SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1808.00157 · 2018

Instance-level Human Parsing via Part Grouping Network

arXiv · PDF · Open in the Atlas

Code that ran

6 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 4 have no contract verdict; 2 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/1808.00157.json · badge: /api/ran/1808.00157.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
Engineering-Course/CIHP_PGN canonical (classifier label)
classifier basis: census
6 ran · 8 no recorded run
FunctionStatusWhere it lives
average_gradients Ran
ran; our contract draft was wrong, not the code
Engineering-Course/CIHP_PGN/train_pgn.py
code served (permissive licence) · get_code("c598804162457140")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list. 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 sample gradients and variables for multiple towers
# The function expects: List of lists of (gradient, variable) tuples
# Outer list: over individual gradients (shared variables)
# Inner list: over towers

# Create simple variables (using tf.Variable as stand-ins)
var1 = tf.Variable(np.random.randn(4, 3), dtype=tf.float32)
var2 = tf.Variable(np.random.randn(2, 5), dtype=tf.float32)

# Create gradients for each variable from multiple towers (e.g., 2 towers)
# Tower 1 gradients
tower1_grad1 = tf.constant(np.random.randn(4, 3), dtype=tf.float32)
tower1_grad2 = tf.constant(np.random.randn(2, 5), dtype=tf.float32)

# Tower 2 gradients
tower2_grad1 = tf.constant(np.random.randn(4, 3), dtype=tf.float32)
tower2_grad2 = tf.constant(np.random.randn(2, 5), dtype=tf.float32)

# Construct tower_grads: list of lists of (gradient, variable) tuples
# Each element in outer list is for one tower
tower_grads = [
    [(tower1_grad1, var1), (tower1_grad2, var2)],
    [(tower2_grad1, var1), (tower2_grad2, var2)]
]

ARGS = {
    'tower_grads': tower_grads
}
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 list — a list 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_filter_output_shape Ran
ran on a synthesized input
Engineering-Course/CIHP_PGN/kaffe/shapes.py
code served (permissive licence) · get_code("f0cb824658baf378")
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 int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import math

class ConvParams:
    def __init__(self, pad_h, pad_w, kernel_h, kernel_w, stride_h, stride_w):
        self.pad_h = pad_h
        self.pad_w = pad_w
        self.kernel_h = kernel_h
        self.kernel_w = kernel_w
        self.stride_h = stride_h
        self.stride_w = stride_w

ARGS = {
    "i_h": 28,
    "i_w": 32,
    "params": ConvParams(
        pad_h=1,
        pad_w=1,
        kernel_h=3,
        kernel_w=3,
        stride_h=1,
        stride_w=1
    ),
    "round_func": math.floor
}
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 tuple, ndim 1, dtype family int — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_strided_kernel_output_shape Ran
ran on a synthesized input
Engineering-Course/CIHP_PGN/kaffe/shapes.py
code served (permissive licence) · get_code("619139704cd246c3")
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 TensorShape. 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 collections import namedtuple
import math

TensorShape = namedtuple('TensorShape', ['batch_size', 'channels', 'height', 'width'])

class KernelParameters:
    def __init__(self):
        self.pad_h = 1
        self.pad_w = 1
        self.kernel_h = 3
        self.kernel_w = 3
        self.stride_h = 1
        self.stride_w = 1

class LayerParameters:
    def __init__(self):
        self.num_output = 16

class Layer:
    def __init__(self):
        self.kernel_parameters = KernelParameters()
        self.parameters = LayerParameters()

class Node:
    def __init__(self):
        self.layer = Layer()
        self._parent = None
    
    def get_only_parent(self):
        return self._parent

class ParentNode:
    def __init__(self):
        self.output_shape = TensorShape(batch_size=2, channels=4, height=8, width=8)

# Create the node structure
parent_node = ParentNode()
node = Node()
node._parent = parent_node

ARGS = {
    'node': node,
    'round_func': math.floor
}
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 TensorShape — a TensorShape output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a TensorShape output the recorded ndim 1 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
layer Ran
ran; our contract draft was wrong, not the code
Engineering-Course/CIHP_PGN/kaffe/tensorflow/network.py
code served (permissive licence) · get_code("fab32b621c712604")
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 function. 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)

class MockNetworkBuilder:
    """Mock class that simulates a network builder with layer management."""
    def __init__(self):
        self.terminals = []
        self.layers = {}
        self._name_counter = {}
    
    def get_unique_name(self, name):
        """Generate unique layer names."""
        if name not in self._name_counter:
            self._name_counter[name] = 0
        else:
            self._name_counter[name] += 1
        return f"{name}_{self._name_counter[name]}"
    
    def feed(self, layer_output):
        """Update terminals with new layer output."""
        self.terminals = [layer_output]

class MockOp:
    """Mock operation function that processes layer input."""
    def __call__(self, builder, layer_input, name=None):
        # Simulate a simple operation that returns a tensor
        if isinstance(layer_input, list):
            return torch.cat(layer_input, dim=1)
        else:
            return layer_input * 2

# Create a mock builder instance
mock_builder = MockNetworkBuilder()

# Initialize terminals with a sample tensor (batch_size=2, features=4)
sample_tensor = torch.randn(2, 4)
mock_builder.terminals = [sample_tensor]

# Create a mock operation
mock_op = MockOp()

# Define ARGS
ARGS = {
    'op': mock_op
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
max_pool Ran
ran on a synthesized input
Engineering-Course/CIHP_PGN/utils/ops.py
code served (permissive licence) · get_code("bfae8c1c80fbeb1c")
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 4, dtype family float, shape (2, 4, 3, 2) 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 a small input tensor for max pooling
# TensorFlow max_pool expects 4D tensor: [batch, height, width, channels]
batch_size = 2
height = 4
width = 3
channels = 2
input_data = np.random.randn(batch_size, height, width, channels).astype(np.float32)
input_tensor = tf.constant(input_data)

# Define kernel size
kernel = 2

# Define stride
stride = 1

# Define operation name
name = "max_pool_op"

ARGS = {
    "input_": input_tensor,
    "kernel": kernel,
    "stride": stride,
    "name": name
}
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 4, dtype family float, shape (2, 4, 3, 2) — shape (2, 4, 3, 2) 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
shape_identity Ran
ran on a synthesized input
Engineering-Course/CIHP_PGN/kaffe/shapes.py
code served (permissive licence) · get_code("f9387ac8956d5501")
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 int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

class MockNode:
    def __init__(self, output_shape, parents=None):
        self.output_shape = output_shape
        self.parents = parents if parents is not None else []

# Create parent node with a specific output shape
parent_node = MockNode(output_shape=(2, 4, 3))

# Create the node to be passed to shape_identity
node = MockNode(output_shape=(2, 5, 6), parents=[parent_node])

ARGS = {
    "node": node
}
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 tuple, ndim 1, dtype family int — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
conv2d Not yet run
unverified (harvested, no recorded run)
Engineering-Course/CIHP_PGN/utils/ops.py
code served (permissive licence) · get_code("285297765b0a1be2")
How it ran

no invocation recorded.

image_mirroring Not yet run
unverified (harvested, no recorded run)
Engineering-Course/CIHP_PGN/utils/image_reader_pgn.py
code served (permissive licence) · get_code("2496574c6a643967")
How it ran

no invocation recorded.

image_mirroring Not yet run
unverified (harvested, no recorded run)
Engineering-Course/CIHP_PGN/utils/image_reade_inf.py
code served (permissive licence) · get_code("b73f410e9cae7cf2")
How it ran

no invocation recorded.

image_mirroring Not yet run
unverified (harvested, no recorded run)
Engineering-Course/CIHP_PGN/utils/image_reader.py
code served (permissive licence) · get_code("b5ac15f02ef566e4")
How it ran

no invocation recorded.

image_scaling Not yet run
unverified (harvested, no recorded run)
Engineering-Course/CIHP_PGN/utils/image_reader_pgn.py
code served (permissive licence) · get_code("05a080c8a7d0297f")
How it ran

no invocation recorded.

image_scaling Not yet run
unverified (harvested, no recorded run)
Engineering-Course/CIHP_PGN/utils/image_reade_inf.py
code served (permissive licence) · get_code("846c829b29a2563c")
How it ran

no invocation recorded.

linear Not yet run
unverified (harvested, no recorded run)
Engineering-Course/CIHP_PGN/utils/ops.py
code served (permissive licence) · get_code("b2a7ddf5cb874b47")
How it ran

no invocation recorded.

random_resize_img_labels Not yet run
unverified (harvested, no recorded run)
Engineering-Course/CIHP_PGN/utils/image_reader_pgn.py
code served (permissive licence) · get_code("b874fe7b2d022945")
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, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 2 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
layer 5 other papers
2 dated earlier, 3 later
1606.00373 (2016-06)
Deeper Depth Prediction with Fully Convolutional Residual Networks
1611.08050 (2016-11)
Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields
1903.08527 (2019-03)
Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set
and 2 more not named here
average_gradients 3 other papers
2 dated earlier, 1 later
1511.06422 (2015-11)
All you need is a good init
1710.09829 (2017-10)
Dynamic Routing Between Capsules
1809.01465 (2018-09)
Deep Bilevel Learning

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

Instance-level human parsing towards real-world human analysis scenarios is still under-explored due to the absence of sufficient data resources and technical difficulty in parsing multiple instances in a single pass. Several related works all follow the "parsing-by-detection" pipeline that heavily relies on separately trained detection models to localize instances and then performs human parsing for each instance sequentially. Nonetheless, two discrepant optimization targets of detection and parsing lead to suboptimal representation learning and error accumulation for final results. In this work, we make the first attempt to explore a detection-free Part Grouping Network (PGN) for efficiently parsing multiple people in an image in a single pass. Our PGN reformulates instance-level human parsing as two twinned sub-tasks that can be jointly learned and mutually refined via a unified network: 1) semantic part segmentation for assigning each pixel as a human part (e.g., face, arms); 2) instance-aware edge detection to group semantic parts into distinct person instances. Thus the shared intermediate representation would be endowed with capabilities in both characterizing fine-grained parts and inferring instance belongings of each part. Finally, a simple instance partition process is employed to get final results during inference. We conducted experiments on PASCAL-Person-Part dataset and our PGN outperforms all state-of-the-art methods. Furthermore, we show its superiority on a newly collected multi-person parsing dataset (CIHP) including 38,280 diverse images, which is the largest dataset so far and can facilitate more advanced human analysis. The CIHP benchmark and our source code are available at http://sysu-hcp.net/lip/.

For agents

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

get_harvested_code_for_paper("1808.00157")
get_code_for_paper("1808.00157")
have("1808.00157")

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

curl https://syntology.ai/api/ran/1808.00157.json

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

[![Syntology run record](https://syntology.ai/api/ran/1808.00157.svg)](https://syntology.ai/paper/1808.00157)

Connect an agent — have() is free.