SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2301.06281 · CVPR · 2023

DPE: Disentanglement of Pose and Expression for General Video Portrait Editing

Yong Zhang, Dong-Ming Yan, Yanbo Fan, Ying Shan, Xiaodong Cun, Weize Quan, Youxin Pang

arXiv · PDF · Open in the Atlas

Code that ran

15 of 23 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (9 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 1 violated it and 11 have no contract verdict; 3 failures of our instrument; 8 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/2301.06281.json · badge: /api/ran/2301.06281.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
Carlyx/DPE marked official in Papers with Code
Papers with Code archive
14 ran · 8 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
FunctionStatusWhere it lives
Blur Ran
ran on a synthesized input · constructed an object; no result was computed
Carlyx/DPE/networks/generator.py
code served (permissive licence) · get_code("d56e5456e614facc")
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 an instance of its own class, Blur: the run constructed the object and did not call it, so no result was computed. 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.nn import functional as F

torch.manual_seed(0)

ARGS = {
    'kernel': [1.0, 2.0, 1.0],
    'pad': (1, 1),
    'upsample_factor': 1
}
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 Blur — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a Blur 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
ConstantInput Ran
ran on a synthesized input
Carlyx/DPE/networks/generator.py
code served (permissive licence) · get_code("2791e7e6779bf494")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, ndim 4, dtype family float, shape (2, 8, 4, 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
from torch import nn

class ConstantInput(nn.Module):

    def __init__(self, channel, size=4):
        super().__init__()
        self.input = nn.Parameter(torch.randn(1, channel, size, size))

    def forward(self, input):
        batch = input.shape[0]
        out = self.input.repeat(batch, 1, 1, 1)
        return out


INIT_ARGS = {
    'channel': 8,
    'size': 4,
}

ARGS = {
    'input': torch.randn(2, 3, 5, 5),
}

if __name__ == '__main__':
    model = ConstantInput(**INIT_ARGS)
    output = model(**ARGS)
    print(f"Output shape: {output.shape}")
    print(f"Expected shape: (2, 8, 4, 4)")
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
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 (2, 8, 4, 4) — shape (2, 8, 4, 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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
Direction Ran
ran on a synthesized input · constructed an object; no result was computed
Carlyx/DPE/networks/generator.py
code served (permissive licence) · get_code("9f3db3d59434def1")
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 an instance of its own class, Direction: the run constructed the object and did not call it, so no result was computed. 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)

# The Direction class takes motion_dim as parameter
# Looking at the forward method:
# - It creates weight of shape (512, motion_dim)
# - Performs QR decomposition on weight
# - If input is None, returns Q
# - Otherwise, treats input as a diagonal and multiplies with Q.T
# - input should be 1D for diag_embed to work properly

motion_dim = 4

ARGS = {
    "motion_dim": motion_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 Direction — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a Direction 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
EncoderApp Ran
ran on a synthesized input · constructed an object; no result was computed
Carlyx/DPE/networks/generator.py
code served (permissive licence) · get_code("48671646da78ef35")
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 an instance of its own class, EncoderApp: the run constructed the object and did not call it, so no result was computed. 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
from torch import nn

torch.manual_seed(0)

ARGS = {
    'size': 256,
    'w_dim': 512,
}
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 EncoderApp — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a EncoderApp 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
EqualConv2d Ran
ran on a synthesized input · constructed an object; no result was computed
Carlyx/DPE/networks/generator.py
code served (permissive licence) · get_code("56cc85f0f1ca1e37")
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 an instance of its own class, EqualConv2d: the run constructed the object and did not call it, so no result was computed. 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
from torch import nn
from torch.nn import functional as F

class EqualConv2d(nn.Module):

    def __init__(self, in_channel, out_channel, kernel_size, stride=1, padding=0, bias=True):
        super().__init__()
        self.weight = nn.Parameter(torch.randn(out_channel, in_channel, kernel_size, kernel_size))
        self.scale = 1 / math.sqrt(in_channel * kernel_size ** 2)
        self.stride = stride
        self.padding = padding
        if bias:
            self.bias = nn.Parameter(torch.zeros(out_channel))
        else:
            self.bias = None

    def forward(self, input):
        return F.conv2d(input, self.weight * self.scale, bias=self.bias, stride=self.stride, padding=self.padding)

    def __repr__(self):
        return f'{self.__class__.__name__}({self.weight.shape[1]}, {self.weight.shape[0]}, {self.weight.shape[2]}, stride={self.stride}, padding={self.padding})'

torch.manual_seed(0)

ARGS = {
    'in_channel': 3,
    'out_channel': 16,
    'kernel_size': 3,
    'stride': 1,
    'padding': 1,
    'bias': True
}
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 EqualConv2d — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a EqualConv2d 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
EqualLinear Ran
ran on a synthesized input · constructed an object; no result was computed
Carlyx/DPE/networks/generator.py
code served (permissive licence) · get_code("ada97d5a14aed1a7")
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 an instance of its own class, EqualLinear: the run constructed the object and did not call it, so no result was computed. 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)

# Build arguments for EqualLinear
in_dim = 4
out_dim = 3
bias = True
bias_init = 0.1
lr_mul = 2.0
activation = "lrelu"  # or None

ARGS = {
    "in_dim": in_dim,
    "out_dim": out_dim,
    "bias": bias,
    "bias_init": bias_init,
    "lr_mul": lr_mul,
    "activation": activation,
}
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 EqualLinear — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a EqualLinear 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
FusedLeakyReLU Ran
ran on a synthesized input · constructed an object; no result was computed
Carlyx/DPE/networks/generator.py
code served (permissive licence) · get_code("1bfc9df1f20629ae")
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 an instance of its own class, FusedLeakyReLU: the run constructed the object and did not call it, so no result was computed. 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
from torch import nn

torch.manual_seed(0)

# FusedLeakyReLU.__init__ takes: channel, negative_slope=0.2, scale=2**0.5
# We need to provide these arguments for instantiation

ARGS = {
    "channel": 4,
    "negative_slope": 0.2,
    "scale": 2 ** 0.5
}
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 FusedLeakyReLU — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a FusedLeakyReLU 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
ModulatedConv2d Ran
ran on a synthesized input · constructed an object; no result was computed
Carlyx/DPE/networks/generator.py
code served (permissive licence) · get_code("fbc7a646183a73f6")
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 an instance of its own class, ModulatedConv2d: the run constructed the object and did not call it, so no result was computed. 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
import math

torch.manual_seed(0)

ARGS = {
    'in_channel': 3,
    'out_channel': 4,
    'kernel_size': 3,
    'style_dim': 8,
    'demodulate': True,
    'upsample': False,
    'downsample': False,
    'blur_kernel': [1, 3, 3, 1]
}
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 ModulatedConv2d — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a ModulatedConv2d 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
NoiseInjection Ran
ran on a synthesized input
Carlyx/DPE/networks/generator.py
code served (permissive licence) · get_code("a803ab12c3986ffc")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, 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 numpy as np

# NoiseInjection.__init__ takes no parameters beyond self
INIT_ARGS = {}

# forward takes image and optional noise
# Create a small batch of images and noise with distinct dimensions
batch_size = 2
channels = 3
height = 8
width = 6

image = torch.randn(batch_size, channels, height, width)
noise = torch.randn(batch_size, channels, height, width)

ARGS = {
    'image': image,
    'noise': noise
}
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
numpy, 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 — no output shape is stated: observe_signature.py observed this class with its constructor sizes canonicalised where it could, which the node does not record, so its shape is not stated as this setup block's
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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
ScaledLeakyReLU Ran
ran on a synthesized input · constructed an object; no result was computed
Carlyx/DPE/networks/generator.py
code served (permissive licence) · get_code("bd5e20e1864404e7")
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 an instance of its own class, ScaledLeakyReLU: the run constructed the object and did not call it, so no result was computed. 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
from torch import nn

torch.manual_seed(0)

# ScaledLeakyReLU only uses the negative_slope parameter in __init__
# The forward method takes an input tensor and applies F.leaky_relu with that slope
# So we need to construct valid arguments for __init__

ARGS = {
    'negative_slope': 0.2
}
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 ScaledLeakyReLU — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a ScaledLeakyReLU 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
Upsample Ran
ran on a synthesized input · constructed an object; no result was computed
Carlyx/DPE/networks/generator.py
code served (permissive licence) · get_code("3cb4513942fd17d4")
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 an instance of its own class, Upsample: the run constructed the object and did not call it, so no result was computed. 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.nn import functional as F

torch.manual_seed(0)

ARGS = {
    'kernel': [1.0, 2.0, 1.0],
    'factor': 2
}
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 Upsample — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a Upsample 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
fused_leaky_relu Ran
ran; our contract draft was wrong, not the code
Carlyx/DPE/networks/generator.py
code served (permissive licence) · get_code("44c69c91b5434020")
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
import torch.nn as nn

torch.manual_seed(0)

# Create tiny tensors for the function parameters
input_tensor = torch.randn(2, 4)
bias_tensor = torch.randn(4)

# Build the ARGS dictionary with all parameters
ARGS = {
    'input': input_tensor,
    'bias': bias_tensor,
    'negative_slope': 0.2,
    'scale': 2 ** 0.5
}
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
make_kernel Ran
ran, violated the contract we drafted
this paper's copy was not recorded; identical code first harvested from dkn16/multi-fidel-gan-21cm
pointer only; the stored copy get_code serves, from dkn16/multi-fidel-gan-21cm, is pointer only (licence: NOASSERTION) · get_code("6f65e378a4313f87")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

upfirdn2d Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Carlyx/DPE/networks/generator.py
code served (permissive licence) · get_code("c5d084250637f1f8")
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 4, dtype family float, shape (2, 4, 1, 3) 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.functional as F

torch.manual_seed(0)

# Create a small input tensor: (batch=2, channels=4, height=3, width=5)
input_tensor = torch.randn(2, 4, 3, 5)

# Create a small kernel tensor: (kernel_h=3, kernel_w=3)
kernel_tensor = torch.randn(3, 3)

# Define upsampling factors
up_factor = 1

# Define downsampling factors
down_factor = 1

# Define padding
pad_tuple = (0, 0)

ARGS = {
    "input": input_tensor,
    "kernel": kernel_tensor,
    "up": up_factor,
    "down": down_factor,
    "pad": pad_tuple,
}
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 4, dtype family float, shape (2, 4, 1, 3) — shape (2, 4, 1, 3) 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
upfirdn2d_native Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Carlyx/DPE/networks/generator.py
code served (permissive licence) · get_code("200baf9e83c9a4de")
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 4, dtype family float, shape (2, 4, 6, 10) 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
import torch.nn.functional as F

torch.manual_seed(0)

# Create small test tensors
batch_size = 2
minor = 4
in_h = 3
in_w = 5

input_tensor = torch.randn(batch_size, minor, in_h, in_w)

# Kernel tensor - small upsampling kernel
kernel = torch.randn(3, 3)

# Upsampling factors
up_x = 2
up_y = 2

# Downsampling factors
down_x = 1
down_y = 1

# Padding parameters
pad_x0 = 1
pad_x1 = 1
pad_y0 = 1
pad_y1 = 1

ARGS = {
    "input": input_tensor,
    "kernel": kernel,
    "up_x": up_x,
    "up_y": up_y,
    "down_x": down_x,
    "down_y": down_y,
    "pad_x0": pad_x0,
    "pad_x1": pad_x1,
    "pad_y0": pad_y0,
    "pad_y1": pad_y1,
}
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 4, dtype family float, shape (2, 4, 6, 10) — shape (2, 4, 6, 10) 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
ConvLayer Not yet run
unverified (harvested, no recorded run)
Carlyx/DPE/networks/generator.py
code served (permissive licence) · get_code("8c8d2d8103bf9805")
How it ran

no invocation recorded.

Encoder Not yet run
unverified (harvested, no recorded run)
Carlyx/DPE/networks/generator.py
code served (permissive licence) · get_code("52dad034d993c841")
How it ran

no invocation recorded.

Generator Not yet run
unverified (harvested, no recorded run)
Carlyx/DPE/networks/generator.py
code served (permissive licence) · get_code("aaeb71b262fddbbc")
How it ran

no invocation recorded.

ResBlock Not yet run
unverified (harvested, no recorded run)
Carlyx/DPE/networks/generator.py
code served (permissive licence) · get_code("8db5aa5bd9cfcd07")
How it ran

no invocation recorded.

StyledConv Not yet run
unverified (harvested, no recorded run)
Carlyx/DPE/networks/generator.py
code served (permissive licence) · get_code("fe5a013ac94efe7a")
How it ran

no invocation recorded.

Synthesis Not yet run
unverified (harvested, no recorded run)
Carlyx/DPE/networks/generator.py
code served (permissive licence) · get_code("0a86e04f7ae8efc1")
How it ran

no invocation recorded.

ToFlow Not yet run
unverified (harvested, no recorded run)
Carlyx/DPE/networks/generator.py
code served (permissive licence) · get_code("4a62baba6f413f56")
How it ran

no invocation recorded.

ToRGB Not yet run
unverified (harvested, no recorded run)
Carlyx/DPE/networks/generator.py
code served (permissive licence) · get_code("a394679999e6ea1c")
How it ran

no invocation recorded.

Also present in other papers' code

Of 23 samples lifted from this paper's linked repositories, 23 carry a function identity and 0 do not. Of the 23 distinct functions with an identity, 8 are also present in other papers whose code we hold (8 with at least one paper dated earlier, 0 the same month, 8 later) and 15 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
make_kernel
brick of this paper's assembly: helper
40 other papers
31 dated earlier, 9 later · 10 only as an assembly brick
1812.04948 (2018-12)
A Style-Based Generator Architecture for Generative Adversarial Networks
1912.04958 (2019-12)
Analyzing and Improving the Image Quality of StyleGAN
2007.06600 (2020-07)
Closed-Form Factorization of Latent Semantics in GANs
and 37 more not named here
fused_leaky_relu
brick of this paper's assembly: helper
10 other papers
4 dated earlier, 5 later, 1 same year, order not determinable · 3 only as an assembly brick
2007.15651 (2020-07)
Contrastive Learning for Unpaired Image-to-Image Translation
2104.11116 (2021-04)
Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representation
2204.13656 (2022-04)
Unsupervised Multi-Modal Medical Image Registration via Discriminator-Free Image-to-Image Translation
and 7 more not named here
upfirdn2d_native
brick of this paper's assembly: helper
9 other papers
3 dated earlier, 5 later, 1 same year, order not determinable · 2 only as an assembly brick
2007.15651 (2020-07)
Contrastive Learning for Unpaired Image-to-Image Translation
2104.11116 (2021-04)
Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representation
2204.13656 (2022-04)
Unsupervised Multi-Modal Medical Image Registration via Discriminator-Free Image-to-Image Translation
and 6 more not named here
ConstantInput
brick of this paper's assembly: helper
8 other papers
7 dated earlier, 1 later · 5 only as an assembly brick
1812.04948 (2018-12)
A Style-Based Generator Architecture for Generative Adversarial Networks
2101.02477 (2021-01)
GAN-Control: Explicitly Controllable GANs
2103.17249 (2021-03)
StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery
and 5 more not named here
EqualLinear
brick of this paper's assembly: helper
8 other papers
6 dated earlier, 2 later
1812.04948 (2018-12)
A Style-Based Generator Architecture for Generative Adversarial Networks
2101.02477 (2021-01)
GAN-Control: Explicitly Controllable GANs
2103.17249 (2021-03)
StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery
and 5 more not named here
upfirdn2d
brick of this paper's assembly: helper
6 other papers
3 dated earlier, 2 later, 1 same year, order not determinable · 2 only as an assembly brick
2007.15651 (2020-07)
Contrastive Learning for Unpaired Image-to-Image Translation
2104.11116 (2021-04)
Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representation
2204.13656 (2022-04)
Unsupervised Multi-Modal Medical Image Registration via Discriminator-Free Image-to-Image Translation
and 3 more not named here
FusedLeakyReLU
brick of this paper's assembly: helper
3 other papers
2 dated earlier, 1 later · 2 only as an assembly brick
2204.13656 (2022-04)
Unsupervised Multi-Modal Medical Image Registration via Discriminator-Free Image-to-Image Translation
2209.09502 (2022-09)
GAMA: Generative Adversarial Multi-Object Scene Attacks
2602.04307 (2026-02)
Universal Robust Speech Adaptation for Cross-Domain Speech Recognition and Enhancement
ConvLayer
brick of this paper's assembly: helper
2 other papers
1 dated earlier, 1 later · 1 only as an assembly brick
2204.13656 (2022-04)
Unsupervised Multi-Modal Medical Image Registration via Discriminator-Free Image-to-Image Translation
2602.04307 (2026-02)
Universal Robust Speech Adaptation for Cross-Domain Speech Recognition and Enhancement

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

modified latent codes to images, respectively. Moreover, to guarantee the disentanglement, we propose a bidirectional cyclic training strategy with well-designed constraints. Evaluations demonstrate our method can control pose or expression independently and be used for general video editing.

For agents

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

get_harvested_code_for_paper("2301.06281")
get_code_for_paper("2301.06281")
have("2301.06281")

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

curl https://syntology.ai/api/ran/2301.06281.json

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

[![Syntology run record](https://syntology.ai/api/ran/2301.06281.svg)](https://syntology.ai/paper/2301.06281)

Connect an agent — have() is free.