minesh1291

How to install CUDA & cuDNN on Ubuntu 22.04

Install NVIDIA drivers

Update & upgrade

sudo apt update && sudo apt upgrade

Remove previous NVIDIA installation

minesh1291

from transformers import Trainer, TrainingArguments

training_args = TrainingArguments(
    output_dir="./logs/model_name",
    logging_dir="./logs/runs",
    overwrite_output_dir=True,
    do_train=True,
    per_device_train_batch_size=32,
    num_train_epochs=1,
    evaluate_during_training=True,

minesh1291

from multimodal_transformers.model import AutoModelWithTabular, TabularConfig
from transformers import AutoConfig

num_labels = len(np.unique(torch_dataset, labels))
config = AutoConfig.from_pretrained('bert-base-uncased')
tabular_config = TabularConfig(
    num_labels=num_labels,
    cat_feat_dim=torch_dataset.cat_feats.shape[1],
    numerical_feat_dim=torch_dataset.numerical_feats.shape[1],
    combine_feat_method='weighted_feature_sum_on_transformer_cat_and_numerical_feats',

minesh1291

import pandas as pd
from multimodal_transformers.data import load_data
from transformers import AutoTokenizer

data_df = pd.read_csv('Womens Clothing E-Commerce Reviews.csv')
text_cols = ['Title', 'Review Text']
# The label col is expected to contain integers from 0 to N_classes - 1
label_col = 'Recommended IND' 
categorical_cols = ['Clothing ID', 'Division Name', 'Department Name', 'Class Name']
numerical_cols = ['Rating', 'Age', 'Positive Feedback Count']

minesh1291

minesh1291

"""
An implementation of the pytorch Subset that returns an instance of the original dataset with a reduced number of items.
This has two benefits:
  - It allows to stil access the attributes of the Dataset class, such as methods, or properties.
  - You can use the usual python index notation with slices to chunk the dataset, rather than creating a list of indices

"""
class Dataset(object):
  def __init__(self, iterable):
    self.items = iterable

minesh1291

import json
import numpy as np
from pycocotools import mask
from skimage import measure

ground_truth_binary_mask = np.array([[  0,   0,   0,   0,   0,   0,   0,   0,   0,   0],
                                     [  0,   0,   0,   0,   0,   0,   0,   0,   0,   0],
                                     [  0,   0,   0,   0,   0,   1,   1,   1,   0,   0],
                                     [  0,   0,   0,   0,   0,   1,   1,   1,   0,   0],
                                     [  0,   0,   0,   0,   0,   1,   1,   1,   0,   0],

minesh1291

from pycocotools.coco import COCO
import numpy as np
import cv2

import os

coco_dataset_path = "/export/public/MS-COCO-2017/"
coco = COCO(coco_dataset_path + "annotations/instances_val2017.json")

minesh1291

import tensorflow as tf


def _bytestring_feature(list_of_bytestrings):
    return tf.train.Feature(bytes_list=tf.train.BytesList(value=list_of_bytestrings))


def _int_feature(list_of_ints):  # int64
    return tf.train.Feature(int64_list=tf.train.Int64List(value=list_of_ints))

minesh1291

import argparse
import math
import os

import numpy as np
import pandas as pd
import tensorflow as tf


_BASE_DIR = os.path.dirname(os.path.abspath(__file__))