SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.15296 · 2022

Frequency Dynamic Convolution: Frequency-Adaptive Pattern Recognition for Sound Event Detection

arXiv · PDF · Open in the Atlas

Code that ran

8 of 11 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 7 have no contract verdict; 1 failure of our instrument; 3 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/2203.15296.json · badge: /api/ran/2203.15296.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
frednam93/FDY-SED canonical (classifier label)
classifier basis not recorded on the link
8 ran · 3 no recorded run
FunctionStatusWhere it lives
frame_shift Ran
ran on a synthesized input
frednam93/FDY-SED/utils/data_aug.py
code served (permissive licence) · get_code("fc4d7ca68be30162")
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, through the batch API) and returned tuple, ndim 4, 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 torch
import random

torch.manual_seed(0)
random.seed(0)

# Create tiny tensors for testing
batch_size = 2
feature_dim = 4
time_steps = 3

# Features tensor: (batch_size, feature_dim, time_steps)
features = torch.randn(batch_size, feature_dim, time_steps)

# Label tensor: (batch_size, feature_dim, time_steps)
label = torch.randn(batch_size, feature_dim, time_steps)

# Net pooling parameter (used in the label shifting calculation)
net_pooling = 2

ARGS = {
    "features": features,
    "label": label,
    "net_pooling": net_pooling,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 4, 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
get_configs Ran
ran on a synthesized input
frednam93/FDY-SED/utils/settings.py
code served (permissive licence) · get_code("35d34e23002c3f6c")
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, through the batch API) and returned tuple, ndim 1, 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 yaml
import tempfile
import os

# Create temporary directory and YAML files
temp_dir = tempfile.mkdtemp()

# Create config_dir YAML file with required structure
config_content = {
    'training': {
        'epochs': 10,
        'learning_rate': 0.001,
        'batch_sizes': None,  # Will be overwritten
        'net_pooling': None,  # Will be overwritten
    },
    'feature': {
        'net_subsample': 2,
        'feature_dim': 128,
    }
}

config_path = os.path.join(temp_dir, 'config.yaml')
with open(config_path, 'w') as f:
    yaml.dump(config_content, f)

# Create server config YAML file
server_config_content = {
    'batch_size': 32,
    'server_param': 'value',
}

server_config_path = os.path.join(temp_dir, 'config_server.yaml')
with open(server_config_path, 'w') as f:
    yaml.dump(server_config_content, f)

ARGS = {
    'config_dir': config_path,
    'server_config_dir': server_config_path,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
yaml — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, 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
get_event_list_current_file Ran
ran; our contract draft was wrong, not the code
frednam93/FDY-SED/utils/evaluation_measures.py
code served (permissive licence) · get_code("642c47d1500f9afe")
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, through the batch API) and returned list, ndim 1, 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 pandas as pd

# Create a sample dataframe with the required columns
df = pd.DataFrame({
    'filename': ['file1.txt', 'file2.txt', 'file3.txt', 'file1.txt'],
    'event_label': ['event_a', 'event_b', pd.NA, 'event_c']
})

# Define the filename to search for
fname = 'file1.txt'

ARGS = {
    'df': df,
    'fname': fname
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list 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
mixup Ran
ran on a synthesized input
frednam93/FDY-SED/utils/data_aug.py
code served (permissive licence) · get_code("fcf7e299ada9da07")
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, through the batch API) 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 numpy as np

torch.manual_seed(0)
np.random.seed(0)

# Create small tensors for testing
batch_size = 2
feature_dim = 4
num_classes = 3

features = torch.randn(batch_size, feature_dim)
label = torch.rand(batch_size, num_classes)
permutation = torch.tensor([1, 0])
c = 0.5
alpha = 0.2
beta = 0.2
mixup_label_type = 'soft'
returnc = False

ARGS = {
    'features': features,
    'label': label,
    'permutation': permutation,
    'c': c,
    'alpha': alpha,
    'beta': beta,
    'mixup_label_type': mixup_label_type,
    'returnc': returnc,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, 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
normalize_wav Ran
ran on a synthesized input
frednam93/FDY-SED/utils/dataset.py
code served (permissive licence) · get_code("42603004cab20d23")
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, through the batch API) and returned Tensor, ndim 2, dtype family float, shape (2, 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

torch.manual_seed(0)

# Create a small audio waveform tensor
# The function expects a tensor and performs normalization on it
wav = torch.randn(2, 4)  # Small batch of audio samples

ARGS = {
    "wav": wav
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 2, dtype family float, shape (2, 4) — shape (2, 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
time_mask Ran
ran on a synthesized input
frednam93/FDY-SED/utils/data_aug.py
code served (permissive licence) · get_code("7990a733fe90164b")
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, through the batch API) 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)

# Build small tensors with distinct dimensions
# features shape: (batch=2, channels=4, frames=20)
features = torch.randn(2, 4, 20)

# labels shape: (batch=2, channels=3, frames=20)
labels = torch.randn(2, 3, 20)

# net_pooling is used as a multiplier for time indices
net_pooling = 2

# mask_ratios determines the range for random mask width selection
mask_ratios = (10, 20)

ARGS = {
    "features": features,
    "labels": labels,
    "net_pooling": net_pooling,
    "mask_ratios": mask_ratios,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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
to_mono Ran
ran on a synthesized input
frednam93/FDY-SED/utils/dataset.py
code served (permissive licence) · get_code("2a09e6597b934159")
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, through the batch API) and returned ndarray, ndim 1, dtype family float, shape (1000,) 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 numpy as np

# Create test audio data
# Mono case: 1D array
wav_mono = np.random.randn(1000)

# Stereo case: 2D array with shape (samples, channels)
wav_stereo = np.random.randn(1000, 2)

# Multi-channel case: 2D array with shape (samples, channels)
wav_multichannel = np.random.randn(1000, 4)

ARGS = {
    "wav": wav_stereo,
    "rand_ch": False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (1000,) — shape (1000,) 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
update_ema Ran
ran on a synthesized input
frednam93/FDY-SED/utils/utils.py
code served (permissive licence) · get_code("4a179359e2060751")
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, through the batch API) and returned SimpleNet. 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 torch.nn as nn

torch.manual_seed(0)

# Create a simple neural network model
class SimpleNet(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
    
    def forward(self, x):
        x = self.linear1(x)
        x = self.linear2(x)
        return x

# Create instances of the network and EMA network
net = SimpleNet()
ema_net = SimpleNet()

# Initialize EMA network with same parameters as net
for ema_param, param in zip(ema_net.parameters(), net.parameters()):
    ema_param.data.copy_(param.data)

# Define arguments
ARGS = {
    'net': net,
    'ema_net': ema_net,
    'step': 5,
    'ema_factor': 0.999
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type SimpleNet — a SimpleNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SimpleNet output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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
decode_pred_batch Not yet run
unverified (harvested, no recorded run)
frednam93/FDY-SED/utils/utils.py
code served (permissive licence) · get_code("09740df508b27138")
How it ran

no invocation recorded.

get_logger Not yet run
unverified (harvested, no recorded run)
frednam93/FDY-SED/utils/settings.py
code served (permissive licence) · get_code("5f1a7881bda24d62")
How it ran

no invocation recorded.

get_save_directories Not yet run
unverified (harvested, no recorded run)
frednam93/FDY-SED/utils/settings.py
code served (permissive licence) · get_code("999fa7df4f591099")
How it ran

no invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 later) and 10 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
get_event_list_current_file 1 other paper
1 later
2206.11260 (2022-06)
Few-shot Long-Tailed Bird Audio Recognition

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

2D convolution is widely used in sound event detection (SED) to recognize two dimensional time-frequency patterns of sound events. However, 2D convolution enforces translation equivariance on sound events along both time and frequency axis while frequency is not shift-invariant dimension. In order to improve physical consistency of 2D convolution on SED, we propose frequency dynamic convolution which applies kernel that adapts to frequency components of input. Frequency dynamic convolution outperforms the baseline by 6.3% in DESED validation dataset in terms of polyphonic sound detection score (PSDS). It also significantly outperforms other pre-existing content-adaptive methods on SED. In addition, by comparing class-wise F1 scores of baseline and frequency dynamic convolution, we showed that frequency dynamic convolution is especially more effective for detection of non-stationary sound events with intricate time-frequency patterns. From this result, we verified that frequency dynamic convolution is superior in recognizing frequency-dependent patterns.

For agents

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

get_harvested_code_for_paper("2203.15296")
get_code_for_paper("2203.15296")
have("2203.15296")

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

curl https://syntology.ai/api/ran/2203.15296.json

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

[![Syntology run record](https://syntology.ai/api/ran/2203.15296.svg)](https://syntology.ai/paper/2203.15296)

Connect an agent — have() is free.