{
  "fetched_at": "2026-10-19T06:32:33Z",
  "source_url": "https://www.kaggle.com/competitions/budgeted-model-training-iccv-2023-rcv-workshop/data",
  "pages": [
    {
      "name": "data-description",
      "content": "**Imagenet-100 Set1**\nThis dataset is a subset of ImageNet-1k created by choosing 100 classes of imagenet and splitting them into train, val and test sets.\n\n## Files\n\n*   **train.csv** - a csv file containing training image names and their corresponding labels.\n*   **val.csv** - a csv file containing validation image names and their corresponding labels.\n*   **sample_submission.csv** - a sample submission file in the correct format\n\n## Folders\n* **train** - contains training images\n* **val** - contains validation images\n* **test** - contains test images",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "## Motivation\n\nDespite the success of CNNs and, more recently, transformers, the scale of deep learning models has grown exponentially due to the rapid development of computational resources. Going forward, it is critical to focus on the practical training and inference efficiency of these models, as well as ensuring that even the largest models have viable real-world applications. Moreover, compute efficiency of computer vision models is becoming increasingly crucial for downstream tasks such as segmentation, object tracking, and action recognition, among others.\n\nThere exist several different directions towards making deep learning efficient for computer vision, thereby leading to a reduction in the required computational memory or the associated training and inference time. This competition will aim at bringing research efforts into practice for one such direction: *budget-aware model training*. Most research that exists focuses on making deep learning methods efficient, however, the resource associated with real-world AI devices can vary drastically, and a method termed efficient for a certain choice of resource budgets might be completely inefficient for a different one. This competition will also focus on methods that aim at performing budget-aware model training in best possible ways under limited GPU memory memory as well as limited training time.\n\n**This challenge is part of the ICCV 2023 Resource-Efficient Deep Learning (RCV) Workshop to be held between Oct 2-5, 2023 in Paris, France.**\n\n## Problem description\nAs part of this budgeted model training challenge, we pose the problem of the classification of ImageNet100. The goal is to build the best possible classifier for classifying the samples of ImageNet100 into one of the pre-defined 100 classes. However, there are certain rules to be respected to qualify as a winning solution. \n1. For final evaluation, each submitted solution will be used to train ImageNet100 with a different set of 100 classes than those revealed here. The score on this corresponding test set will be used to decide the performance of the model. \n2. All the models will be trained on a P100 GPU card along with 4 cpu cores for a maximum of 9 hours.\n3. The GPU memory consumption should not exceed 6 GB at any point of the training process of the final evaluation.\n4. Note that your code should not use any pretrained models and we will be training your models in the absence of internet, so make sure your code does not depend on any external pretrained models. \n5. Together with your code (only python scripts), you will be required to submit the run environment as a .yaml that will be used to run the code.\n6. The main script file should be named main.py and should take only one command line argument --data_dir to produce a submission.csv in the current working directory.\n\nThis competition will be running in two phases: **Phase I** and **Phase II**. \n\n**Phase I**: This phase is a standard classification problem where the goal is to maximize the accuracy on the test set and improve the ranking on the leaderboard. This phase of the competition will be hosted here on Kaggle and the leaderboard of Kaggle will be used to rank the solutions. Note that this phase will only use accuracy as the evaluation measure. Although this phase does not take the GPU memory and time constraint into consideration, participants are recommended to adhere to an approximate estimate and use the leaderboard to assess the performance of their efficient models that could pass on to the next Phase. **Using very large networks and pretrained models, that cannot later qualify the time and memory constraint criterion, is highly discouraged, since this will improve your ranking in Phase I, but will not be able to qualify you for Phase II.** See the rules stated above for more details.\n\n**Phase II**: We will post a baseline solution and all solutions that obtain an accuracy higher than baseline accuracy will be eligible to submit their solutions for Phase II. For details on the evaluation of the solutions for this phase, see the final evaluation details describe for the final evaluation above. This phase will be in an offline mode and results can be viewed at [Phase II Leaderboard](https://sites.google.com/view/rcv2023/leaderboard-workshop-challenges). We will keep updating the leaderboard on a rolling basis, however, every solution can be expected to get reflected on the leaderboard in 5 days from the day of the submission. Every team will be able to submit their two best solutions in one instance. For the start date of this phase, check the timeline page.\n\n## Challenge Organizer team\nFor details related to the organizing team, see https://sites.google.com/view/rcv2023/organizing-committee\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "### One account per participant\nYou cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts.\n\n### No private sharing outside teams\nPrivately sharing code or data outside of teams is not permitted. It's okay to share code if made available to all participants on the forums.\n\n### Team Mergers\nThere are no team mergers permitted in this competition.\n\n### Team Limits\nEach team can be formed with a maximum of 3 members.\n\n### Submission Limits\nYou may submit a maximum of 5 entries per day.\n\nYou may select up to 2 final submissions for judging.\n\nPrize Eligibility\nIn order to be eligible for the prizes, you must:\n\nParticipate in Phase II of the competition that will be held in an offline model.\n\nSubmit code on time for the team to evaluate. Note that the code should not use any pretrained model as well as ensure that it works with the python environment provided by the organizers.\n\nPlease note that people affiliated with Transmute AI Lab are not eligible for the prizes.\n\nCompetition Timeline\nCompetition Timeline dates (including Entry Deadline, Final Submission Deadline,  and Start Date, as applicable) are reflected on the competition’s Overview > Timeline page.\n\nCompetition Data\n\"Competition Data\" means the data or datasets available from the Competition Website for the purpose of use in the Competition, including any prototype or executable code provided on the Competition Website. The Competition Data will contain private and public test sets. Which data belongs to which set will not be made available to participants.\n\nA. Data Access and Use. Competition Use only: You may access and use the Competition Data only for participating in the Competition and on Kaggle.com forums. The Competition Sponsor reserves the right to disqualify any participant who uses the Competition Data other than as permitted by the Competition Website and these Rules.\n\nB. Data Security. You agree to use reasonable and suitable measures to prevent persons who have not formally agreed to these Rules from gaining access to the Competition Data. You agree not to transmit, duplicate, publish, redistribute or otherwise provide or make available the Competition Data to any party not participating in the Competition. You agree to notify Hosts immediately upon learning of any possible unauthorized transmission of or unauthorized access to the Competition Data and agree to work with them to rectify any unauthorized transmission or access.\n\nC. External Data. You may not use data other than the Competition Data (“External Data”) to develop and test your Submissions.\n\nSubmissions may not use or incorporate information from hand labeling or human prediction of the training or test data records.\n\nCompetition Code\nCode related to all submissions on the leaderboard should be submitted during the course of the competition. The submitted code, in its original form, should be able to reproduce the scores. Your code should not be using any external data to produce the reported scores.\nBy participating in the competition, you provide rights to the competition organizers to use your code, associated solution and any related ideas for any venue or publication outside the competition.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Timeline",
      "content": "## Timeline (in UTC)\n- Phase I starts: April 12, 2023\n- Phase II starts: June 12, 2023\n- Phase II ends: July 30, 2023\n- Final leaderboard update: Aug 05, 2023\n- Notification of results: Aug 05, 2023\n- Submission of report: Aug 09, 2023",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "All submissions will be evaluated with different metrics at the two phases of the competition.\n\n- **Phase I**: This phase is hosted on Kaggle and will be using accuracy as the evaluation measure. \n\n- **Phase II**: This phase will run in an offline manner in which the qualifying participants from Phase I will submit their code scripts to be re-run on another set of private data under 6GB of GPU (RTX8000) memory limit and 9 hours of time constraints and the accuracy on the test set of this private data will be used for the final rankings.\nThe following machine configuration will be used for training your models/frameworks -\nGPU : Quadro RTX 8000 \nGPU Mem. Limit : 6GB\nTotal Time Limit : 9 Hours \nCPU Cores : 4\nRAM : 32GB\n\n## Submission File for Phase I\n\nFor each `image_id`, you should predict the corresponding image label in the `label` column\n\nThe file should be named submission.csv and contain the columns `image_id` and `label` in the following format:\n~~~~\nimage_id,label\nasdfghjklo,0\nzxcvbnmlkj,1\n~~~~\n\n## Submission File for Phase II\nEach qualifying team is required to submit scripts that will be run and evaluated on a private dataset. The details of qualification to Phase II and format of code scripts is specified in the **Description** tab.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Prizes",
      "content": "## Prizes\n\nNote that Kaggle platform is only used to run Phase I of the challenge. The final prizes will be based on Phase II results and the details can be found here: https://sites.google.com/view/rcv2023/workshop-challenges",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}