SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2110.05069 · 2021

Efficient Training of Audio Transformers with Patchout

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 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, 0 violated it and 0 have no contract verdict; 3 failures of our instrument; 0 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/2110.05069.json · badge: /api/ran/2110.05069.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
kkoutini/passt canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
FunctionStatusWhere it lives
adapt_image_pos_embed_to_passt Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
kkoutini/passt/models/passt.py
code served (permissive licence) · get_code("154029eca1a62725")
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
import math

torch.manual_seed(0)

# Create a position embedding tensor
# Shape: (batch_size, num_positions, embedding_dim)
# num_positions = num_tokens + grid_size^2
# Let's use num_tokens=1, gs_old=4 (so 16 grid positions), embedding_dim=8
num_tokens = 1
gs_old = 4
embedding_dim = 8
num_grid_positions = gs_old * gs_old
total_positions = num_tokens + num_grid_positions

posemb = torch.randn(1, total_positions, embedding_dim)

# New grid size for interpolation
gs_new = (8, 6)  # Different dimensions for clarity

ARGS = {
    'posemb': posemb,
    'num_tokens': num_tokens,
    'gs_new': gs_new,
    'mode': 'bicubic'
}
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
adapt_input_conv Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
kkoutini/passt/models/passt.py
code served (permissive licence) · get_code("552d614343c6f5b0")
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 Tensor, ndim 4, dtype family float, shape (4, 1, 5, 5) 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 math

torch.manual_seed(0)

# Create a small conv weight tensor
# Shape: (O, I, J, K) = (out_channels, in_channels, kernel_h, kernel_w)
# Using distinct sizes: 4, 3, 5, 5
conv_weight = torch.randn(4, 3, 5, 5, dtype=torch.float32)

# Test case 1: in_chans = 1
in_chans = 1

ARGS = {
    "in_chans": in_chans,
    "conv_weight": conv_weight
}
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 Tensor, ndim 4, dtype family float, shape (4, 1, 5, 5) — shape (4, 1, 5, 5) 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
resize_pos_embed Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
kkoutini/passt/models/passt.py
code served (permissive licence) · get_code("39ffb2244e2dcbe1")
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 Tensor, ndim 3, dtype family float, shape (1, 17, 4) 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 math

torch.manual_seed(0)

# Create position embedding tensor
# Shape: (batch=1, num_tokens + grid_tokens, embedding_dim=4)
# We'll have 1 cls token + 9 grid tokens (3x3 grid)
posemb = torch.randn(1, 10, 4)

# Create new position embedding tensor with different grid size
# We want to resize to a 4x4 grid, so 1 cls token + 16 grid tokens
posemb_new = torch.randn(1, 17, 4)

# Number of class/distillation tokens
num_tokens = 1

# New grid size (4x4)
gs_new = [4, 4]

# Interpolation mode
mode = 'bicubic'

ARGS = {
    'posemb': posemb,
    'posemb_new': posemb_new,
    'num_tokens': num_tokens,
    'gs_new': gs_new,
    'mode': mode,
}
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 Tensor, ndim 3, dtype family float, shape (1, 17, 4) — shape (1, 17, 4) 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

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 3 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 1 the same month, 3 later) and 0 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
adapt_input_conv 6 other papers
1 the same month, 5 later
2110.07641 (2021-10)
Non-deep Networks
2204.07683 (2022-04)
Safe Self-Refinement for Transformer-based Domain Adaptation
2206.03452 (2022-06)
Can CNNs Be More Robust Than Transformers?
and 3 more not named here
adapt_image_pos_embed_to_passt 1 other paper
1 later
2211.13956 (2022-11)
Learning General Audio Representations With Large-Scale Training of Patchout Audio Transformers
resize_pos_embed 1 other paper
1 later
2211.13956 (2022-11)
Learning General Audio Representations With Large-Scale Training of Patchout Audio Transformers

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

The great success of transformer-based models in natural language processing (NLP) has led to various attempts at adapting these architectures to other domains such as vision and audio. Recent work has shown that transformers can outperform Convolutional Neural Networks (CNNs) on vision and audio tasks. However, one of the main shortcomings of transformer models, compared to the well-established CNNs, is the computational complexity. In transformers, the compute and memory complexity is known to grow quadratically with the input length. Therefore, there has been extensive work on optimizing transformers, but often at the cost of degrading predictive performance. In this work, we propose a novel method to optimize and regularize transformers on audio spectrograms. Our proposed models achieve a new state-of-the-art performance on Audioset and can be trained on a single consumer-grade GPU. Furthermore, we propose a transformer model that outperforms CNNs in terms of both performance and training speed. Source code: https://github.com/kkoutini/PaSST

For agents

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

get_harvested_code_for_paper("2110.05069")
get_code_for_paper("2110.05069")
have("2110.05069")

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

curl https://syntology.ai/api/ran/2110.05069.json

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

[![Syntology run record](https://syntology.ai/api/ran/2110.05069.svg)](https://syntology.ai/paper/2110.05069)

Connect an agent — have() is free.