SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.02308 · 2024

Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures

arXiv · PDF · Open in the Atlas

Code that ran

15 of 19 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; 7 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 7 failures of our instrument; 4 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/2403.02308.json · badge: /api/ran/2403.02308.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
OpenGVLab/Vision-RWKV canonical (classifier label)
classifier basis: census
15 ran · 4 no recorded run
FunctionStatusWhere it lives
allreduce_hook Ran
ran; our contract draft was wrong, not the code
OpenGVLab/Vision-RWKV/classification_internimage/ddp_hooks.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from gls0425/linvt, is pointer only (licence: NONE) · get_code("bb1a26fe42d7075c")
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 gls0425/linvt, 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.

attn_flops Ran
ran, honoured the contract we drafted
OpenGVLab/Vision-RWKV/classification/get_flops_backbone.py
code served (permissive licence) · get_code("85eb4384e6e00dc3")
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 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.

import torch

torch.manual_seed(0)

# attn_flops takes three parameters: h, w, dim
# The function computes: 2 * (h * w) * (h * w) * dim
# These are simple numeric dimensions for attention computation

h = 4
w = 3
dim = 2

ARGS = {
    'h': h,
    'w': w,
    'dim': dim
}
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 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
bf16_compress_hook Ran
ran on a synthesized input
OpenGVLab/Vision-RWKV/classification_internimage/ddp_hooks.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from gls0425/linvt, is pointer only (licence: NONE) · get_code("21bd5be56c8f79d0")
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 gls0425/linvt, 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.

build_optimizer Ran
ran; our contract draft was wrong, not the code
OpenGVLab/Vision-RWKV/classification_internimage/optimizer.py
code served (permissive licence) · get_code("c345681a7f3952a1")
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 AdamW. 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
from torch import optim as optim

torch.manual_seed(0)

# Build a minimal model that satisfies the function's expectations
class MinimalBackbone(nn.Module):
    def __init__(self):
        super().__init__()
        # Create some layers that will be picked up by named_parameters
        self.cls_token = nn.Parameter(torch.randn(1, 4))
        self.pos_embed = nn.Parameter(torch.randn(1, 4))
        self.patch_embed = nn.Linear(4, 4)
        
        # Create layers list with some blocks
        self.layers = nn.ModuleList([
            nn.Linear(4, 4),
            nn.Linear(4, 4),
            nn.Linear(4, 4),
        ])
        
        # Add some spatial decay parameters
        self.spatial_decay = nn.Parameter(torch.randn(4))
        self.spatial_first = nn.Parameter(torch.randn(4))

class MinimalModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.backbone = MinimalBackbone()
    
    def forward(self, x):
        return x

# Build minimal config
class MinimalConfig:
    class MODEL:
        TYPE = 'vrwkv'
    
    class TRAIN:
        WEIGHT_DECAY = 0.05
        OPTIMIZER = type('obj', (object,), {'NAME': 'adamw'})()
        BASE_LR = 1e-4
        LR_LAYER_DECAY = True
        LR_LAYER_DECAY_RATIO = 0.75

# Create instances
model = MinimalModel()
config = MinimalConfig()

# Define ARGS
ARGS = {
    'config': config,
    'model': model,
}
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 AdamW — a AdamW output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a AdamW 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
build_scheduler Ran
ran; our contract draft was wrong, not the code
OpenGVLab/Vision-RWKV/classification_internimage/lr_scheduler.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from leaplabthu/inline, is pointer only (licence: NONE) · get_code("07e8b4b487c0abb6")
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 leaplabthu/inline, 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.

create_logger Ran
ran; our contract draft was wrong, not the code
OpenGVLab/Vision-RWKV/classification_internimage/logger.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from ghrua/seqpe, is pointer only (licence: NONE) · get_code("80450600f7f09b0a")
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 ghrua/seqpe, 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.

fp16_compress_hook Ran
ran; our contract draft was wrong, not the code
OpenGVLab/Vision-RWKV/classification_internimage/ddp_hooks.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from gls0425/linvt, is pointer only (licence: NONE) · get_code("26bfffb625dfe211")
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 gls0425/linvt, 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_layer_id_for_vrwkv Ran
ran, honoured the contract we drafted
OpenGVLab/Vision-RWKV/classification_internimage/optimizer.py
code served (permissive licence) · get_code("cc198154486fa894")
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 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.

import torch

torch.manual_seed(0)

ARGS = {
    "name": "backbone.blocks.5.attn.qkv.weight",
    "num_layers": 12
}
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 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
get_num_layer_for_vit Ran
ran, honoured the contract we drafted
OpenGVLab/Vision-RWKV/detection/mmcv_custom/layer_decay_optimizer_constructor.py
code served (permissive licence) · get_code("62f6742745cb0637")
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 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.

import torch
import torch.nn as nn

torch.manual_seed(0)

# The function uses:
# - var_name: a string that is checked against specific prefixes and values
# - num_max_layer: an integer used in arithmetic operations

# Test case 1: var_name with backbone.cls_token
var_name_1 = 'backbone.cls_token'
num_max_layer_1 = 12

# Test case 2: var_name with backbone.blocks layer
var_name_2 = 'backbone.blocks.5.weight'
num_max_layer_2 = 12

# Test case 3: var_name with backbone.layers layer
var_name_3 = 'backbone.layers.3.bias'
num_max_layer_3 = 12

# Test case 4: var_name that doesn't match any condition
var_name_4 = 'head.fc.weight'
num_max_layer_4 = 12

# Test case 5: var_name with backbone.patch_embed
var_name_5 = 'backbone.patch_embed.proj.weight'
num_max_layer_5 = 12

# Test case 6: var_name with backbone.visual_embed
var_name_6 = 'backbone.visual_embed.weight'
num_max_layer_6 = 12

# Test case 7: var_name with backbone.pos_embed
var_name_7 = 'backbone.pos_embed'
num_max_layer_7 = 12

ARGS = {
    'var_name': 'backbone.blocks.2.attn.qkv.weight',
    'num_max_layer': 12
}
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 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
get_num_layer_for_vit Ran
ran, honoured the contract we drafted
OpenGVLab/Vision-RWKV/segmentation/mmcv_custom/layer_decay_optimizer_constructor.py
code served (permissive licence) · get_code("7e302eeb245b5b47")
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 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.

import torch

torch.manual_seed(0)

ARGS = {
    'var_name': 'backbone.blocks.5.attn.qkv.weight',
    'num_max_layer': 12
}
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 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
load_ema_checkpoint Ran
ran, honoured the contract we drafted
OpenGVLab/Vision-RWKV/classification_internimage/utils.py
code served (permissive licence) · get_code("6cfeb87841e13fbc")
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 float, 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 torch.nn as nn
from collections import OrderedDict
from unittest.mock import MagicMock

torch.manual_seed(0)

# Build a minimal config object with MODEL.RESUME attribute
class MockConfig:
    def __init__(self):
        self.MODEL = MagicMock()
        self.MODEL.RESUME = '/tmp/checkpoint.pt'

# Build a minimal model_ema object that has:
# - ema_has_module attribute
# - ema attribute with load_state_dict method
class MockEMA:
    def __init__(self):
        self.ema_has_module = False
        self.decay = 0.999
        self.ema = nn.Linear(4, 3)

# Build a minimal logger with info and warning methods
class MockLogger:
    def info(self, msg):
        pass
    
    def warning(self, msg):
        pass

# Create checkpoint dict that will be loaded
checkpoint_dict = {
    'model_ema': OrderedDict([
        ('weight', torch.randn(3, 4)),
        ('bias', torch.randn(3))
    ]),
    'max_accuracy_ema': 0.95,
    'ema_decay': 0.9999
}

# Mock torch.load to return our checkpoint without file I/O
original_torch_load = torch.load
torch.load = lambda path, **kwargs: checkpoint_dict

# Build arguments
config = MockConfig()
model_ema = MockEMA()
logger = MockLogger()

ARGS = {
    'config': config,
    'model_ema': model_ema,
    'logger': logger
}
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 float, 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
param_groups_lrd_vrwkv Ran
ran; our contract draft was wrong, not the code
OpenGVLab/Vision-RWKV/classification_internimage/optimizer.py
code served (permissive licence) · get_code("4f76ba4ee84cca1f")
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 torch.nn as nn

torch.manual_seed(0)

class MockBackbone(nn.Module):
    def __init__(self, num_layers=3):
        super().__init__()
        self.cls_token = nn.Parameter(torch.randn(1, 4))
        self.pos_embed = nn.Parameter(torch.randn(1, 10, 4))
        self.patch_embed = nn.Linear(3, 4)
        
        self.layers = nn.ModuleList([
            nn.Linear(4, 4) for _ in range(num_layers)
        ])
        
        # Add some parameters with spatial_decay and spatial_first
        self.spatial_decay = nn.Parameter(torch.randn(2, 3))
        self.spatial_first = nn.Parameter(torch.randn(5))

class MockModel(nn.Module):
    def __init__(self, num_layers=3):
        super().__init__()
        self.backbone = MockBackbone(num_layers=num_layers)
    
    def named_parameters(self):
        """Override to return model parameters with proper names"""
        for name, param in super().named_parameters():
            yield name, param

model = MockModel(num_layers=3)

ARGS = {
    'model': model,
    'weight_decay': 0.05,
    'no_weight_decay_list': ['backbone.cls_token'],
    'layer_decay': 0.75
}
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 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
q_shift Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
OpenGVLab/Vision-RWKV/classification_internimage/models/vrwkv.py
code served (permissive licence) · get_code("a2d0a36f82b566d4")
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 3, dtype family float, shape (2, 12, 8) 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)

# The function expects:
# - input: tensor of shape (B, N, C) which gets reshaped to (B, C, H, W)
# - shift_pixel: int, default 1
# - gamma: float, default 1/4
# - patch_resolution: tuple of (H, W)

# Working backwards: if input is (B, N, C) and gets reshaped to (B, C, H, W),
# then N = H * W

B = 2  # batch size
H = 4  # patch height
W = 3  # patch width
N = H * W  # 12
C = 8  # channels (must be divisible by 4 for gamma operations)

# Create input tensor of shape (B, N, C)
input_tensor = torch.randn(B, N, C)

ARGS = {
    "input": input_tensor,
    "shift_pixel": 1,
    "gamma": 1 / 4,
    "patch_resolution": (H, W)
}
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 3, dtype family float, shape (2, 12, 8) — shape (2, 12, 8) 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
vrwkv6_flops Ran
ran, honoured the contract we drafted
OpenGVLab/Vision-RWKV/classification/get_flops_backbone.py
code served (permissive licence) · get_code("d14161cfbbe61ae4")
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 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.

import torch
import numpy as np

torch.manual_seed(0)

# Based on the function signature and body, vrwkv6_flops takes three numeric parameters:
# - n: sequence length (used in multiplication)
# - dim: dimension size (used in multiplication)
# - head_size: head size (used in multiplication)

# All three are scalars used in arithmetic operations
ARGS = {
    "n": 8,
    "dim": 64,
    "head_size": 16
}
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 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
vrwkv_flops Ran
ran, honoured the contract we drafted
OpenGVLab/Vision-RWKV/classification/get_flops_backbone.py
code served (permissive licence) · get_code("dcf92f15525d8f6d")
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 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.

import torch

torch.manual_seed(0)

# The function vrwkv_flops takes two parameters:
# - n: appears to be a sequence length or count
# - dim: appears to be a dimension size
# Both are used in a simple arithmetic expression: n * dim * 29

ARGS = {
    "n": 128,      # sequence length
    "dim": 64,     # embedding dimension
}
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 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
build_model Not yet run
unverified (harvested, no recorded run)
OpenGVLab/Vision-RWKV/classification_internimage/models/build.py
code served (permissive licence) · get_code("f8e2a8ed567765db")
How it ran

no invocation recorded.

convert_22k_head_to_1k Not yet run
unverified (harvested, no recorded run)
OpenGVLab/Vision-RWKV/classification_internimage/utils.py
code served (permissive licence) · get_code("78511e137c0af18c")
How it ran

no invocation recorded.

get_config Not yet run
unverified (harvested, no recorded run)
OpenGVLab/Vision-RWKV/classification_internimage/config.py
code served (permissive licence) · get_code("5037b16e3cb5e09d")
How it ran

no invocation recorded.

load_checkpoint Not yet run
unverified (harvested, no recorded run)
OpenGVLab/Vision-RWKV/classification_internimage/utils.py
code served (permissive licence) · get_code("9f63c219db4ba592")
How it ran

no invocation recorded.

Also present in other papers' code

Of 19 samples lifted from this paper's linked repositories, 19 carry a function identity and 0 do not. Of the 19 distinct functions with an identity, 9 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 1 the same month, 7 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_config 51 other papers
27 dated earlier, 1 the same month, 19 later, 4 same year, order not determinable
2103.14030 (2021-03)
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
2106.03650 (2021-06)
Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer
2106.03746 (2021-06)
Efficient Training of Visual Transformers with Small Datasets
and 48 more not named here
create_logger 35 other papers
21 dated earlier, 12 later, 2 same year, order not determinable
2104.13840 (2021-04)
Twins: Revisiting the Design of Spatial Attention in Vision Transformers
2106.03650 (2021-06)
Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer
2106.03746 (2021-06)
Efficient Training of Visual Transformers with Small Datasets
and 32 more not named here
build_scheduler 13 other papers
6 dated earlier, 5 later, 2 same year, order not determinable
2103.14030 (2021-03)
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
2307.06947 (2023-07)
Video-FocalNets: Spatio-Temporal Focal Modulation for Video Action Recognition
2309.01430 (2023-09)
DAT++: Spatially Dynamic Vision Transformer with Deformable Attention
and 10 more not named here
allreduce_hook 2 other papers
1 dated earlier, 1 later
2401.06197 (2024-01)
Efficient Deformable ConvNets: Rethinking Dynamic and Sparse Operator for Vision Applications
2412.05185 (2024-12)
LinVT: Empower Your Image-level Large Language Model to Understand Videos
bf16_compress_hook 2 other papers
1 dated earlier, 1 later
2401.06197 (2024-01)
Efficient Deformable ConvNets: Rethinking Dynamic and Sparse Operator for Vision Applications
2412.05185 (2024-12)
LinVT: Empower Your Image-level Large Language Model to Understand Videos
fp16_compress_hook 2 other papers
1 dated earlier, 1 later
2401.06197 (2024-01)
Efficient Deformable ConvNets: Rethinking Dynamic and Sparse Operator for Vision Applications
2412.05185 (2024-12)
LinVT: Empower Your Image-level Large Language Model to Understand Videos
get_num_layer_for_vit 1 other paper
1 same year, order not determinable
05527 (2024 (year only))
A Semantic Space is Worth 256 Language Descriptions: Make Stronger Segmentation Models with Descriptive Properties
get_num_layer_for_vit 1 other paper
1 dated earlier
2306.07050 (2023-06)
Revisiting Token Pruning for Object Detection and Instance Segmentation
q_shift 1 other paper
1 later
2505.23068 (2025-05)
URWKV: Unified RWKV Model with Multi-state Perspective for Low-light Image Restoration

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

Transformers have revolutionized computer vision and natural language processing, but their high computational complexity limits their application in high-resolution image processing and long-context analysis. This paper introduces Vision-RWKV (VRWKV), a model adapted from the RWKV model used in the NLP field with necessary modifications for vision tasks. Similar to the Vision Transformer (ViT), our model is designed to efficiently handle sparse inputs and demonstrate robust global processing capabilities, while also scaling up effectively, accommodating both large-scale parameters and extensive datasets. Its distinctive advantage lies in its reduced spatial aggregation complexity, which renders it exceptionally adept at processing high-resolution images seamlessly, eliminating the necessity for windowing operations. Our evaluations demonstrate that VRWKV surpasses ViT's performance in image classification and has significantly faster speeds and lower memory usage processing high-resolution inputs. In dense prediction tasks, it outperforms window-based models, maintaining comparable speeds. These results highlight VRWKV's potential as a more efficient alternative for visual perception tasks. Code is released at https://github.com/OpenGVLab/Vision-RWKV.

For agents

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

get_harvested_code_for_paper("2403.02308")
get_code_for_paper("2403.02308")
have("2403.02308")

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

curl https://syntology.ai/api/ran/2403.02308.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.02308.svg)](https://syntology.ai/paper/2403.02308)

Connect an agent — have() is free.