SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1607.08022 · 2016

Instance Normalization: The Missing Ingredient for Fast Stylization

arXiv · PDF · Open in the Atlas

Code that ran

16 of 18 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 12 have no contract verdict; 4 failures of our instrument; 2 no recorded run), measured 2026-11-21; 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/1607.08022.json · badge: /api/ran/1607.08022.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
Net-Mist/style-transfer-tf2 community (classifier label)
classifier basis not recorded on the link
11 ran · 0 no recorded run
brightyoun/Video-Style-Transfer community (classifier label)
classifier basis not recorded on the link
3 ran · 1 no recorded run
hollygrimm/cyclegan-keras-art-attrs community (classifier label)
classifier basis not recorded on the link
2 ran · 1 no recorded run
FunctionStatusWhere it lives
abs_criterion Ran
ran on a synthesized input
Net-Mist/style-transfer-tf2/src/losses.py
code served (permissive licence) · get_code("54e8627bef847403")
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 EagerTensor, 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 tensorflow as tf
import numpy as np

# Create small sample tensors
logits = tf.constant([[1.0, 2.0, 3.0, 4.0],
                      [5.0, 6.0, 7.0, 8.0]], dtype=tf.float32)

target = tf.constant([[1.5, 1.8, 3.2, 3.9],
                      [5.1, 5.9, 7.2, 8.1]], dtype=tf.float32)

ARGS = {
    "logits": logits,
    "target": target,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, 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
bytes_feature Ran
ran; our contract draft was wrong, not the code
Net-Mist/style-transfer-tf2/src/tfrecord.py
code served (permissive licence) · get_code("d682a9593710857e")
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 Feature. 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 tensorflow as tf

# bytes_feature expects a single parameter 'value' which should be bytes
# The function wraps it in tf.train.BytesList and then tf.train.Feature

ARGS = {
    "value": b"example_bytes_data"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Feature — a Feature output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Feature 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
discriminator_loss Ran
ran on a synthesized input
Net-Mist/style-transfer-tf2/src/losses.py
code served (permissive licence) · get_code("4d3711e216e605bf")
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 tensorflow as tf
import numpy as np

# Set seed for reproducibility
tf.random.set_seed(0)

# Create small discriminator prediction tensors
# The function iterates over these lists and applies _discriminator_loss to each element
# Each element should be a tensor of logits (unbounded float values)

# Batch size 2, discriminator output dim 1 (single scalar per sample)
batch_size = 2
logit_dim = 1

# Create lists of prediction tensors
# discriminate_art: predictions that should be classified as 1 (art)
discriminate_art = [
    tf.random.normal((batch_size, logit_dim), dtype=tf.float32),
    tf.random.normal((batch_size, logit_dim), dtype=tf.float32),
]

# discriminate_picture: predictions that should be classified as 0 (regular pictures)
discriminate_picture = [
    tf.random.normal((batch_size, logit_dim), dtype=tf.float32),
    tf.random.normal((batch_size, logit_dim), dtype=tf.float32),
]

# discriminate_encoded_picture: predictions that should be classified as 0 (encoded pictures)
discriminate_encoded_picture = [
    tf.random.normal((batch_size, logit_dim), dtype=tf.float32),
    tf.random.normal((batch_size, logit_dim), dtype=tf.float32),
]

ARGS = {
    'discriminate_encoded_picture': discriminate_encoded_picture,
    'discriminate_picture': discriminate_picture,
    'discriminate_art': discriminate_art,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — 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
get_config_from_json Ran
ran; our contract draft was wrong, not the code
hollygrimm/cyclegan-keras-art-attrs/utils/utils.py
code served (permissive licence) · get_code("f31979b7dfe88d5e")
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 dict. 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 json
import tempfile
import os

# Create a temporary JSON file with a valid config
temp_dir = tempfile.mkdtemp()
json_file_path = os.path.join(temp_dir, "config.json")

config_data = {
    "model": "test_model",
    "learning_rate": 0.001,
    "batch_size": 32,
    "epochs": 10,
    "hidden_dim": 128,
    "layers": [64, 128, 256]
}

with open(json_file_path, 'w') as f:
    json.dump(config_data, f)

ARGS = {
    "json_file": json_file_path
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
gram_matrix Ran
ran; our contract draft was wrong, not the code
brightyoun/Video-Style-Transfer/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from davidpengucf/SFDAHPE, is pointer only (licence: NONE) · get_code("430c582cd8bbb1df")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from davidpengucf/SFDAHPE, 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.

image_postprocess Ran
ran on a synthesized input
Net-Mist/style-transfer-tf2/src/inference.py
code served (permissive licence) · get_code("35d23f8a7f5739a1")
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 3, dtype family int, shape (3, 4, 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 cv2
import numpy as np
import torch

torch.manual_seed(0)

# Construct a valid image tensor for the function
# The function expects:
# - image[0, :, :, :] to extract first item from batch
# - pixel values that will be transformed: ((image + 1) * 127.5)
# - conversion from RGB to BGR via cv2.cvtColor
# 
# Create a batch of 2 RGB images, with height 3, width 4, and 3 channels (RGB)
# Values should be in range [-1, 1] based on how the postprocessing works
image = np.random.uniform(-1, 1, size=(2, 3, 4, 3)).astype(np.float32)

ARGS = {
    "image": image
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family int, shape (3, 4, 3) — shape (3, 4, 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
image_preprocess Ran
ran on a synthesized input
Net-Mist/style-transfer-tf2/src/inference.py
code served (permissive licence) · get_code("4ad5af47aa088209")
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 4, dtype family float, shape (1, 480, 640, 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 cv2
import numpy as np

# Create a small sample BGR image (OpenCV format)
# Using a small 480x640 image to match the resized_shape expectation
image = np.random.randint(0, 255, size=(480, 640, 3), dtype=np.uint8)

# resized_shape parameter (though it's not actually used in the function body)
resized_shape = (640, 480)

ARGS = {
    'image': image,
    'resized_shape': resized_shape
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 4, dtype family float, shape (1, 480, 640, 3) — shape (1, 480, 640, 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
int64_feature Ran
ran; our contract draft was wrong, not the code
Net-Mist/style-transfer-tf2/src/tfrecord.py
code served (permissive licence) · get_code("328d17201d9a0e68")
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 Feature. 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 tensorflow as tf

def int64_feature(value):
    return tf.train.Feature(int64_list=tf.train.Int64List(value=[value]))

ARGS = {
    "value": 42
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Feature — a Feature output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Feature 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
int64_list_feature Ran
ran on a synthesized input
Net-Mist/style-transfer-tf2/src/tfrecord.py
code served (permissive licence) · get_code("f6d735872f4495ed")
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 Feature. 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 tensorflow as tf

# The function expects a 'value' parameter that will be passed to
# tf.train.Int64List(value=value). This should be an iterable of integers.

ARGS = {
    "value": [1, 2, 3, 4, 5]
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Feature — a Feature output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Feature 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
inverted_res_block Ran
ran on a synthesized input
Net-Mist/style-transfer-tf2/src/model.py
code served (permissive licence) · get_code("f169004dc49d5433")
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 SymbolicTensor. 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 tensorflow as tf
from tensorflow import keras
import numpy as np

# Create a tiny input tensor: batch_size=2, height=4, width=4, channels=3
inputs = tf.constant(np.random.randn(2, 4, 4, 3).astype(np.float32))

# stride parameter
stride = 1

# in_channels parameter
in_channels = 3

# out_channels parameter
out_channels = 5

# norm_layer parameter - a callable that returns a normalization layer
norm_layer = keras.layers.BatchNormalization

# expansion parameter
expansion = 1

ARGS = {
    "inputs": inputs,
    "stride": stride,
    "in_channels": in_channels,
    "out_channels": out_channels,
    "norm_layer": norm_layer,
    "expansion": expansion,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type SymbolicTensor — a SymbolicTensor 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
load_image Ran
ran on a synthesized input
brightyoun/Video-Style-Transfer/utils.py
code served (permissive licence) · get_code("698dca7627594fdb")
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 PngImageFile. 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 tempfile
import os
from PIL import Image
import numpy as np

# Create a temporary image file for testing
temp_dir = tempfile.mkdtemp()
temp_image_path = os.path.join(temp_dir, "test_image.png")

# Create a simple test image
test_array = np.random.randint(0, 256, (100, 150, 3), dtype=np.uint8)
test_image = Image.fromarray(test_array)
test_image.save(temp_image_path)

# Define arguments for load_image function
ARGS = {
    "filename": temp_image_path,
    "size": None,
    "scale": None
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type PngImageFile — a PngImageFile output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a PngImageFile 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
make_encoder_model_adaptive_style_transfer Ran
ran on a synthesized input
Net-Mist/style-transfer-tf2/src/model.py
code served (permissive licence) · get_code("4cd71027cd44ac18")
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 Sequential. 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.

from absl import flags
import tensorflow as tf
from tensorflow import keras

FLAGS = flags.FLAGS

# Set required FLAGS
flags.DEFINE_integer('image_size', 256, 'Image size')
flags.DEFINE_integer('n_filter_generator', 32, 'Number of filters for generator')
flags.DEFINE_float('l2_reg', 0.0001, 'L2 regularization')

FLAGS.mark_as_parsed()

class SimpleNormLayer(keras.layers.Layer):
    """Simple normalization layer that satisfies the norm_layer parameter requirements."""
    
    def __init__(self, input_shape=None, dtype=None, **kwargs):
        super().__init__(**kwargs)
        self.input_shape_arg = input_shape
        self.dtype_arg = dtype
    
    def call(self, inputs):
        return tf.nn.batch_normalization(inputs, mean=0.0, variance=1.0, offset=None, scale=None, variance_epsilon=1e-3)

ARGS = {
    'norm_layer': SimpleNormLayer
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
absl, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential 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
mse_criterion Ran
ran on a synthesized input
Net-Mist/style-transfer-tf2/src/losses.py
code served (permissive licence) · get_code("25abb9d374dd012a")
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 EagerTensor, ndim 0, 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 tensorflow as tf
import numpy as np

# Create small TensorFlow tensors for the function
batch_size = 2
feature_dim = 4

# Create logits tensor (model predictions)
logits = tf.constant(np.random.randn(batch_size, feature_dim), dtype=tf.float32)

# Create target tensor (ground truth)
target = tf.constant(np.random.randn(batch_size, feature_dim), dtype=tf.float32)

ARGS = {
    "logits": logits,
    "target": target,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded SymbolicTensor ndim 0, which disagrees with the fixture run
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
normalize_batch Ran
ran on a synthesized input
brightyoun/Video-Style-Transfer/utils.py
code served (permissive licence) · get_code("844101ff39c69346")
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, 3, 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

torch.manual_seed(0)

# Create a small batch tensor
# batch should be a tensor with shape (batch_size, channels, height, width)
# The function calls new_tensor() on it, views tensors, and does arithmetic
batch = torch.randint(0, 256, (2, 3, 4, 4), dtype=torch.float32)

ARGS = {
    "batch": batch
}
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, 3, 4, 4) — shape (2, 3, 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: none by the harness; any seed is in the setup block
process_config Ran
ran on a synthesized input
hollygrimm/cyclegan-keras-art-attrs/utils/utils.py
code served (permissive licence) · get_code("7081cbaca5dca320")
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 dict. 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 json
import tempfile
import os

# Create a temporary JSON file with valid configuration
temp_dir = tempfile.mkdtemp()
json_file_path = os.path.join(temp_dir, "config.json")

config_data = {
    "model": "bert",
    "batch_size": 32,
    "learning_rate": 0.001,
    "num_epochs": 10,
    "hidden_dim": 768,
    "dropout": 0.1
}

with open(json_file_path, 'w') as f:
    json.dump(config_data, f)

ARGS = {
    "json_file": json_file_path
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
relu6 Ran
ran on a synthesized input
Net-Mist/style-transfer-tf2/src/model.py
code served (permissive licence) · get_code("4ab5b6864f23abf4")
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 SymbolicTensor. 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 tensorflow as tf
import numpy as np

# Create a small test tensor
x = tf.constant([[1.0, 2.0, 3.0, 4.0],
                  [5.0, 6.0, 7.0, 8.0]], dtype=tf.float32)

ARGS = {
    "x": x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type SymbolicTensor — a SymbolicTensor 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
create_dirs Not yet run
unverified (harvested, no recorded run)
hollygrimm/cyclegan-keras-art-attrs/utils/utils.py
code served (permissive licence) · get_code("83c24e1bbc6c05f7")
How it ran

no invocation recorded.

stylize_onnx_caffe2 Not yet run
unverified (harvested, no recorded run)
brightyoun/Video-Style-Transfer/neural_style.py
code served (permissive licence) · get_code("33bdd8217a2859e8")
How it ran

no invocation recorded.

Also present in other papers' code

Of 18 samples lifted from this paper's linked repositories, 18 carry a function identity and 0 do not. Of the 18 distinct functions with an identity, 6 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 6 later) and 12 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
gram_matrix 9 other papers
2 dated earlier, 7 later
1508.06576 (2015-08)
A Neural Algorithm of Artistic Style
1603.08155 (2016-03)
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
1703.06953 (2017-03)
Multi-style Generative Network for Real-time Transfer
and 6 more not named here
bytes_feature 8 other papers
1 dated earlier, 7 later
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
1609.05158 (2016-09)
Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network
1802.05591 (2018-02)
Towards End-to-End Lane Detection: an Instance Segmentation Approach
and 5 more not named here
int64_feature 7 other papers
7 later
1611.07810 (2016-11)
A dataset and exploration of models for understanding video data through fill-in-the-blank question-answering
1802.05591 (2018-02)
Towards End-to-End Lane Detection: an Instance Segmentation Approach
1803.10562 (2018-03)
ELEGANT: Exchanging Latent Encodings with GAN for Transferring Multiple Face Attributes
and 4 more not named here
int64_list_feature 5 other papers
5 later
1803.10562 (2018-03)
ELEGANT: Exchanging Latent Encodings with GAN for Transferring Multiple Face Attributes
1812.00442 (2018-12)
Deep Cosine Metric Learning for Person Re-Identification
1904.01569 (2019-04)
Exploring Randomly Wired Neural Networks for Image Recognition
and 2 more not named here
get_config_from_json 1 other paper
1 later
2002.05810 (2020-02)
RNA Secondary Structure Prediction By Learning Unrolled Algorithms
stylize_onnx_caffe2 1 other paper
1 later
1811.08560 (2018-11)
Adjustable Real-time Style Transfer

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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

It this paper we revisit the fast stylization method introduced in Ulyanov et. al. (2016). We show how a small change in the stylization architecture results in a significant qualitative improvement in the generated images. The change is limited to swapping batch normalization with instance normalization, and to apply the latter both at training and testing times. The resulting method can be used to train high-performance architectures for real-time image generation. The code will is made available on github at https://github.com/DmitryUlyanov/texture_nets. Full paper can be found at arXiv:1701.02096.

For agents

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

get_harvested_code_for_paper("1607.08022")
get_code_for_paper("1607.08022")
have("1607.08022")

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

curl https://syntology.ai/api/ran/1607.08022.json

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

[![Syntology run record](https://syntology.ai/api/ran/1607.08022.svg)](https://syntology.ai/paper/1607.08022)

Connect an agent — have() is free.