SP2203

# Imports
import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt

import keras
from keras.datasets import mnist
from keras.layers import Dense, Flatten, Input
from keras.layers import Conv2D, MaxPooling2D

SP2203

import onnx
print(onnx.__version__)

SP2203

import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt

import tensorflow as tf
from tensorflow.keras import layers
from tensorflow.keras.datasets import mnist
from tensorflow.keras.layers import Dense, Flatten, Input, Dropout
from tensorflow.keras.layers import Conv2D, MaxPooling2D

SP2203

import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt

import tensorflow as tf
from tensorflow.keras import layers
from tensorflow.keras.datasets import mnist
from tensorflow.keras.layers import Dense, Flatten, Input, Dropout
from tensorflow.keras.layers import Conv2D, MaxPooling2D, BatchNormalization

SP2203

import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt

import tensorflow as tf
from tensorflow.keras import layers
from tensorflow.keras.datasets import mnist
from tensorflow.keras.layers import Dense, Flatten, Input, Dropout
from tensorflow.keras.layers import Conv2D, MaxPooling2D, BatchNormalization

SP2203

# # Load pretrained model and tokenizer
from transformers import AutoModel, AutoTokenizer

model_name = "sentence-transformers/all-MiniLM-L6-v2"

tokenizer = AutoTokenizer.from_pretrained(model_name, 
                                          do_lower_case=True )

model = AutoModel.from_pretrained(model_name )

SP2203

import time
import pandas as pd
import numpy as np

from tqdm import tqdm

df = pd.read_csv('./imdb_top_1000.csv', usecols=['Overview'])

total_samples = len(df)

SP2203

import onnxruntime
import numpy as np

sess_options = onnxruntime.SessionOptions()

session = onnxruntime.InferenceSession(export_model_path, 
                                       sess_options, 
                                       providers=['CPUExecutionProvider'])

latency = []

SP2203

device = torch.device("cuda")

# Set model to inference mode, which is required before exporting 
# the model because some operators behave differently in
# inference and training mode.

model.eval()
model.to(device)

total_samples = len(df)

SP2203

import onnxruntime
import numpy as np

sess_options = onnxruntime.SessionOptions()

session = onnxruntime.InferenceSession(export_model_path, 
                                       sess_options, 
                                       providers=['CUDAExecutionProvider'])

latency = []