SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2306.16699 · 2023

Rapid-INR: Storage Efficient CPU-free DNN Training Using Implicit Neural Representation

arXiv · PDF · Open in the Atlas

Code that ran

3 of 5 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 2 failures of our instrument; 2 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2306.16699.json · badge: /api/ran/2306.16699.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
sharc-lab/rapid-inr canonical (classifier label)
classifier basis: classifier_2025
3 ran · 2 no recorded run
FunctionStatusWhere it lives
is_image_file Ran
ran, violated the contract we drafted
sharc-lab/rapid-inr/INR_encoding.py
code served (permissive licence) · get_code("2383223cfe77b76c")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned bool, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

def is_image_file(filename):
    return any((filename.endswith(extension) for extension in ['.png', '.jpg', '.jpeg', '.PNG', '.JPG', '.JPEG']))

# Test with a valid image filename
ARGS = {
    'filename': 'test_image.png'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bool, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
load_image_path Ran
ran; our contract draft was wrong, not the code
sharc-lab/rapid-inr/INR_encoding.py
code served (permissive licence) · get_code("fc4fa9d0c6ec7c74")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned tuple, ndim 2, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import os
import tempfile
import shutil

# Create a temporary directory structure with image files
temp_dir = tempfile.mkdtemp()

# Create subdirectories and image files
subdir1 = os.path.join(temp_dir, "subdir1")
subdir2 = os.path.join(temp_dir, "subdir2")
os.makedirs(subdir1, exist_ok=True)
os.makedirs(subdir2, exist_ok=True)

# Create dummy image files
open(os.path.join(subdir1, "image1.png"), 'w').close()
open(os.path.join(subdir1, "image2.jpg"), 'w').close()
open(os.path.join(subdir1, "image3.jpeg"), 'w').close()
open(os.path.join(subdir2, "image4.PNG"), 'w').close()
open(os.path.join(subdir2, "image5.JPG"), 'w').close()
open(os.path.join(subdir2, "image6.JPEG"), 'w').close()

# Create some non-image files that should be ignored
open(os.path.join(subdir1, "readme.txt"), 'w').close()
open(os.path.join(subdir2, "data.csv"), 'w').close()

ARGS = {
    "imgDir": temp_dir
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 2, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
to_coordinates_and_features Ran
ran; our contract draft was wrong, not the code
sharc-lab/rapid-inr/INR_encoding.py
code served (permissive licence) · get_code("d23ec1986312cdd1")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create a small image tensor with shape (channels, height, width)
# Using distinct dimensions: 4 channels, 3 height, 5 width
img = torch.randn(4, 3, 5)

ARGS = {
    "img": img
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
bpp Not yet run
unverified (harvested, no recorded run)
sharc-lab/rapid-inr/train_script.py
code served (permissive licence) · get_code("9bbc135f83be2187")
How it ran

no invocation recorded.

model_size_in_bits Not yet run
unverified (harvested, no recorded run)
sharc-lab/rapid-inr/train_script.py
code served (permissive licence) · get_code("e1b0b37b3501c3f1")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 4 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
is_image_file 4 other papers
3 dated earlier, 1 later
1609.04802 (2016-09)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
1911.07850 (2019-11)
Frequency Separation for Real-World Super-Resolution
2104.10338 (2021-04)
Shadow Generation for Composite Image in Real-world Scenes
and 1 more not named here

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Implicit Neural Representation (INR) is an innovative approach for representing complex shapes or objects without explicitly defining their geometry or surface structure. Instead, INR represents objects as continuous functions. Previous research has demonstrated the effectiveness of using neural networks as INR for image compression, showcasing comparable performance to traditional methods such as JPEG. However, INR holds potential for various applications beyond image compression. This paper introduces Rapid-INR, a novel approach that utilizes INR for encoding and compressing images, thereby accelerating neural network training in computer vision tasks. Our methodology involves storing the whole dataset directly in INR format on a GPU, mitigating the significant data communication overhead between the CPU and GPU during training. Additionally, the decoding process from INR to RGB format is highly parallelized and executed on-the-fly. To further enhance compression, we propose iterative and dynamic pruning, as well as layer-wise quantization, building upon previous work. We evaluate our framework on the image classification task, utilizing the ResNet-18 backbone network and three commonly used datasets with varying image sizes. Rapid-INR reduces memory consumption to only about 5% of the original dataset size in RGB format and achieves a maximum 6$\times$ speedup over the PyTorch training pipeline, as well as a maximum 1.2x speedup over the DALI training pipeline, with only a marginal decrease in accuracy. Importantly, Rapid-INR can be readily applied to other computer vision tasks and backbone networks with reasonable engineering efforts. Our implementation code is publicly available at https://github.com/sharc-lab/Rapid-INR.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2306.16699")
get_code_for_paper("2306.16699")
have("2306.16699")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2306.16699.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2306.16699.svg)](https://syntology.ai/paper/2306.16699)

Connect an agent — have() is free.