask, redirect, url_for, request, render_template
from werkzeug.utils import secure_filename
from gevent.pywsgi import WSGIServer
# Import Keras dependencies
from tensorflow.keras.models import model_from_json
from tensorflow.python.framework import ops
ops.reset_default_graph()
from keras.preprocessing import image
# Import other dependecies
import numpy as np
import h5py
from PIL import Image
import PIL
import os
#::: Flask App Engine :::
# Define a Flask app
app = Flask(__name__)
# ::: Prepare Keras Model :::
# Model files
MODEL_ARCHITECTURE = './model/model_adam.json'
MODEL_WEIGHTS = './model/model_100_eopchs_adam_20190807.h5'
# Load the model from external files
json_file = open(MODEL_ARCHITECTURE)
loaded_model_json = json_file.read()
json_file.close()
model = model_from_json(loaded_model_json)
# Get weights into the model
model.load_weights(MODEL_WEIGHTS)
print('Model loaded. Check http://127.0.0.1:5000/')
# ::: MODEL FUNCTIONS :::
def model_predict(img_path, model):
'''
Args:
-- img_path : an URL path where a given image is stored.
-- model : a given Keras CNN model.
'''
IMG = image.load_img(img_path).convert('L')
print(type(IMG))
# Pre-processing the image
IMG_ = IMG.resize((257, 342))
print(type(IMG_))
IMG_ = np.asarray(IMG_)
print(IMG_.shape)
IMG_ = np.true_divide(IMG_, 255)
IMG_ = IMG_.reshape(1, 342, 257, 1)
print(type(IMG_), IMG_.shape)
print(model)
model.compile(loss='categorical_crossentropy', metrics=['accuracy'], optimizer='rmsprop')
predict_x = model.predict(IMG_)
print(predict_x)
prediction = np.argmax(predict_x,axis=1)
print(prediction)
return prediction
# ::: FLASK ROUTES
#app.route('/', methods=['GET'])
def index():
# Main Page
return render_template('index.html')
#app.route('/predict', methods=['GET', 'POST'])
def upload():
# Constants:
classes = {'TRAIN': ['BACTERIA', 'NORMAL', 'VIRUS'],
'VALIDATION': ['BACTERIA', 'NORMAL'],
'TEST': ['BACTERIA', 'NORMAL', 'VIRUS']}
if request.method == 'POST':
# Get the file from post request
f = request.files['file']
# Save the file to ./uploads
basepath = os.path.dirname(__file__)
file_path = os.path.join(
basepath, 'uploads', secure_filename(f.filename))
f.save(file_path)
# Make a prediction
prediction = model_predict(file_path, model)
predicted_class = classes['TRAIN'][prediction[0]]
print('We think that is {}.'.format(predicted_class.lower()))
return str(predicted_class).lower()
if __name__ == '__main__':
app.run(debug = True)`
Below again is the already functioning script of Pneumonia binary classification which is taking in dicom files that I am trying to integrate with the weights and preprocessing information of the Viral and Bacterial classifier that I want to use:
## Loading standard modules and libraries
import numpy as np
import pandas as pd
import pydicom
%matplotlib inline
import matplotlib.pyplot as plt
import keras
from keras.models import Sequential
from keras.layers import Dense
from keras.models import model_from_json
from skimage.transform import resize
# This function reads in a .dcm file, checks the important fields for our device, and returns a numpy array
# of just the imaging data
def check_dicom(filename):
print('Loading file {} ...'.format(filename))
ds = pydicom.dcmread(filename)
if (ds.BodyPartExamined !='CHEST') | (ds.Modality !='DX') | (ds.PatientPosition not in ['PA', 'AP']):
print('The image is not valid because the image position, the image type or the body part is not as per standards')
return
else:
print('ID:', ds.PatientID,
'Age:', ds.PatientAge,
'Modality:', ds.Modality,
'Postion: ', ds.PatientPosition,
'Body Part: ', ds.BodyPartExamined,
'Study Desc: ', ds.StudyDescription)
img = ds.pixel_array
return img
# This function takes the numpy array output by check_dicom and
# runs the appropriate pre-processing needed for our model input
def preprocess_image(img,img_mean,img_std,img_size):
# todo
img = resize(img, (224,224))
img = img / 255.0
grey_img = (img - img_mean) / img_std
proc_img = np.zeros((224,224,3))
proc_img[:, :, 0] = grey_img
proc_img[:, :, 1] = grey_img
proc_img[:, :, 2] = grey_img
proc_img = np.resize(proc_img, img_size)
return proc_img
# This function loads in our trained model w/ weights and compiles it
def load_model(model_path, weight_path):
# todo
json_file = open(model_path, 'r')
loaded_model_json = json_file.read()
json_file.close()
model = model_from_json(loaded_model_json)
model.load_weights(weight_path)
return model
# This function uses our device's threshold parameters to predict whether or not
# the image shows the presence of pneumonia using our trained model
def predict_image(model, img, thresh):
# todo
result = model.predict(img)
print('Predicted value:', result)
predict=result[0]
prediction = "Negative"
if(predict > thresh):
prediction = "Positive"
return prediction
# This function uses our device's threshold parameters to predict whether or not
# the image shows the presence of pneumonia using our trained model
def predict_image(model, img, thresh):
# todo
result = model.predict(img)
print('Predicted value:', result)
predict=result[0]
prediction = "Negative"
if(predict > thresh):
prediction = "Positive"
return prediction
test_dicoms = ['test1.dcm','test2.dcm','test3.dcm','test4.dcm','test5.dcm','test6.dcm']
model_path = "my_model2.json" #path to saved model
weight_path = "xray_class_my_model2.best.hdf5" #path to saved best weights
IMG_SIZE=(1,224,224,3) # This might be different if you did not use vgg16
img_mean = 0.49262813 # mean image value from Build and train model line 22
img_std = 0.24496286 # loads the std dev from Build and train model line 22
my_model = load_model(model_path, weight_path) #loads model
thresh = 0.62786263 #threshold value for New Model2 from Build and train model line 66 at 80% Precision
# use the .dcm files to test your prediction
for i in test_dicoms:
img = np.array([])
img = check_dicom(i)
if img is None:
continue
img_proc = preprocess_image(img,img_mean,img_std,IMG_SIZE)
pred = predict_image(my_model,img_proc,thresh)
print('Model Classification:', pred , 'for Pneumonia' )
print('--------------------------------------------------------------------------------------------------------')
Output of above script:
Loading file test1.dcm ...
ID: 2 Age: 81 Modality: DX Postion: PA Body Part: CHEST Study Desc: No Finding
Predicted value: [[0.4775539]]
Model Classification: Negative for Pneumonia
--------------------------------------------------------------------------------------------------------
Loading file test2.dcm ...
ID: 1 Age: 58 Modality: DX Postion: AP Body Part: CHEST Study Desc: Cardiomegaly
Predicted value: [[0.47687072]]
Model Classification: Negative for Pneumonia
--------------------------------------------------------------------------------------------------------
Loading file test3.dcm ...
ID: 61 Age: 77 Modality: DX Postion: AP Body Part: CHEST Study Desc: Effusion
Predicted value: [[0.47764364]]
Model Classification: Negative for Pneumonia
--------------------------------------------------------------------------------------------------------
Loading file test4.dcm ...
The image is not valid because the image position, the image type or the body part is not as per standards
Loading file test5.dcm ...
The image is not valid because the image position, the image type or the body part is not as per standards
Loading file test6.dcm ...
The image is not valid because the image position, the image type or the body part is not as per standards
Threshold of 0.62786263 is considered at 80% Precision
Below is what I have tried so far but the diagnosis I am getting is always Viral on each and every dicom sample:
## Loading standard modules and libraries
import numpy as np
import pandas as pd
import pydicom
from PIL import Image
#%matplotlib inline
import matplotlib.pyplot as plt
import keras
from keras.models import Sequential
from keras.layers import Dense
from keras.models import model_from_json
from keras.preprocessing import image
from skimage.transform import resize
# This function reads in a .dcm file, checks the important fields for our device, and returns a numpy array
# of just the imaging data
def check_dicom(filename):
print('Loading file {} ...'.format(filename))
ds = pydicom.dcmread(filename)
if (ds.BodyPartExamined !='CHEST'): #| (ds.Modality !='DX'): #| (ds.PatientPosition not in ['PA', 'AP']):
print('The image is not valid because the image position, the image type or the body part is not as per standards')
return
else:
print('ID:', ds.PatientID,
'Age:', ds.PatientAge,
'Modality:', ds.Modality,
'Postion: ', ds.PatientPosition,
'Body Part: ', ds.BodyPartExamined,
'Study Desc: ', ds.StudyDescription)
img = ds.pixel_array
return img
# This function takes the numpy array output by check_dicom and
# runs the appropriate pre-processing needed for our model input
def preprocess_image(img):
# todo
#im = np.reshape(img, (342,257 ))
#im = np.arange(257)
#img = Image.fromarray(im)
#img = image.load_img(img).convert('L')
img = resize(img, (342,257))
grey_img = img / 255.0
#grey_img = (img - img_mean) / img_std
proc_img = np.zeros((1,342,257,1))
proc_img[:, :, :, 0] = grey_img
#proc_img[:, :, :, 1] = grey_img
#proc_img[:, :, :, 2] = grey_img
proc_img = proc_img.reshape(1, 342, 257, 1)
return proc_img
# This function loads in our trained model w/ weights and compiles it
def load_model(model_path, weight_path):
# todo
json_file = open(model_path, 'r')
loaded_model_json = json_file.read()
json_file.close()
model = model_from_json(loaded_model_json)
model.load_weights(weight_path)
model.compile(loss='categorical_crossentropy', metrics=['accuracy'], optimizer='rmsprop')
return model
# This function uses our device's threshold parameters to predict whether or not
# the image shows the presence of pneumonia using our trained model
def predict_image(model, img):
# todo
model.compile(loss='categorical_crossentropy', metrics=['accuracy'], optimizer='rmsprop')
#x = np.expand_dims(img, axis=0)
predict_x= model.predict(img)
print(predict_x)
prediction = np.argmax(predict_x,axis=1)
print(prediction)
return prediction
test_dicoms = ['test3.dcm','test2.dcm','test1.dcm','test4.dcm','test5.dcm','test6.dcm']
model_path = "model_adam.json" #path to saved model
weight_path = "model.h5" #path to saved best weights
#IMG_SIZE=(1,342,257,1) # This might be different if you did not use vgg16
#img_mean = 0.49262813 # mean image value from Build and train model line 22
#img_std = 0.24496286 # loads the std dev from Build and train model line 22
#my_model = load_model(model_path, weight_path) #loads model
#thresh = 0.62786263 #threshold value for New Model2 from Build and train model line 66 at 80% Precision
# use the .dcm files to test your prediction
for i in test_dicoms:
img = np.array([])
img = check_dicom(i)
if img is None:
continue
classes = {'TRAIN': ['BACTERIAL', 'NORMAL', 'VIRAL'],
'VALIDATION': ['BACTERIA', 'NORMAL'],
'TEST': ['BACTERIA', 'NORMAL', 'VIRUS']}
img_proc = preprocess_image(img)
prediction = predict_image(load_model(model_path, weight_path),img_proc)
predicted_class = classes['TRAIN'][int(prediction[0])]
print('Model Classification:', predicted_class, 'Pneumonia' )
print('--------------------------------------------------------------------------------------------------------')
Below is the output:
2022-01-02 10:50:00.817561: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory
2022-01-02 10:50:00.817601: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
Loading file test3.dcm ...
ID: 61 Age: 77 Modality: DX Postion: AP Body Part: CHEST Study Desc: Effusion
2022-01-02 10:50:02.652828: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcuda.so.1'; dlerror: libcuda.so.1: cannot open shared object file: No such file or directory
2022-01-02 10:50:02.652859: W tensorflow/stream_executor/cuda/cuda_driver.cc:269] failed call to cuInit: UNKNOWN ERROR (303)
2022-01-02 10:50:02.652899: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:156] kernel driver does not appear to be running on this host (Wisdom-HP-250-G3-Notebook-PC): /proc/driver/nvidia/version does not exist
2022-01-02 10:50:02.653123: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
[[0.01132523 0.00254696 0.98612785]]
[2]
Model Classification: VIRAL Pneumonia
--------------------------------------------------------------------------------------------------------
Loading file test2.dcm ...
ID: 1 Age: 58 Modality: DX Postion: AP Body Part: CHEST Study Desc: Cardiomegaly
[[0.01112939 0.00251635 0.9863543 ]]
[2]
Model Classification: VIRAL Pneumonia
--------------------------------------------------------------------------------------------------------
Loading file test1.dcm ...
ID: 2 Age: 81 Modality: DX Postion: PA Body Part: CHEST Study Desc: No Finding
[[0.01128576 0.00255111 0.9861631 ]]
[2]
Model Classification: VIRAL Pneumonia
--------------------------------------------------------------------------------------------------------
Loading file test4.dcm ...
The image is not valid because the image position, the image type or the body part is not as per standards
Loading file test5.dcm ...
ID: 2 Age: 81 Modality: CT Postion: PA Body Part: CHEST Study Desc: No Finding
[[0.01128576 0.00255111 0.9861631 ]]
[2]
Model Classification: VIRAL Pneumonia
--------------------------------------------------------------------------------------------------------
Loading file test6.dcm ...
ID: 2 Age: 81 Modality: DX Postion: XX Body Part: CHEST Study Desc: No Finding
WARNING:tensorflow:5 out of the last 5 calls to <function Model.make_predict_function.<locals>.predict_function at 0x7fba38ed19d0> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating #tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your #tf.function outside of the loop. For (2), #tf.function has experimental_relax_shapes=True option that relaxes argument shapes that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details.
[[0.01128576 0.00255111 0.9861631 ]]
[2]
Model Classification: VIRAL Pneumonia
---------------------------------------
My suspicion is that I did it wrong on the image preprocessing steps when I have integrated these two scripts (Remember: The goal is to take advantage of the Dicom reading function of the second script). Thus the model is taking in and predicting wrong input altogether due to wrong array arrangements on trying to preprocess when I have integrated these two scripts.
If in need of some information on parameters in the jupyter training presentation of the model kindly highlight.
When a classifier work okay in train/test but not when doing inference in production, a very common reason is that the training data was processed differently from the production data. The fix is to make sure it is processed the same, ideally using the same bit of code.
How were the jpegs the classifier was trained on processed? Do the originally come from dicoms? If yes, what was the exact code for the conversion?
How were the jpegs loaded during training? Pay special attention to bits that modify the data rather than merely copy it, such as grey_img = (img - img_mean) / img_std and the other commented out lines in your code (maybe they were not commented out during training)
If you copy the dicom->jpeg conversion from 1 and the jpeg loading from 2, you will probably have a working prediction
The below dicom to jpeg conversion function did the job for me:
def take_dicom(dicomname):
ds = read_file('Dicom_files/' + dicomname)
im = fromarray(ds.pixel_array)
final_img = im.save('./Jpeg/' + dicomname + '.jpg')
pure_jpg = dicomname + '.jpg'
return pure_jpg
Just had to use the os function to point my prediction function to where it should pick these jpegs before they are preprocessed and diagnosed:
def preprocess_image(pure_jpg):
'''
Args:
-- img_path : an URL path where a given image is stored.
-- model : a given Keras CNN model.
'''
#print(pure_jpg)
basepath = os.path.dirname('./Jpeg/')
file_path = os.path.join(
basepath, img)
#image = take_dicom(file_path)
#print(str(image))
IMG = image.load_img(file_path).convert('L')
#print(IMG)
#print(type(IMG))
# Pre-processing the image
IMG_ = IMG.resize((257, 342))
#print(type(IMG_))
IMG_ = np.asarray(IMG_)
#print(IMG_.shape)
IMG_ = np.true_divide(IMG_, 255)
IMG_ = IMG_.reshape(1, 342, 257, 1)
#print(type(IMG_), IMG_.shape)
return IMG_
However, the problem is that it's only working for the following two dicom imaging modalities:
DX (Digital X-Ray)
CT (Computed Tormography)
CR (Computed Radiography) dicom images are failing to convert.

SpaCy: how do you add custom NER labels to a pre-trained model?

I am new to SpaCy and NLP. I am using SpaCy v 3.1 and Python 3.9.7 64-bit.
My objective: to use a pre-trained SpaCy model (en_core_web_sm) and add a set of custom labels to the existing NER labels (GPE, PERSON, MONEY, etc.) so that the model can recognize both the default AND the custom entities.
I've looked at the SpaCy documentation and what I need seems to be an EntityRecogniser, specifically a new pipe.
However, it is not really clear to me at what point in my workflow I should add this new pipe, since in SpaCy 3 the training happens in CLI, and from the docs it's not even clear to me where the pre-trained model is called.
Any tutorials or pointers you might have are highly appreciated.
This is what I think should be done, but I am not sure how:
import spacy
from spacy import displacy
from spacy_langdetect import LanguageDetector
from spacy.language import Language
from spacy.pipeline import EntityRecognizer
# Load model
nlp = spacy.load("en_core_web_sm")
# Register custom component and turn a simple function into a pipeline component
#Language.factory('new-ner')
def create_bespoke_ner(nlp, name):
# Train the new pipeline with custom labels here??
return LanguageDetector()
# Add custom pipe
custom = nlp.add_pipe("new-ner")
This is what my config file looks like so far. I suspect my new pipe needs to go next to "tok2vec" and "ner".
[paths]
train = null
dev = null
vectors = null
init_tok2vec = null
[system]
gpu_allocator = null
seed = 0
[nlp]
lang = "en"
pipeline = ["tok2vec","ner"]
batch_size = 1000
disabled = []
before_creation = null
after_creation = null
after_pipeline_creation = null
tokenizer = {"#tokenizers":"spacy.Tokenizer.v1"}
[components]
[components.ner]
factory = "ner"
incorrect_spans_key = null
moves = null
update_with_oracle_cut_size = 100
For Spacy 3.2 I did it this way:
import spacy
import random
from spacy import util
from spacy.tokens import Doc
from spacy.training import Example
from spacy.language import Language
def print_doc_entities(_doc: Doc):
if _doc.ents:
for _ent in _doc.ents:
print(f" {_ent.text} {_ent.label_}")
else:
print(" NONE")
def customizing_pipeline_component(nlp: Language):
# NOTE: Starting from Spacy 3.0, training via Python API was changed. For information see - https://spacy.io/usage/v3#migrating-training-python
train_data = [
('We need to deliver it to Festy.', [(25, 30, 'DISTRICT')]),
('I like red oranges', [])
]
# Result before training
print(f"\nResult BEFORE training:")
doc = nlp(u'I need a taxi to Festy.')
print_doc_entities(doc)
# Disable all pipe components except 'ner'
disabled_pipes = []
for pipe_name in nlp.pipe_names:
if pipe_name != 'ner':
nlp.disable_pipes(pipe_name)
disabled_pipes.append(pipe_name)
print(" Training ...")
optimizer = nlp.create_optimizer()
for _ in range(25):
random.shuffle(train_data)
for raw_text, entity_offsets in train_data:
doc = nlp.make_doc(raw_text)
example = Example.from_dict(doc, {"entities": entity_offsets})
nlp.update([example], sgd=optimizer)
# Enable all previously disabled pipe components
for pipe_name in disabled_pipes:
nlp.enable_pipe(pipe_name)
# Result after training
print(f"Result AFTER training:")
doc = nlp(u'I need a taxi to Festy.')
print_doc_entities(doc)
def main():
nlp = spacy.load('en_core_web_sm')
customizing_pipeline_component(nlp)
if __name__ == '__main__':
main()

PipelineException: No mask_token ([MASK]) found on the input

I am getting this error "PipelineException: No mask_token ([MASK]) found on the input"
when I run this line.
fill_mask("Auto Car .")
I am running it on Colab.
My Code:
from transformers import BertTokenizer, BertForMaskedLM
from pathlib import Path
from tokenizers import ByteLevelBPETokenizer
from transformers import BertTokenizer, BertForMaskedLM
paths = [str(x) for x in Path(".").glob("**/*.txt")]
print(paths)
bert_tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
from transformers import BertModel, BertConfig
configuration = BertConfig()
model = BertModel(configuration)
configuration = model.config
print(configuration)
model = BertForMaskedLM.from_pretrained("bert-base-uncased")
from transformers import LineByLineTextDataset
dataset = LineByLineTextDataset(
tokenizer=bert_tokenizer,
file_path="./kant.txt",
block_size=128,
)
from transformers import DataCollatorForLanguageModeling
data_collator = DataCollatorForLanguageModeling(
tokenizer=bert_tokenizer, mlm=True, mlm_probability=0.15
)
from transformers import Trainer, TrainingArguments
training_args = TrainingArguments(
output_dir="./KantaiBERT",
overwrite_output_dir=True,
num_train_epochs=1,
per_device_train_batch_size=64,
save_steps=10_000,
save_total_limit=2,
)
trainer = Trainer(
model=model,
args=training_args,
data_collator=data_collator,
train_dataset=dataset,
)
trainer.train()
from transformers import pipeline
fill_mask = pipeline(
"fill-mask",
model=model,
tokenizer=bert_tokenizer,
device=0,
)
fill_mask("Auto Car <mask>."). # This line is giving me the error...
The last line is giving me the error mentioned above. Please let me know what I am doing wrong or what I have to do in order to remove this error.
Complete error: "f"No mask_token ({self.tokenizer.mask_token}) found on the input","
Even if you have already found the error, a recommendation to avoid it in the future. Instead of calling
fill_mask("Auto Car <mask>.")
you can do the following to be more flexible when you use different models:
MASK_TOKEN = tokenizer.mask_token
fill_mask("Auto Car {}.".format(MASK_TOKEN))
If the model implementation changes the token to be identified (some identify , some [mask]), then you get into trouble. It is better to use f strings and pass the argument. The advantage of using an f-string is that it is intuitive to understand.
The following code works for me -
from transformers import BertTokenizer
tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
mask_fill = pipeline("fill-mask", model="bert-base-uncased")
mask_fill(f"The gaming laptop is {tokenizer.mask_token} and I have loved playing games on it.", top_k=2)

Categories