Dataset

This dataset was created by Alexis Cook

Contents

https://www.kaggle.com/datasets/muzammilaliveltech/farm-harmful-animals-dataset

this dataset is not mine, it was uploaded to Kaggle by MUZAMMIL ALI VELTECH under CC0: Public Domain. This Roboflow project was made as an attempt to use the dataset after having issue trying to import in Jupyter Notebook from Kaggle

Clean the data, Preprocess it and then make predictions. Try and Learn.

Mirror of external ZIP: https://aic-data.ledo.io.vn/Videos_L22_a.zip

Uploaded via Kaggle Notebook (one-file-per-dataset).

Custom Training with YOLOv7 🔥

Some Important links

• Model Inference🤖
• 🚀Training Yolov7 on Kaggle
• Weight and Biases 🐝
• HuggingFace 🤗 Model Repo

Contact Information

• Name - Owais Ahmad
• Phone - +91-9515884381
• Email - owaiskhan9654@gmail.com
• Portfolio - https://owaiskhan9654.github.io/

Objective

To Showcase custom Object Detection on the Given Dataset to train and Infer the Model using newly launched YoloV7.

Data Acquisition

The goal of this task is to train a model that can localize and classify each instance of Person and Car as accurately as possible.

• Link to the Downloadable Dataset

from IPython.display import Markdown, display

display(Markdown("../input/Car-Person-v2-Roboflow/README.roboflow.txt"))

Custom Training with YOLOv7 🔥

In this Notebook, I have processed the images with RoboFlow because in COCO formatted dataset was having different dimensions of image and Also data set was not splitted into different Format. To train a custom YOLOv7 model we need to recognize the objects in the dataset. To do so I have taken the following steps:

• Export the dataset to YOLOv7
• Train YOLOv7 to recognize the objects in our dataset
• Evaluate our YOLOv7 model's performance
• Run test inference to view performance of YOLOv7 model at work

📦 YOLOv7

https://raw.githubusercontent.com/Owaiskhan9654/Yolo-V7-Custom-Dataset-Train-on-Kaggle/main/car-person-2.PNG" width=800>

Image Credit - jinfagang

Step 1: Install Requirements

!git clone https://github.com/WongKinYiu/yolov7 # Downloading YOLOv7 repository and installing requirements
%cd yolov7
!pip install -qr requirements.txt
!pip install -q roboflow

Downloading YOLOV7 starting checkpoint

!wget "https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7.pt"

import os
import glob
import wandb
import torch
from roboflow import Roboflow
from kaggle_secrets import UserSecretsClient
from IPython.display import Image, clear_output, display # to display images



print(f"Setup complete. Using torch {torch._version_} ({torch.cuda.get_device_properties(0).name if torch.cuda.is_available() else 'CPU'})")

https://camo.githubusercontent.com/dd842f7b0be57140e68b2ab9cb007992acd131c48284eaf6b1aca758bfea358b/68747470733a2f2f692e696d6775722e636f6d2f52557469567a482e706e67">

I will be integrating W&B for visualizations and logging artifacts and comparisons of different models!

YOLOv7-Car-Person-Custom

try:
  user_secrets = UserSecretsClient()
  wandb_api_key = user_secrets.get_secret("wandb_api")
  wandb.login(key=wandb_api_key)
  anonymous = None
except:
  wandb.login(anonymous='must')
  print('To use your W&B account,
Go to Add-ons -> Secrets and provide your W&B access token. Use the Label name as WANDB. 
Get your W&B access token from here: https://wandb.ai/authorize')
  
  
  
wandb.init(project="YOLOvR",name=f"7. YOLOv7-Car-Person-Custom-Run-7")

Step 2: Assemble Our Dataset

https://uploads-ssl.webflow.com/5f6bc60e665f54545a1e52a5/615627e5824c9c6195abfda9_computer-vision-cycle.png" alt="">

In order to train our custom model, we need to assemble a dataset of representative images with bounding box annotations around the objects that we want to detect. And we need our dataset to be in YOLOv7 format.

In Roboflow, We can choose between two paths:

• Convert an existing Coco dataset to YOLOv7 format. In Roboflow it supports over 30 formats object detection formats for conversion.
• Uploading only these raw images and annotate them in Roboflow with Roboflow Annotate.

Version v2 Aug 12, 2022 Looks like this.

https://raw.githubusercontent.com/Owaiskhan9654/Yolo-V7-Custom-Dataset-Train-on-Kaggle/main/Roboflow.PNG" alt="">

user_secrets = UserSecretsClient()
roboflow_api_key = user_secrets.get_secret("roboflow_api")

rf = Roboflow(api_key=roboflow_api_key)
project = rf.workspace("owais-ahmad").project("custom-yolov7-on-kaggle-on-custom-dataset-rakiq")
dataset = project.version(2).download("yolov7")

Step 3: Training Custom pretrained YOLOv7 model

Here, I am able to pass a number of arguments: - img: define input image size - batch: determine

Dataset Creation

The notebook uploaded here is used to convert videos frames into tensor files (audio + video) which will be used by the training script to train the Video Decoder Module. The Dataset used was "https://www.kaggle.com/datasets/pevogam/ucf101". This dataset must be imported into the environment (Eg. Kaggle) and the path UCF_VIDEO_DIR must be updated in the notebook

Amazon Scrapping Dataset; 1. Import libraries 2. Connect to the website 3. Import CSV and datetime 4. Import pandas 5. Appending dataset to CSV 6. Automation Dataset updated 7. Timers setup 8. Email notification

Dataset Creation

The notebook uploaded here is used to convert the audio and image into tensor files which will be used by the training script to train the Image Decoder Module. The Dataset used was "https://www.kaggle.com/datasets/jorvan/image-audio-pairs-1-of-3". This dataset must be imported into the environment (Eg. Kaggle) and the path BASE_DATA_PATH must be updated in the notebook

MIntRec stands for multimodal intent recognition. The benchmark dataset is first introduced at ACM MM 2022: https://dl.acm.org/doi/10.1145/3503161.3547906. The uploaded version is a latest second version which is introduced in ICLR 2024: https://openreview.net/forum?id=nY9nITZQjc.

More details can be found here: https://github.com/thuiar/MIntRec2.0 , and among the 3 versions, I uploaded the feature and raw data(this one's raw data) because they seem to be the best way to practice on the Kaggle Notebook Environment.

The purpose of uploading this dataset is to practice multi-classification tasks using LLMs whether the large models can recognize and classify human intent properly.

Info

Source repo is google/flan-t5-large.

Usage

1. Add dataset to Kaggle notebook;
2. Import pretrained from folder;

from transformers import AutoTokenizer, AutoModel


model = AutoModel.from_pretrained('/kaggle/input/googleflan-t5-large/flan-t5-large')
tokenizer = AutoTokenizer.from_pretrained('/kaggle/input/googleflan-t5-large/flan-t5-large')

Context

• Giba has introduced hybrid approach which use other notebooks result for better performance: https://www.kaggle.com/titericz/h-m-ensembling-how-to/notebook
• Altu has a new improved version with lstm model: https://www.kaggle.com/code/atulverma/h-m-ensembling-with-lstm

But you need to download other notebooks result, then upload it if you want to use within your notebook. So i create this dataset for anyone who want to use directly notebook result without download/upload. Please upvote if it help you

Content

This dataset contain 5 results as input using for a hybrid approach in this notebook: * https://www.kaggle.com/titericz/h-m-ensembling-how-to/notebook. * https://www.kaggle.com/code/atulverma/h-m-ensembling-with-lstm

If you want to use this notebook but can't access to private dataset, please add my dataset to your notebook, than change file path. It has 5 files: * submissio_byfone_chris.csv: Submission result from: https://www.kaggle.com/lichtlab/0-0226-byfone-chris-combination-approach
* submission_exponential_decay.csv: Submission result from: https://www.kaggle.com/tarique7/hnm-exponential-decay-with-alternate-items/notebook * submission_trending.csv: Submission result from: https://www.kaggle.com/lunapandachan/h-m-trending-products-weekly-add-test/notebook * submission_sequential_model.csv: Submission result from: https://www.kaggle.com/code/astrung/sequential-model-fixed-missing-last-item/notebook * submission_sequential_with_item_feature.csv: Submission result from: https://www.kaggle.com/code/astrung/lstm-model-with-item-infor-fix-missing-last-item/notebook

This dataset contains different variants of the RoBERTa and XLM-RoBERTa model by Meta AI available on Hugging Face's model repository.

By making it a dataset, it is significantly faster to load the weights since you can directly attach a Kaggle dataset to the notebook rather than downloading the data every time. See the speed comparison notebook. Another benefit of loading models as a dataset is that it can be used in competitions that require internet access to be "off".

For more information on usage visit the roberta hugging face docs and the xlm-roberta hugging face docs.

Usage

To use this dataset, attach it to your notebook and specify the path to the dataset. For example:

from transformers import AutoTokenizer, AutoModelForPreTraining
​
MODEL_DIR = "/kaggle/input/huggingface-roberta/"
​
tokenizer = AutoTokenizer.from_pretrained(MODEL_DIR + "roberta-base")
model = AutoModelForPreTraining.from_pretrained(MODEL_DIR + "roberta-base")

Acknowledgements All the copyrights and IP relating to RoBERTa and XLM-RoBERTa belong to the original authors (Liu et al. and Conneau et al.) and Meta AI. All copyrights relating to the transformers library belong to Hugging Face. Please reach out directly to the authors if you have questions regarding licenses and usage.

This dataset is inspired from the work of @akensert in retrieving the tiles from each image. I decided to upload my dataset version in order to train also in Kaggle notebook. I cropped the "level 1" of the original images, and each image comes with a dimension n_crops*256, 256, 3. Therefore, it is possible to retrieve the original image reshaping it to (-1, 256, 256, 3).

Mirror of external ZIP: https://aic-data.ledo.io.vn/media-info-aic25-b1.zip

Uploaded via Kaggle Notebook (one-file-per-dataset).

✅ Step 1: Mount to Dataset

Search for my dataset pytorch-models and add it — this will mount it at:

/kaggle/input/pytorch-models/

✅ Step 2: Check file paths Once mounted, the four files will be available at:

/kaggle/input/pytorch-models/base_models.py
/kaggle/input/pytorch-models/ext_base_models.py
/kaggle/input/pytorch-models/ext_hybrid_models.py
/kaggle/input/pytorch-models/hybrid_models.py

✅ Step 3: Copy files to working directory To make them importable, copy the .py files to your notebook’s working directory (/kaggle/working/):

import shutil

shutil.copy('/kaggle/input/pytorch-models/base_models.py', '/kaggle/working/')
shutil.copy('/kaggle/input/pytorch-models/ext_base_models.py', '/kaggle/working/')
shutil.copy('/kaggle/input/pytorch-models/ext_hybrid_models.py', '/kaggle/working/')
shutil.copy('/kaggle/input/pytorch-models/hybrid_models.py', '/kaggle/working/')

✅ Step 4: Import your modules Now that they are in the working directory, you can import them like normal:

import base_models
import ext_base_models
import ext_hybrid_models
import hybrid_models

Or, if you only want to import specific classes or functions:

from base_models import YourModelClass
from ext_base_models import AnotherModelClass

✅ Step 5: Use the models You can now initialize and use the models/classes/functions defined inside each file:

model = base_models.YourModelClass()
output = model(input_data)

Mirror of external ZIP: https://aic-data.ledo.io.vn/clip-features-32-aic25-b1.zip

Uploaded via Kaggle Notebook (one-file-per-dataset).

This dataset has been processed from the Smart meters in London available on Kaggle. The original dataset contains information on households, and the meter readings can be aggregated at various levels - household, blocks, and the entire city. However, due to long processing times and high memory usage during aggregation, this dataset provides processed results that can be directly used for analysis or modeling.

To explore and model the dataset, an example notebook is available at the Github link.

Using the OpenAI CLIP Model in Kaggle

https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F11228484%2F27123889b0ce5c7a326965dfc9c29f00%2Foverview-a.svg?generation=1719898030106027&alt=media" alt="Overview A">

https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F11228484%2Faa6a6110c2a9a63690339c6a6bfe7ab6%2Foverview-b.svg?generation=1719898209012848&alt=media" alt="Overview B">

Introduction

The CLIP (Contrastive Language–Image Pre-training) model is an innovative approach developed by OpenAI, designed to enhance the robustness of computer vision tasks. It leverages a unique training regimen that aligns images with textual descriptions using a contrastive loss, enabling it to perform image classification tasks in a zero-shot manner. This means CLIP can generalize to classify images it has never seen before based solely on textual descriptions, without the need for further training specific to those tasks.

Model Details

• Model Release Date: January 2021
• Architecture: The model uses a Vision Transformer (ViT-B/32) as the image encoder and a masked self-attention Transformer as the text encoder. These components are trained to maximize the similarity between corresponding image and text pairs.
• Implementation Variants: Originally, CLIP was released in two variants — one using a ResNet image encoder and another using a Vision Transformer. The version provided here employs the Vision Transformer architecture.

Usage Instructions

To use the CLIP model in your Kaggle notebooks, follow these simple steps:

1. Add the Model as a Kaggle Dataset: Ensure that the dataset containing the CLIP model files is attached to your Kaggle notebook. This dataset includes the necessary model and processor files.

2. Initialize the Model and Processor: You can load the model and processor directly from the path where the dataset files are stored using the following code snippet:

   # Import CLIP model from transformers
   from transformers import CLIPModel, CLIPProcessor
   
   # Set the path to the model files
   model_path = '/kaggle/input/openaiclip-vit-base-patch32'
   
   # Load the CLIP model
   clip_model = CLIPModel.from_pretrained(model_path)
   
   # Load the CLIP processor
   clip_processor = CLIPProcessor.from_pretrained(model_path)
   

Documents

• Blog
• CLIP Paper

This dataset contains different variants of the MobileBERT model by Google available on Hugging Face's model repository.

By making it a dataset, it is significantly faster to load the weights since you can directly attach a Kaggle dataset to the notebook rather than downloading the data every time. See the speed comparison notebook. Another benefit of loading models as a dataset is that it can be used in competitions that require internet access to be "off".

For more information on usage visit the mobilebert hugging face docs.

Usage

To use this dataset, attach it to your notebook and specify the path to the dataset. For example:

from transformers import AutoTokenizer, AutoModelForPreTraining
​
MODEL_DIR = "/kaggle/input/huggingface-google-mobilebert/"
​
tokenizer = AutoTokenizer.from_pretrained(MODEL_DIR)
model = AutoModelForPreTraining.from_pretrained(MODEL_DIR)

Acknowledgements All the copyrights and IP relating to MobileBERT belong to the original authors (Sun et al.) and Google. All copyrights relating to the transformers library belong to Hugging Face. Please reach out directly to the authors if you have questions regarding licenses and usage.

This dataset is generated for the purpose of analyzing furniture sales data using multiple regression techniques. It contains 2,500 rows with 15 columns, including 7 numerical columns and 7 categorical columns, along with a target variable (revenue) which represents the total revenue generated from furniture sales. The dataset captures various aspects of furniture sales, such as pricing, cost, sales volume, discount percentage, inventory levels, delivery time, and different categorical attributes like furniture type, material, color, and store location.

Guys please upload your notebook of this dataset so that others can also learn from your work