14,938 Topics

Member Avatar for
Member Avatar for usmanmalik57

On March 4, 2024, [Anthropic](https://www.anthropic.com/) launched the [Claude 3 family of large language models](https://www.anthropic.com/news/claude-3-family). Anthropic claimed that its Claude 3 Opus model outperforms GPT-4 on various benchmarks. Intrigued by Anthropic's claim, I performed a simple test to compare the performances of Claude 3 Opus, [Google Gemini Pro](https://deepmind.google/technologies/gemini/#introduction), and [OpenAI's GPT-4](https://openai.com/research/gpt-4) …

1
15
Member Avatar for usmanmalik57

In the rapidly evolving field of Natural Language Processing (NLP), open-source large language models (LLMs) are becoming increasingly popular as they are free to use. Among these, the [Mistral](https://docs.mistral.ai/models/) family of models stands out as a state-of-the-art model that is freely accessible to the public. Comparable in performance to the …

2
21
Member Avatar for vegaseat

Using PySide's QAbstractTableModel allows you to easily customize a widget like QTableView and make it more generic in its application. Here we use it to present solvent data in tabular form and sort each column content by simply clicking on the header. You can feed it any data as long …

Member Avatar for Mark_94
5
6K
Member Avatar for SEO_935

AI-powered code reviews are bringing about a revolution in the way developers collaborate, enabling more efficient, accurate, and thorough evaluations of code prior to its integration into the central project repository. This transformation is made possible by leveraging machine learning and artificial intelligence to automate and enhance different facets of …

0
31
Member Avatar for usmanmalik57

In a previous article, I explained [how to fine-tune Google's Gemma model for text classification](https://www.daniweb.com/programming/computer-science/tutorials/541544/fine-tuning-google-gemma-model-for-text-classification-in-python). In this article, I will explain how you can improve performance of a pretrained large language model (LLM) using retrieval augmented generation (RAG) technique. So, let's begin without ado. ## What is Retrieval Augmented Generation …

2
127
Member Avatar for usmanmalik57

On February 21, 2024, Google released [Gemma](https://ai.google.dev/gemma), a family of state-of-the-art open-source large language models (LLMs). As per initial results, its 7b (seven billion parameter) version is known to perform better than Meta's [Llama 2](https://llama.meta.com/), the previous state-of-the-art open-source LLM. As always, my first test with any new open-source LLM …

1
253
Member Avatar for usmanmalik57

In a previous article, I explained [how to extract tabular data from PDF image documents using Multimodal Google Gemini Pro](https://www.daniweb.com/programming/computer-science/tutorials/541449/pdf-image-table-extractor-web-app-with-google-gemini-pro-and-streamlit#post2296083). However, there are a couple of disadvantages with Google Gemini Pro. First, Google Gemini Pro is not free, and second, it needs complex prompt engineering to retrieve table, columns, and …

1
69
Member Avatar for Tom_45

I am trying to extract three values from the td tags in an html downloaded file. <tr align="right"><td>236</td><td>Roy</td><td>Allyson</td> <tr align="right"><td>237</td><td>Marvin</td><td>Pamela</td> <tr align="right"><td>238</td><td>Micah</td><td>Kristine</td> <tr align="right"><td>239</td><td>Collin</td><td>Raquel</td> I am using the pattern match = re.findall(r'<td.?>([\d+])([.?])*<\/td>', file) The file is created with a read() statement. The output should look like (236, "Roy", "Allyson") (237, …

Member Avatar for Tom_45
1
76
Member Avatar for Tom_45

I am trying to extract three values from the td tags in an html downloaded file. <tr align="right"><td>236</td><td>Roy</td><td>Allyson</td> <tr align="right"><td>237</td><td>Marvin</td><td>Pamela</td> <tr align="right"><td>238</td><td>Micah</td><td>Kristine</td> <tr align="right"><td>239</td><td>Collin</td><td>Raquel</td> I am using the pattern match = re.findall(r'<td.*?>([\d+])([.*?])*<\/td>', file) The file is created with a read() statement. The output should look like (236, "Roy", "Allyson") (237, …

Member Avatar for Tom_45
1
81
Member Avatar for Tom_45

I am working on an exercise from Google's Python class dealing with popular baby names. I have the program running properly when using only one filename, but when I try to use the wildcard to get all files with baby####.html files I get differing errors every time I run the …

Member Avatar for Tom_45
2
41
Member Avatar for usmanmalik57

In my previous article, I explained [how to convert PDF image to CSV using Multimodal Google Gemini Pro](https://www.daniweb.com/programming/computer-science/tutorials/541365/converting-pdf-image-to-csv-using-multimodal-google-gemini-pro). To do so, I wrote a Python script that passes text command to [Google Gemino Pro](https://blog.google/technology/ai/google-gemini-ai/) for extracting tables from PDF images and storing them in a CSV file. In this article, …

1
79
Member Avatar for amrutraj

I am building a crawler+parser in Python. It has to be run for, like 20 hours. How can I modify the code such that the code execution pauses (before next urllib2.urlopen) when the internet is disconnected, and AUTOMATICALLY resumes with the same variable values, when the internet connection is back …

Member Avatar for musawir_2
0
252
Member Avatar for usmanmalik57

Integrating language models like ChatGPT into third-party applications has become increasingly popular due to their ability to comprehend and generate human-like text. However, it's crucial to acknowledge the limitations of ChatGPT, such as its knowledge cut-off date in September 2021 and its inability to access external sources like Wikipedia or …

Member Avatar for catherine_11
3
1K
Member Avatar for cored0mp

I'll admit that I have an opinion about this. Is the point of professional coding to write creative software or to write software that adheres closely to standards?

Member Avatar for cored0mp
0
91
Member Avatar for usmanmalik57

## Introduction ## In a previous article, I explained [how to fine-tune the vision transformer model for image classification in PyTorch](https://www.daniweb.com/programming/computer-science/tutorials/540749/fine-tuning-vision-transformer-for-image-classification-in-pytorch). In this article, I will explain how to fine-tune the pre-trained OpenAI Whisper model for audio classification in PyTorch. Audio classification is an important task that can be applied …

Member Avatar for habi_2
2
657
Member Avatar for usmanmalik57

In this article, you will learn to use [Google Gemini Pro](https://blog.google/technology/ai/google-gemini-ai/), a state-of-the-art multimodal generative model, to extract information from PDF and convert it to CSV files. You will use a simple text prompt to tell Google Gemini Pro about the information you want to extract. This is a valuable …

2
116
Member Avatar for usmanmalik57

In this article, you will learn how to track faces within a video using the Python DeepFace library. Additionally, you'll discover how to include portions of the video background in face tracking by implementing custom methods that utilize the DeepFace library's `extract_faces()` method for face extraction. I explained how to …

Member Avatar for EdwardMatthew
1
89
Member Avatar for cored0mp

I had some fun this weekend having a go at pdfkit with mixed results. Can anyone nominate a candidate for best PDF writing?

Member Avatar for cored0mp
0
28
Member Avatar for usmanmalik57

In this article, we will compare two state-of-the-art large language models for zero-shot text classification: [Google Gemini Pro](https://deepmind.google/technologies/gemini/#introduction) and [OpenAI GPT-4](https://openai.com/research/gpt-4). Zero-shot text classification is a task where a model is trained on a set of labeled examples but can then classify new examples from previously unseen classes. This is …

1
45
Member Avatar for cored0mp

Hey Gang! OK today I am having trouble with my transaction processing application implemented in python/MySQL. Here is some "working" testing code. import psycopg2 from psycopg2 import Error import binascii from binascii import unhexlify import mysql.connector as mysql sql='''CREATE PROCEDURE testprocedure(OUT tacos INT) BEGIN show tables; SET tacos := 1 …

Member Avatar for Dani
1
25
Member Avatar for FarrisFahad
Member Avatar for Dani
2
33
Member Avatar for usmanmalik57

## Introduction ## This tutorial explains how to perform multiple-label text classification using the [Hugging Face](https://huggingface.co/) transformers library. Hugging Face library implements advanced transformer architectures, proven to be state-of-the-art for various natural language processing tasks, including text classification. Hugging Face library provides trainable transformer models in three flavors: 1. Via …

Member Avatar for Aravind_11
1
855
Member Avatar for usmanmalik57

I recently tackled a challenging research task involving multimodal data for a classification problem using [TensorFlow Keras](https://www.tensorflow.org/guide/keras). One of the trickiest aspects was figuring out how to load multimodal data in batches from storage efficiently. While TensorFlow Keras offers helpful functions for batch-loading images from various sources, the documentation and …

2
24
Member Avatar for usmanmalik57

Sentiment analysis, a subfield of Natural Language Processing (NLP), aims to discern and classify the underlying sentiment or emotion expressed in textual data. Whether it is understanding customers' opinions about a product, analyzing social media posts, or gauging public sentiment towards a political event, sentiment analysis plays a vital role …

Member Avatar for Abdul_116
6
2K
Member Avatar for usmanmalik57

In a [previous tutorial](https://www.daniweb.com/programming/computer-science/tutorials/541123/stock-price-prediction-using-1d-cnn-in-tensorflow-keras), I covered how to predict future stock prices using a deep learning model with 1D CNN layers. This method is effective for basic time series forecasting. Recently, I've enhanced this model by not just considering past closing prices but also factors like Open, High, Low, Volume, …

0
43
Member Avatar for usmanmalik57

A video is a series of images, or frames, shown in rapid succession. Its frame rate, measured in frames per second (FPS), dictates the display speed. For instance, a 30 FPS video shows 30 frames each second. The frame count and frame rate determine a video's detail, smoothness, file size, …

Member Avatar for usmanmalik57
2
118
Member Avatar for usmanmalik57

## Introduction ## Loss functions are the driving force behind all machine learning algorithms. They quantify how well our models are performing by calculating the difference between the predicted and actual outcomes. The goal of every machine learning algorithm is to minimize this loss function, thereby improving the model’s accuracy. …

Member Avatar for AndreRet
3
166
Member Avatar for usmanmalik57

As a researcher, I have often found myself buried under a mountain of research articles, each promising insights and breakthroughs crucial for my work. The sheer volume of information is overwhelming, and the time it takes to extract the relevant data can be daunting. However, extracting meaningful information from research …

Member Avatar for AndreRet
3
117
Member Avatar for usmanmalik57

Facial emotion detection, as the name suggests, involves detecting emotions from faces in images or videos. Recently, I was working on a facial emotion detection task and came across the DeepFace library that implements various state-of-the-art facial emotion detection models. However, in my experience, the performance of the DeepFace library …

Member Avatar for peol
3
278
Member Avatar for usmanmalik57

Stock price prediction is a challenging task that requires analyzing historical trends, market sentiments, economic indicators, and company performance. One of the popular methods for stock price prediction is using deep learning models, such as convolutional neural networks (CNNs). CNNs are a type of neural network that can extract features …

0
161

The End.