SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2006.14536 · 2020

Smooth Adversarial Training

arXiv · PDF · Open in the Atlas

Code that ran

12 of 14 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 8 have no contract verdict; 4 failures of our instrument; 2 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/2006.14536.json · badge: /api/ran/2006.14536.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
cihangxie/SmoothAdversarialTraining canonical (classifier label)
classifier basis: census
12 ran · 2 no recorded run
FunctionStatusWhere it lives
blend Ran
ran; our contract draft was wrong, not the code
cihangxie/SmoothAdversarialTraining/EfficientNet/autoaugment.py
code served (permissive licence) · get_code("2a1ec1fdff9feda1")
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.compat.v1 as tf
import numpy as np

tf.disable_v2_behavior()

# Create small uint8 image tensors
# image1: 4x3 uint8 tensor
image1_data = np.array([
    [[255, 128, 64], [200, 100, 50]],
    [[150, 75, 25], [100, 50, 10]]
], dtype=np.uint8)

# image2: 4x3 uint8 tensor (different values)
image2_data = np.array([
    [[200, 100, 50], [150, 75, 25]],
    [[100, 50, 10], [50, 25, 5]]
], dtype=np.uint8)

image1 = tf.constant(image1_data, dtype=tf.uint8)
image2 = tf.constant(image2_data, dtype=tf.uint8)

# Test with factor = 0.5 (interpolation case)
factor = 0.5

ARGS = {
    "image1": image1,
    "image2": image2,
    "factor": factor
}
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
build_learning_rate Ran
ran on a synthesized input
cihangxie/SmoothAdversarialTraining/EfficientNet/utils.py
code served (permissive licence) · get_code("9f8ac1471e474b31")
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.compat.v1 as tf
import numpy as np

tf.disable_v2_behavior()

# Create a global step variable
global_step = tf.Variable(0, trainable=False, dtype=tf.int64)

# Define ARGS dict with all parameters
ARGS = {
    'initial_lr': 0.1,
    'global_step': global_step,
    'steps_per_epoch': 100,
    'lr_decay_type': 'exponential',
    'decay_factor': 0.97,
    'decay_epochs': 2.4,
    'total_steps': 1000,
    'warmup_epochs': 5
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
absl, 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
build_optimizer Ran
ran on a synthesized input
cihangxie/SmoothAdversarialTraining/EfficientNet/utils.py
code served (permissive licence) · get_code("8b0555eb0514ca06")
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 RMSPropOptimizer. 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.compat.v1 as tf

# Disable v2 behavior for TF1 compatibility
tf.disable_v2_behavior()

ARGS = {
    'learning_rate': 0.001,
    'optimizer_name': 'rmsprop',
    'decay': 0.9,
    'epsilon': 0.001,
    'momentum': 0.9,
}
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 RMSPropOptimizer — a RMSPropOptimizer output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a RMSPropOptimizer 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
cutout Ran
ran; our contract draft was wrong, not the code
cihangxie/SmoothAdversarialTraining/EfficientNet/autoaugment.py
code served (permissive licence) · get_code("ea1b2be8595d0bb3")
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.compat.v1 as tf
import numpy as np

tf.disable_v2_behavior()

# Create a small test image
# Image shape: [height, width, channels]
# Using uint8 dtype as required by the function
image_array = np.random.randint(0, 256, size=(4, 3, 3), dtype=np.uint8)
image_tensor = tf.constant(image_array, dtype=tf.uint8)

ARGS = {
    "image": image_tensor,
    "pad_size": 1,
    "replace": 0
}
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
distorted_bounding_box_crop Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
cihangxie/SmoothAdversarialTraining/EfficientNet/preprocessing.py
code served (permissive licence) · get_code("b54e5d5d7eccda19")
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.compat.v1 as tf
import numpy as np

tf.disable_v2_behavior()

# Create a minimal valid JPEG image as bytes
# A minimal 4x3 JPEG (arbitrary small dimensions)
minimal_jpeg = b'\xff\xd8\xff\xe0\x00\x10JFIF\x00\x01\x01\x00\x00\x01\x00\x01\x00\x00\xff\xdb\x00C\x00\x08\x06\x06\x07\x06\x05\x08\x07\x07\x07\t\t\x08\n\x0c\x14\r\x0c\x0b\x0b\x0c\x19\x12\x13\x0f\x14\x1d\x1a\x1f\x1e\x1d\x1a\x1c\x1c $.\' ",#\x1c\x1c(7),01444\x1f\'9=82<.342\xff\xc0\x00\x0b\x08\x00\x03\x00\x04\x01\x01\x11\x00\xff\xc4\x00\x1f\x00\x00\x01\x05\x01\x01\x01\x01\x01\x01\x00\x00\x00\x00\x00\x00\x00\x00\x01\x02\x03\x04\x05\x06\x07\x08\t\n\x0b\xff\xc4\x00\xb5\x10\x00\x02\x01\x03\x03\x02\x04\x03\x05\x05\x04\x04\x00\x00\x01}\x01\x02\x03\x00\x04\x11\x05\x12!1A\x06\x13Qa\x07"q\x142\x81\x91\xa1\x08#B\xb1\xc1\x15R\xd1\xf0$3br\x82\t\n\x16\x17\x18\x19\x1a%&\'()*456789:CDEFGHIJSTUVWXYZcdefghijstuvwxyz\x83\x84\x85\x86\x87\x88\x89\x8a\x92\x93\x94\x95\x96\x97\x98\x99\x9a\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xff\xda\x00\x08\x01\x01\x00\x00?\x00\xfb\xd4\xff\xd9'

# image_bytes: a tensor containing binary JPEG data
image_bytes = tf.constant(minimal_jpeg)

# bbox: tensor of shape [1, num_boxes, 4] with coordinates in [0, 1)
# Using 2 boxes as an example
bbox = tf.constant([
    [
        [0.1, 0.1, 0.5, 0.5],  # [ymin, xmin, ymax, xmax]
        [0.2, 0.2, 0.8, 0.8]
    ]
], dtype=tf.float32)

# min_object_covered: fraction of bounding box that must be in crop
min_object_covered = 0.1

# aspect_ratio_range: (min_aspect, max_aspect) where aspect = width / height
aspect_ratio_range = (0.75, 1.33)

# area_range: (min_area, max_area) as fractions of original image
area_range = (0.05, 1.0)

# max_attempts: number of attempts to generate valid crop
max_attempts = 100

# scope: optional name scope
scope = None

ARGS = {
    'image_bytes': image_bytes,
    'bbox': bbox,
    'min_object_covered': min_object_covered,
    'aspect_ratio_range': aspect_ratio_range,
    'area_range': area_range,
    'max_attempts': max_attempts,
    'scope': scope
}
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
drop_connect Ran
ran on a synthesized input
cihangxie/SmoothAdversarialTraining/EfficientNet/utils.py
code served (permissive licence) · get_code("d63756c8fcf336f4")
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.compat.v1 as tf
tf.disable_v2_behavior()

# Create a small input tensor with shape [batch_size, height, width, channels]
# batch_size=2, height=4, width=3, channels=5
inputs = tf.constant([[[[1.0, 2.0, 3.0, 4.0, 5.0],
                        [1.1, 2.1, 3.1, 4.1, 5.1],
                        [1.2, 2.2, 3.2, 4.2, 5.2]],
                       [[1.3, 2.3, 3.3, 4.3, 5.3],
                        [1.4, 2.4, 3.4, 4.4, 5.4],
                        [1.5, 2.5, 3.5, 4.5, 5.5]],
                       [[1.6, 2.6, 3.6, 4.6, 5.6],
                        [1.7, 2.7, 3.7, 4.7, 5.7],
                        [1.8, 2.8, 3.8, 4.8, 5.8]],
                       [[1.9, 2.9, 3.9, 4.9, 5.9],
                        [2.0, 3.0, 4.0, 5.0, 6.0],
                        [2.1, 3.1, 4.1, 5.1, 6.1]]],
                      [[[6.0, 7.0, 8.0, 9.0, 10.0],
                        [6.1, 7.1, 8.1, 9.1, 10.1],
                        [6.2, 7.2, 8.2, 9.2, 10.2]],
                       [[6.3, 7.3, 8.3, 9.3, 10.3],
                        [6.4, 7.4, 8.4, 9.4, 10.4],
                        [6.5, 7.5, 8.5, 9.5, 10.5]],
                       [[6.6, 7.6, 8.6, 9.6, 10.6],
                        [6.7, 7.7, 8.7, 9.7, 10.7],
                        [6.8, 7.8, 8.8, 9.8, 10.8]],
                       [[6.9, 7.9, 8.9, 9.9, 10.9],
                        [7.0, 8.0, 9.0, 10.0, 11.0],
                        [7.1, 8.1, 9.1, 10.1, 11.1]]]], dtype=tf.float32)

is_training = True

survival_prob = 0.8

ARGS = {
    "inputs": inputs,
    "is_training": is_training,
    "survival_prob": survival_prob
}
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 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
efficientnet_params Ran
ran on a synthesized input
cihangxie/SmoothAdversarialTraining/EfficientNet/efficientnet_builder.py
code served (permissive licence) · get_code("a7b35049ce7d1511")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# The function takes a model_name string and looks it up in a dictionary
# No complex objects needed - just a string parameter

ARGS = {
    'model_name': 'efficientnet-b0'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
preprocess_for_eval Ran
ran on a synthesized input
cihangxie/SmoothAdversarialTraining/EfficientNet/preprocessing.py
code served (permissive licence) · get_code("6d17319dde175b8a")
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.compat.v1 as tf
import numpy as np

tf.disable_v2_behavior()

# Create a small valid JPEG image bytes for testing
# We'll create a minimal JPEG by encoding a small image
with tf.Session() as sess:
    # Create a small 100x100 RGB image
    dummy_image = tf.constant(np.random.randint(0, 256, (100, 100, 3), dtype=np.uint8))
    encoded_jpeg = tf.image.encode_jpeg(dummy_image)
    image_bytes_value = sess.run(encoded_jpeg)

ARGS = {
    "image_bytes": image_bytes_value,
    "use_bfloat16": False,
    "image_size": 224,
    "resize_method": None,
}
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
preprocess_for_train Ran
ran on a synthesized input
cihangxie/SmoothAdversarialTraining/EfficientNet/preprocessing.py
code served (permissive licence) · get_code("a923706b61b129ea")
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.compat.v1 as tf
import numpy as np

tf.disable_v2_behavior()

# Create a minimal valid JPEG image binary
def create_dummy_jpeg():
    """Create a minimal valid JPEG binary for testing."""
    # This is a minimal 1x1 JPEG image (grayscale)
    jpeg_bytes = b'\xff\xd8\xff\xe0\x00\x10JFIF\x00\x01\x01\x00\x00\x01\x00\x01\x00\x00\xff\xdb\x00C\x00\x08\x06\x06\x07\x06\x05\x08\x07\x07\x07\t\t\x08\n\x0c\x14\r\x0c\x0b\x0b\x0c\x19\x12\x13\x0f\x14\x1d\x1a\x1f\x1e\x1d\x1a\x1c\x1c $.\' ",#\x1c\x1c(7),01444\x1f\'9=82<.342\xff\xc0\x00\x0b\x08\x00\x01\x00\x01\x01\x11\x00\xff\xc4\x00\x1f\x00\x00\x01\x05\x01\x01\x01\x01\x01\x01\x00\x00\x00\x00\x00\x00\x00\x00\x01\x02\x03\x04\x05\x06\x07\x08\t\n\x0b\xff\xda\x00\x08\x01\x01\x00\x00?\x00\xfb\xd1\xff\xd9'
    return jpeg_bytes

# Create a slightly larger valid JPEG (8x8 pixels)
def create_larger_dummy_jpeg():
    """Create a slightly larger valid JPEG for testing."""
    # 8x8 grayscale JPEG
    jpeg_bytes = b'\xff\xd8\xff\xe0\x00\x10JFIF\x00\x01\x01\x00\x00\x01\x00\x01\x00\x00\xff\xdb\x00C\x00\x08\x06\x06\x07\x06\x05\x08\x07\x07\x07\t\t\x08\n\x0c\x14\r\x0c\x0b\x0b\x0c\x19\x12\x13\x0f\x14\x1d\x1a\x1f\x1e\x1d\x1a\x1c\x1c $.\' ",#\x1c\x1c(7),01444\x1f\'9=82<.342\xff\xc0\x00\x0b\x08\x00\x08\x00\x08\x01\x11\x00\xff\xc4\x00\x1f\x00\x00\x01\x05\x01\x01\x01\x01\x01\x01\x00\x00\x00\x00\x00\x00\x00\x00\x01\x02\x03\x04\x05\x06\x07\x08\t\n\x0b\xff\xda\x00\x08\x01\x01\x00\x00?\x00\xf5\x14P\x14P\x14P\x14P\x14\x05\xff\xd9'
    return jpeg_bytes

image_bytes = tf.constant(create_larger_dummy_jpeg())
use_bfloat16 = False
image_size = 224
augment_name = None
randaug_num_layers = None
randaug_magnitude = None
resize_method = None

ARGS = {
    'image_bytes': image_bytes,
    'use_bfloat16': use_bfloat16,
    'image_size': image_size,
    'augment_name': augment_name,
    'randaug_num_layers': randaug_num_layers,
    'randaug_magnitude': randaug_magnitude,
    'resize_method': resize_method,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
absl, autoaugment, 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
round_filters Ran
ran on a synthesized input
cihangxie/SmoothAdversarialTraining/EfficientNet/efficientnet_model.py
code served (permissive licence) · get_code("9f7fd2caf2b48718")
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
from absl import logging

class GlobalParams:
    def __init__(self, width_coefficient, depth_divisor, min_depth):
        self.width_coefficient = width_coefficient
        self.depth_divisor = depth_divisor
        self.min_depth = min_depth

ARGS = {
    'filters': 32,
    'global_params': GlobalParams(
        width_coefficient=1.2,
        depth_divisor=8,
        min_depth=4
    ),
    'skip': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
absl, 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
solarize Ran
ran; our contract draft was wrong, not the code
cihangxie/SmoothAdversarialTraining/EfficientNet/autoaugment.py
code served (permissive licence) · get_code("2f023d4690a70195")
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.compat.v1 as tf
import numpy as np

# Disable v2 behavior for TensorFlow v1 compatibility
tf.disable_v2_behavior()

# Create a small test image as a TensorFlow constant
# Using values in range [0, 255] typical for image data
# Shape: (2, 4, 3) - batch of 2, spatial dims 4x3
image_data = np.array([
    [[10, 20, 30], [40, 50, 60], [70, 80, 90], [100, 110, 120]],
    [[130, 140, 150], [160, 170, 180], [190, 200, 210], [220, 230, 240]]
], dtype=np.uint8)

image = tf.constant(image_data)

ARGS = {
    "image": image,
    "threshold": 128
}
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
swish Ran
ran on a synthesized input
cihangxie/SmoothAdversarialTraining/EfficientNet/efficientnet_builder.py
code served (permissive licence) · get_code("918db160732a16d0")
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 numpy as np
import tensorflow.compat.v1 as tf

# Disable eager execution for TF 1.x compatibility
tf.disable_eager_execution()

# Create a small tensor to use as the features argument
# Shape: (2, 4) - batch size 2, feature dimension 4
features_value = np.array([
    [-1.0, 0.0, 1.0, 2.0],
    [-2.0, -0.5, 0.5, 1.5]
], dtype=np.float32)

features = tf.constant(features_value, dtype=tf.float32)

ARGS = {
    'features': features,
    'use_native': True,
    'use_hard': False,
}
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
conv_kernel_initializer Not yet run
unverified (harvested, no recorded run)
cihangxie/SmoothAdversarialTraining/EfficientNet/efficientnet_model.py
code served (permissive licence) · get_code("a039ef466f295d02")
How it ran

no invocation recorded.

dense_kernel_initializer Not yet run
unverified (harvested, no recorded run)
cihangxie/SmoothAdversarialTraining/EfficientNet/efficientnet_model.py
code served (permissive licence) · get_code("ec6986123a6a4894")
How it ran

no invocation recorded.

Also present in other papers' code

Of 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 7 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 0 the same month, 7 later) and 7 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
conv_kernel_initializer 4 other papers
3 dated earlier, 1 later
1904.02877 (2019-04)
Single-Path NAS: Designing Hardware-Efficient ConvNets in less than 4 Hours
1905.11946 (2019-05)
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
1911.04252 (2019-11)
Self-training with Noisy Student improves ImageNet classification
and 1 more not named here
dense_kernel_initializer 4 other papers
3 dated earlier, 1 later
1904.02877 (2019-04)
Single-Path NAS: Designing Hardware-Efficient ConvNets in less than 4 Hours
1905.11946 (2019-05)
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
1911.04252 (2019-11)
Self-training with Noisy Student improves ImageNet classification
and 1 more not named here
solarize 4 other papers
1 dated earlier, 3 later
1911.04252 (2019-11)
Self-training with Noisy Student improves ImageNet classification
2103.16201 (2021-03)
MT3: Meta Test-Time Training for Self-Supervised Test-Time Adaption
2110.09192 (2021-10)
Learning Optimal Conformal Classifiers
and 1 more not named here
cutout 3 other papers
1 dated earlier, 2 later
1911.04252 (2019-11)
Self-training with Noisy Student improves ImageNet classification
2103.16201 (2021-03)
MT3: Meta Test-Time Training for Self-Supervised Test-Time Adaption
2310.13807 (2023-10)
Learning to (Learn at Test Time)
blend 2 other papers
1 dated earlier, 1 later
1911.04252 (2019-11)
Self-training with Noisy Student improves ImageNet classification
2310.13807 (2023-10)
Learning to (Learn at Test Time)
distorted_bounding_box_crop 2 other papers
1 dated earlier, 1 later
1904.02877 (2019-04)
Single-Path NAS: Designing Hardware-Efficient ConvNets in less than 4 Hours
2008.03703 (2020-08)
What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimation
swish 1 other paper
1 later
2107.02612 (2021-07)
Combining EfficientNet and Vision Transformers for Video Deepfake Detection

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

It is commonly believed that networks cannot be both accurate and robust, that gaining robustness means losing accuracy. It is also generally believed that, unless making networks larger, network architectural elements would otherwise matter little in improving adversarial robustness. Here we present evidence to challenge these common beliefs by a careful study about adversarial training. Our key observation is that the widely-used ReLU activation function significantly weakens adversarial training due to its non-smooth nature. Hence we propose smooth adversarial training (SAT), in which we replace ReLU with its smooth approximations to strengthen adversarial training. The purpose of smooth activation functions in SAT is to allow it to find harder adversarial examples and compute better gradient updates during adversarial training. Compared to standard adversarial training, SAT improves adversarial robustness for "free", i.e., no drop in accuracy and no increase in computational cost. For example, without introducing additional computations, SAT significantly enhances ResNet-50's robustness from 33.0% to 42.3%, while also improving accuracy by 0.9% on ImageNet. SAT also works well with larger networks: it helps EfficientNet-L1 to achieve 82.2% accuracy and 58.6% robustness on ImageNet, outperforming the previous state-of-the-art defense by 9.5% for accuracy and 11.6% for robustness. Models are available at https://github.com/cihangxie/SmoothAdversarialTraining.

For agents

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

get_harvested_code_for_paper("2006.14536")
get_code_for_paper("2006.14536")
have("2006.14536")

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

curl https://syntology.ai/api/ran/2006.14536.json

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

[![Syntology run record](https://syntology.ai/api/ran/2006.14536.svg)](https://syntology.ai/paper/2006.14536)

Connect an agent — have() is free.