SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2111.09883 · 2021

Swin Transformer V2: Scaling Up Capacity and Resolution

arXiv · PDF · Open in the Atlas

Code that ran

17 of 30 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, 3 violated it and 10 have no contract verdict; 4 failures of our instrument; 13 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/2111.09883.json · badge: /api/ran/2111.09883.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
nku-shengzheliu/PaddlePaddle-Swin-Transformer-V2 community (classifier label)
classifier basis not recorded on the link
8 ran · 3 no recorded run
JunnYu/x-transformers-paddle community (classifier label)
classifier basis not recorded on the link
4 ran · 4 no recorded run
lyqcom/aaic_swintransformerv2 community (classifier label)
classifier basis not recorded on the link
3 ran · 3 no recorded run
Qdriving/Swin-TransformerV2-in-PP community (classifier label)
classifier basis not recorded on the link
2 ran · 3 no recorded run
FunctionStatusWhere it lives
arg_to_varname Ran
ran; our contract draft was wrong, not the code
lyqcom/aaic_swintransformerv2/src/configs/parser.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from Seongyeol-kim/FedWSQ, is pointer only (licence: NONE) · get_code("177a4abf40724f6e")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from Seongyeol-kim/FedWSQ, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

argv_to_vars Ran
ran; our contract draft was wrong, not the code
lyqcom/aaic_swintransformerv2/src/configs/parser.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from Seongyeol-kim/FedWSQ, is pointer only (licence: NONE) · get_code("ffc9d7cced6f71fb")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from Seongyeol-kim/FedWSQ, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

cast_tuple Ran
ran, violated the contract we drafted
JunnYu/x-transformers-paddle/pd_x_transformers/x_transformers.py
code served (permissive licence) · get_code("1f7c550e65142ef8")
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 1, dtype family int; 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

torch.manual_seed(0)

ARGS = {
    "val": 42,
    "depth": 3
}
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, ndim 1, dtype family int — 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
cutmix_generate_bbox_adjust_lam Ran
ran on a synthesized input
nku-shengzheliu/PaddlePaddle-Swin-Transformer-V2/mixup.py
code served (permissive licence) · get_code("80c04c4768d37ac0")
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 numpy as np

# Set seed for reproducibility
np.random.seed(0)

# Define arguments for cutmix_generate_bbox_adjust_lam
ARGS = {
    "image_shape": (1, 3, 224, 224),  # batch, channels, height, width
    "lam": 0.5,  # cutmix lambda value
    "minmax": None,  # not using minmax approach
    "correct_lam": True,  # correct the lambda value
    "count": None,  # generate single bbox
}
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 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
default Ran
ran, violated the contract we drafted
JunnYu/x-transformers-paddle/pd_x_transformers/x_transformers.py
code served (permissive licence) · get_code("424012cb37b31172")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned int, ndim 0, dtype family int, 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.

from inspect import isfunction

def exists(val):
    return val is not None

def default(val, d):
    if exists(val):
        return val
    return d() if isfunction(d) else d

# Test case 1: val exists (not None), d is a regular value
ARGS_1 = {
    'val': 42,
    'd': 100
}

# Test case 2: val is None, d is a regular value
ARGS_2 = {
    'val': None,
    'd': 100
}

# Test case 3: val is None, d is a function
def default_func():
    return 200

ARGS_3 = {
    'val': None,
    'd': default_func
}

# Test case 4: val exists, d is a function
ARGS_4 = {
    'val': "existing_value",
    'd': lambda: "default_value"
}

# Use one of the test cases as the final ARGS
ARGS = ARGS_3
Setup block drafted by
a language model, Claude Sonnet 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 int, ndim 0, dtype family int, 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
exists Ran
ran, violated the contract we drafted
JunnYu/x-transformers-paddle/pd_x_transformers/autoregressive_wrapper.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from ThomasMrY/VCT, is pointer only (licence: NONE) · get_code("aa5486a3650902d8")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from ThomasMrY/VCT, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_logger Ran
ran; our contract draft was wrong, not the code
nku-shengzheliu/PaddlePaddle-Swin-Transformer-V2/main_multi_gpu.py
code served (permissive licence) · get_code("043c2f16bd404117")
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 Logger. 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 sys
import os
import logging
import tempfile

# Create a temporary directory for the log file
temp_dir = tempfile.mkdtemp()
log_file_path = os.path.join(temp_dir, "test_logger.log")

ARGS = {
    "filename": log_file_path,
    "logger_name": "test_logger"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 Logger — a Logger output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Logger 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
is_ellipsis_not_in_parenthesis Ran
ran on a synthesized input
JunnYu/x-transformers-paddle/einops/einops.py
code served (permissive licence) · get_code("eaade2de97f347bc")
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 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

# Construct a valid argument for the function
# The function expects a List[int] as the 'group' parameter

# Test case 1: group with ellipsis marker
group_with_ellipsis = [-999]

# Test case 2: group without ellipsis marker
group_without_ellipsis = [1, 2, 3]

# Use the ellipsis case as the main argument
ARGS = {
    "group": group_with_ellipsis
}
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 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
rand_bbox Ran
ran on a synthesized input
nku-shengzheliu/PaddlePaddle-Swin-Transformer-V2/mixup.py
code served (permissive licence) · get_code("484edb411de743ae")
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 2, dtype family int; 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 numpy as np

np.random.seed(0)

ARGS = {
    "image_shape": (2, 3, 224, 256),
    "lam": 0.5,
    "count": 4
}
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 tuple, ndim 2, dtype family int — 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
rand_bbox_minmax Ran
ran on a synthesized input
nku-shengzheliu/PaddlePaddle-Swin-Transformer-V2/mixup.py
code served (permissive licence) · get_code("b27df77c248443b3")
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 2, dtype family int; 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 numpy as np

np.random.seed(0)

ARGS = {
    "image_shape": (2, 3, 224, 256),
    "minmax": (0.1, 0.5),
    "count": 3
}
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 tuple, ndim 2, dtype family int — 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
rerange_index Ran
ran on a synthesized input
Qdriving/Swin-TransformerV2-in-PP/ppcls/loss/comfunc.py
code served (permissive licence) · get_code("21421188135068e9")
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 int, shape (16,) 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

ARGS = {
    "batch_size": 4,
    "samples_each_class": 2,
}
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 int, shape (16,) — shape (16,) 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
shear_x Ran
ran on a synthesized input
nku-shengzheliu/PaddlePaddle-Swin-Transformer-V2/auto_augment.py
code served (permissive licence) · get_code("e0254103b7a7465f")
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 Image. 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 random
from PIL import Image, ImageEnhance, ImageOps

# Create a small test image
test_image = Image.new('RGB', (32, 32), color=(200, 100, 50))

# Define ARGS dict with all parameters
ARGS = {
    'image': test_image,
    'magnitude': 0.3,
    'fillcolor': (128, 128, 128)
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int 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
shear_y Ran
ran on a synthesized input
nku-shengzheliu/PaddlePaddle-Swin-Transformer-V2/auto_augment.py
code served (permissive licence) · get_code("00da552067622c6f")
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 Image. 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 random
from PIL import Image, ImageEnhance, ImageOps

# Create a small test image
test_image = Image.new('RGB', (64, 48), color=(100, 150, 200))

ARGS = {
    'image': test_image,
    'magnitude': 0.3,
    'fillcolor': (128, 128, 128)
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int 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
similar_architectures Ran
ran on a synthesized input
Qdriving/Swin-TransformerV2-in-PP/paddleclas.py
code served (permissive licence) · get_code("f262aa35d9f2b50f")
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 torch
import numpy as np
from difflib import SequenceMatcher

torch.manual_seed(0)

ARGS = {
    'name': 'resnet',
    'names': [
        'resnet50',
        'resnet101',
        'vgg16',
        '__internal_model',
        'inception_v3',
        'mobilenet_v2',
        'densenet121',
        'efficientnet_b0',
        'squeezenet1_0',
        'shufflenet_v2'
    ],
    'thresh': 0.1,
    'topk': 10
}
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 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
translate_x_relative Ran
ran on a synthesized input
nku-shengzheliu/PaddlePaddle-Swin-Transformer-V2/auto_augment.py
code served (permissive licence) · get_code("5931b70ac74f0d83")
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 Image. 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 random
from PIL import Image

# Create a small test image
test_image = Image.new('RGB', (100, 80), color=(200, 100, 50))

ARGS = {
    'image': test_image,
    'magnitude': 0.2,
    'fillcolor': (128, 128, 128)
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int 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
trim_preceding_hyphens Ran
ran; our contract draft was wrong, not the code
lyqcom/aaic_swintransformerv2/src/configs/parser.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from Seongyeol-kim/FedWSQ, is pointer only (licence: NONE) · get_code("a99f170ebd682af5")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from Seongyeol-kim/FedWSQ, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

update_config Ran
ran on a synthesized input
nku-shengzheliu/PaddlePaddle-Swin-Transformer-V2/config.py
code served (permissive licence) · get_code("1e4ddb470d424318")
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 MockConfig. 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 os
import yaml
import tempfile
from unittest.mock import MagicMock

# Create a mock config object with the required structure and methods
class MockConfig:
    def __init__(self):
        self.DATA = MagicMock()
        self.DATA.DATASET = None
        self.DATA.BATCH_SIZE = 32
        self.DATA.IMAGE_SIZE = 224
        self.DATA.DATA_PATH = "/path/to/data"
        self.DATA.BATCH_SIZE_EVAL = 64
        self.MODEL = MagicMock()
        self.MODEL.PRETRAINED = None
        self.MODEL.RESUME = None
        self.TRAIN = MagicMock()
        self.TRAIN.LAST_EPOCH = 0
        self.NGPUS = 1
        self.EVAL = False
        self.AMP = False
        self._is_frozen = False
    
    def defrost(self):
        self._is_frozen = False
    
    def freeze(self):
        self._is_frozen = True
    
    def merge_from_file(self, cfg_file):
        # Mock implementation - just pretend to merge
        pass

# Create a temporary YAML config file
temp_dir = tempfile.mkdtemp()
cfg_file = os.path.join(temp_dir, "config.yaml")
with open(cfg_file, 'w') as f:
    yaml.dump({'BASE': []}, f)

# Create a mock args object
class MockArgs:
    def __init__(self):
        self.cfg = None
        self.dataset = "imagenet"
        self.batch_size = 64
        self.image_size = 256
        self.data_path = "/data/imagenet"
        self.ngpus = 2
        self.eval = False
        self.pretrained = None
        self.resume = None
        self.last_epoch = None
        self.amp = False

config = MockConfig()
args = MockArgs()

ARGS = {
    "config": config,
    "args": args
}
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 MockConfig — a MockConfig output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a MockConfig 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
apply_for_scriptable_torch Not yet run
unverified (harvested, no recorded run)
JunnYu/x-transformers-paddle/einops/_torch_specific.py
code served (permissive licence) · get_code("29b5922a6530d4e2")
How it ran

no invocation recorded.

check_model_file Not yet run
unverified (harvested, no recorded run)
Qdriving/Swin-TransformerV2-in-PP/paddleclas.py
code served (permissive licence) · get_code("a39394c9a8e29425")
How it ran

no invocation recorded.

get_backend Not yet run
unverified (harvested, no recorded run)
JunnYu/x-transformers-paddle/einops/_backends.py
code served (permissive licence) · get_code("a9ebd0f6584234a5")
How it ran

no invocation recorded.

get_config Not yet run
unverified (harvested, no recorded run)
nku-shengzheliu/PaddlePaddle-Swin-Transformer-V2/config.py
code served (permissive licence) · get_code("160fd4002bd2e51b")
How it ran

no invocation recorded.

rearrange Not yet run
unverified (harvested, no recorded run)
JunnYu/x-transformers-paddle/einops/einops.py
code served (permissive licence) · get_code("942acecd8aa049a5")
How it ran

no invocation recorded.

reduce Not yet run
unverified (harvested, no recorded run)
JunnYu/x-transformers-paddle/einops/einops.py
code served (permissive licence) · get_code("6913149f68bd7808")
How it ran

no invocation recorded.

window_partition Not yet run
unverified (harvested, no recorded run)
lyqcom/aaic_swintransformerv2/src/models/swin_transformer.py
code served (permissive licence) · get_code("73879546dbb5b1b1")
How it ran

no invocation recorded.

window_partition Not yet run
unverified (harvested, no recorded run)
Qdriving/Swin-TransformerV2-in-PP/ppcls/arch/backbone/model_zoo/swin_transformer.py
code served (permissive licence) · get_code("0fd983e99eaff69e")
How it ran

no invocation recorded.

window_reverse Not yet run
unverified (harvested, no recorded run)
Qdriving/Swin-TransformerV2-in-PP/ppcls/arch/backbone/model_zoo/swin_transformer.py
code served (permissive licence) · get_code("1a004818e36b501f")
How it ran

no invocation recorded.

window_reverse Not yet run
unverified (harvested, no recorded run)
lyqcom/aaic_swintransformerv2/src/models/swin_transformer.py
code served (permissive licence) · get_code("1129d77773d2fc84")
How it ran

no invocation recorded.

window_reverse Not yet run
unverified (harvested, no recorded run)
lyqcom/aaic_swintransformerv2/src/models/swin_transformer_v2.py
code served (permissive licence) · get_code("db165c23fedab0fa")
How it ran

no invocation recorded.

windows_partition Not yet run
unverified (harvested, no recorded run)
nku-shengzheliu/PaddlePaddle-Swin-Transformer-V2/swin_transformer.py
code served (permissive licence) · get_code("e14035f3e23f1d93")
How it ran

no invocation recorded.

windows_reverse Not yet run
unverified (harvested, no recorded run)
nku-shengzheliu/PaddlePaddle-Swin-Transformer-V2/swin_transformer.py
code served (permissive licence) · get_code("3f5cac22adf9d786")
How it ran

no invocation recorded.

Also present in other papers' code

Of 30 samples lifted from this paper's linked repositories, 30 carry a function identity and 0 do not. Of the 30 distinct functions with an identity, 12 are also present in other papers whose code we hold (11 with at least one paper dated earlier, 5 the same month, 9 later) and 18 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
exists 486 other papers
69 dated earlier, 2 the same month, 413 later, 2 undated · 78 only as an assembly brick
1603.08155 (2016-03)
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
1804.04637 (2018-04)
EMBER: An Open Dataset for Training Static PE Malware Machine Learning Models
and 483 more not named here
default 207 other papers
9 dated earlier, 198 later · 41 only as an assembly brick
1711.11585 (2017-11)
High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2010.08162 (2020-10)
SidechainNet: An All-Atom Protein Structure Dataset for Machine Learning
and 204 more not named here
arg_to_varname 9 other papers
5 dated earlier, 1 the same month, 3 later
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
1911.13299 (2019-11)
What's Hidden in a Randomly Weighted Neural Network?
2104.00298 (2021-04)
EfficientNetV2: Smaller Models and Faster Training
and 6 more not named here
trim_preceding_hyphens 9 other papers
5 dated earlier, 1 the same month, 3 later
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
1911.13299 (2019-11)
What's Hidden in a Randomly Weighted Neural Network?
2104.00298 (2021-04)
EfficientNetV2: Smaller Models and Faster Training
and 6 more not named here
argv_to_vars 8 other papers
4 dated earlier, 1 the same month, 3 later
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
1911.13299 (2019-11)
What's Hidden in a Randomly Weighted Neural Network?
2104.00298 (2021-04)
EfficientNetV2: Smaller Models and Faster Training
and 5 more not named here
cast_tuple 7 other papers
3 dated earlier, 4 later · 1 only as an assembly brick
2102.13419 (2021-02)
Iterative SE(3)-Transformers
2105.12723 (2021-05)
Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding
2105.15203 (2021-05)
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers
and 4 more not named here
rerange_index 3 other papers
2 dated earlier, 1 later
1807.11626 (2018-07)
MnasNet: Platform-Aware Neural Architecture Search for Mobile
1904.05049 (2019-04)
Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution
2204.02557 (2022-04)
MixFormer: Mixing Features across Windows and Dimensions
check_model_file 2 other papers
2 dated earlier
1807.11626 (2018-07)
MnasNet: Platform-Aware Neural Architecture Search for Mobile
1904.05049 (2019-04)
Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution
get_config 2 other papers
1 dated earlier, 1 the same month
2103.17239 (2021-03)
Going deeper with Image Transformers
2111.06377 (2021-11)
Masked Autoencoders Are Scalable Vision Learners
get_logger 2 other papers
1 dated earlier, 1 later
1702.00758 (2017-02)
HashNet: Deep Learning to Hash by Continuation
2408.03675 (2024-08)
NACL: A General and Effective KV Cache Eviction Framework for LLMs at Inference Time
similar_architectures 2 other papers
2 dated earlier
1807.11626 (2018-07)
MnasNet: Platform-Aware Neural Architecture Search for Mobile
1904.05049 (2019-04)
Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution
window_partition 1 other paper
1 later
2208.05114 (2022-08)
Ghost-free High Dynamic Range Imaging with Context-aware Transformer

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

Large-scale NLP models have been shown to significantly improve the performance on language tasks with no signs of saturation. They also demonstrate amazing few-shot capabilities like that of human beings. This paper aims to explore large-scale models in computer vision. We tackle three major issues in training and application of large vision models, including training instability, resolution gaps between pre-training and fine-tuning, and hunger on labelled data. Three main techniques are proposed: 1) a residual-post-norm method combined with cosine attention to improve training stability; 2) A log-spaced continuous position bias method to effectively transfer models pre-trained using low-resolution images to downstream tasks with high-resolution inputs; 3) A self-supervised pre-training method, SimMIM, to reduce the needs of vast labeled images. Through these techniques, this paper successfully trained a 3 billion-parameter Swin Transformer V2 model, which is the largest dense vision model to date, and makes it capable of training with images of up to 1,536$\times$1,536 resolution. It set new performance records on 4 representative vision tasks, including ImageNet-V2 image classification, COCO object detection, ADE20K semantic segmentation, and Kinetics-400 video action classification. Also note our training is much more efficient than that in Google's billion-level visual models, which consumes 40 times less labelled data and 40 times less training time. Code is available at \url{https://github.com/microsoft/Swin-Transformer}.

For agents

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

get_harvested_code_for_paper("2111.09883")
get_code_for_paper("2111.09883")
have("2111.09883")

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

curl https://syntology.ai/api/ran/2111.09883.json

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

[![Syntology run record](https://syntology.ai/api/ran/2111.09883.svg)](https://syntology.ai/paper/2111.09883)

Connect an agent — have() is free.