SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2104.10956 · NeurIPS · 2021

FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection

Tai Wang, Xinge Zhu, Jiangmiao Pang, Dahua Lin

arXiv · PDF · Open in the Atlas

Code that ran

20 of 22 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; 6 honoured the contract we drafted, 1 violated it and 3 have no contract verdict; 10 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/2104.10956.json · badge: /api/ran/2104.10956.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
konyul/mmdet3d community (classifier label)
classifier basis not recorded on the link
11 ran · 1 no recorded run
AllenPeng0209/deeproute_competition community (classifier label)
classifier basis not recorded on the link
6 ran · 1 no recorded run
Discover304/MMDetection3D-Eloss community (classifier label)
classifier basis not recorded on the link
2 ran · 0 no recorded run
jhkim-spa/FVNet_v2 community (classifier label)
classifier basis not recorded on the link
1 ran · 0 no recorded run
FunctionStatusWhere it lives
average_precision Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
konyul/mmdet3d/mmdet3d/core/evaluation/indoor_eval.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from Xianpeng919/MonoCon, is pointer only (licence: NONE) · get_code("8d35a41368d8dd47")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from Xianpeng919/MonoCon, 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.

bbox3d2result Ran
ran; our contract draft was wrong, not the code
konyul/mmdet3d/mmdet3d/core/bbox/transforms.py
code served (permissive licence) · get_code("049f10575d6acf59")
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 torch

torch.manual_seed(0)

# Create small tensors for bounding boxes, scores, labels, and attributes
bboxes = torch.randn(2, 5)  # 2 bounding boxes with 5 coordinates each
scores = torch.randn(2)     # 2 scores
labels = torch.randint(0, 10, (2,))  # 2 labels
attrs = torch.randint(0, 5, (2,))    # 2 attributes

ARGS = {
    'bboxes': bboxes,
    'scores': scores,
    'labels': labels,
    'attrs': attrs
}
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 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
bbox3d2roi Ran
ran, honoured the contract we drafted
konyul/mmdet3d/mmdet3d/core/bbox/transforms.py
code served (permissive licence) · get_code("071c297bbb04127e")
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 (3, 5) 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)

# bbox_list is a list of tensors, where each tensor contains bounding boxes for one image
# Each bbox tensor has shape (num_boxes, num_coords)
# The function will prepend batch indices, so we need valid bbox tensors

bbox_list = [
    torch.tensor([[1.0, 2.0, 3.0, 4.0], [5.0, 6.0, 7.0, 8.0]], dtype=torch.float32),  # 2 boxes, 4 coords
    torch.tensor([[9.0, 10.0, 11.0, 12.0]], dtype=torch.float32),  # 1 box, 4 coords
]

ARGS = {
    "bbox_list": bbox_list
}
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 (3, 5) — shape (3, 5) 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
bbox3d_mapping_back Ran
ran; our contract draft was wrong, not the code
konyul/mmdet3d/mmdet3d/core/bbox/transforms.py
code served (permissive licence) · get_code("cd7847cc58eb29bd")
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 BaseInstance3DBoxes. 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 numpy as np

torch.manual_seed(0)

class BaseInstance3DBoxes:
    """Stand-in for BaseInstance3DBoxes that implements required methods."""
    
    def __init__(self, tensor):
        self.tensor = tensor.clone()
    
    def clone(self):
        return BaseInstance3DBoxes(self.tensor.clone())
    
    def flip(self, direction):
        """Flip the bboxes in the specified direction."""
        if direction == 'horizontal':
            self.tensor[:, 0] = -self.tensor[:, 0]
        elif direction == 'vertical':
            self.tensor[:, 1] = -self.tensor[:, 1]
    
    def scale(self, scale_factor):
        """Scale the bboxes by the given factor."""
        self.tensor = self.tensor * scale_factor

# Create sample 3D bboxes with shape (2, 7) - typical for 3D boxes
# Format: [x, y, z, length, width, height, rotation]
bboxes_data = torch.tensor([
    [1.0, 2.0, 3.0, 0.5, 0.6, 0.7, 0.1],
    [4.0, 5.0, 6.0, 0.8, 0.9, 1.0, 0.2]
], dtype=torch.float32)

bboxes = BaseInstance3DBoxes(bboxes_data)

ARGS = {
    'bboxes': bboxes,
    'scale_factor': 2.0,
    'flip_horizontal': True,
    'flip_vertical': False
}
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 BaseInstance3DBoxes — a BaseInstance3DBoxes output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a BaseInstance3DBoxes 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
box_camera_to_lidar Ran
ran, honoured the contract we drafted
konyul/mmdet3d/mmdet3d/core/bbox/box_np_ops.py
code served (permissive licence) · get_code("96c8084488bd023b")
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 2, dtype family float, shape (2, 7) 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 numpy as np

np.random.seed(0)

# Create small sample data for box_camera_to_lidar function
# data shape should be [N, 7] where N is number of boxes
# Each box has: [x, y, z, l, h, w, r] (3 position + 3 dimensions + 1 rotation)
data = np.array([
    [5.0, 10.0, 2.0, 3.5, 1.6, 1.8, 0.5],
    [8.0, 12.0, 1.5, 3.2, 1.5, 1.7, 1.2]
], dtype=np.float32)

# r_rect: [4, 4] matrix to project from CAM2 to CAM0
# This is typically the camera rectification matrix
r_rect = np.array([
    [0.9999, -0.0050, 0.0095, 0.0],
    [0.0050, 0.9999, -0.0010, 0.0],
    [-0.0095, 0.0010, 0.9999, 0.0],
    [0.0, 0.0, 0.0, 1.0]
], dtype=np.float32)

# velo2cam: [4, 4] matrix to project from lidar/velodyne to camera coordinate
# This is the extrinsic calibration matrix
velo2cam = np.array([
    [0.0125, -0.9992, 0.0359, -0.0430],
    [-0.2357, -0.0381, -0.9714, -0.2330],
    [0.9719, 0.0106, -0.2360, -0.0144],
    [0.0, 0.0, 0.0, 1.0]
], dtype=np.float32)

ARGS = {
    'data': data,
    'r_rect': r_rect,
    'velo2cam': velo2cam
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (2, 7) — shape (2, 7) 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
calculate_entropy Ran
ran on a synthesized input
Discover304/MMDetection3D-Eloss/mmdet3d/models/losses/eloss.py
code served (permissive licence) · get_code("356e77e178d28771")
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 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create a small feature tensor
# Shape: [batch, channels, height, width]
# The function expects: feats.size() -> (batch, C, H, W)
# Then it reshapes to (-1, C, H*W)
feats = torch.randn(2, 4, 3, 5)

# k parameter (used in the function, though not in calculate_entropy signature shown)
k = 1

ARGS = {
    "feats": feats,
    "k": k,
}
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 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
camera_to_lidar Ran
ran, honoured the contract we drafted
konyul/mmdet3d/mmdet3d/core/bbox/box_np_ops.py
code served (permissive licence) · get_code("9e22984820c39868")
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 2, dtype family float, shape (2, 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 numpy as np

# Create small test data for camera_to_lidar function
# points: shape [N, 3] - points in camera coordinate
np.random.seed(0)
points = np.random.randn(2, 3).astype(np.float32)

# r_rect: shape [4, 4] - matrix to project points from specific camera coord to CAM0
# Create a valid 4x4 transformation matrix
r_rect = np.eye(4, dtype=np.float32)
r_rect[0, 1] = 0.1
r_rect[1, 2] = 0.05

# velo2cam: shape [4, 4] - matrix to project points from camera coord to lidar coord
# Create a valid 4x4 transformation matrix
velo2cam = np.eye(4, dtype=np.float32)
velo2cam[0, 0] = 0.9
velo2cam[1, 1] = 0.95
velo2cam[2, 2] = 1.0

ARGS = {
    "points": points,
    "r_rect": r_rect,
    "velo2cam": velo2cam,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (2, 3) — shape (2, 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
clean_data Ran
ran on a synthesized input
AllenPeng0209/deeproute_competition/mmdet3d/core/evaluation/deeproute_utils/deeproute_eval.py
code served (permissive licence) · get_code("853d5d97b4442543")
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 numpy as np
from scipy.spatial import distance

torch_seed = np.random.seed(42)

# Construct gt_anno dictionary with required keys
gt_anno = {
    'name': ['car', 'van', 'DontCare'],
    'bbox': np.array([[0, 0, 10, 10], [5, 5, 15, 15], [20, 20, 30, 30]], dtype=np.float32),
    'location': np.array([[10, 15, 0], [25, 35, 0], [50, 60, 0]], dtype=np.float32)
}

# Construct dt_anno dictionary with required keys
dt_anno = {
    'name': ['car', 'truck', 'van'],
    'bbox': np.array([[1, 1, 11, 11], [30, 30, 40, 40], [6, 6, 16, 16]], dtype=np.float32),
    'location': np.array([[12, 18, 0], [60, 70, 0], [28, 38, 0]], dtype=np.float32)
}

# current_class: index into CLASS_NAMES (0 = 'car')
current_class = 0

# difficulty: one of 0, 1, or 2 for distance bands
difficulty = 0

# difficulty_metric: optional, can be None
difficulty_metric = None

ARGS = {
    'gt_anno': gt_anno,
    'dt_anno': dt_anno,
    'current_class': current_class,
    'difficulty': difficulty,
    'difficulty_metric': difficulty_metric
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — 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
corners_nd Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
konyul/mmdet3d/mmdet3d/core/bbox/box_np_ops.py
code served (permissive licence) · get_code("5b1dacd1f125c08f")
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 float, shape (2, 8, 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 numpy as np

# Create valid arguments for corners_nd function
dims = np.array([[2.0, 3.0, 1.5], [4.0, 2.5, 3.0]], dtype=np.float32)

origin = 0.5

ARGS = {
    "dims": dims,
    "origin": origin,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — 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 float, shape (2, 8, 3) — shape (2, 8, 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
div_up Ran
ran, honoured the contract we drafted
AllenPeng0209/deeproute_competition/mmdet3d/core/evaluation/deeproute_utils/rotate_iou.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from datongjie/bevspread, is pointer only (licence: NONE) · get_code("20fbfa2279e1ce4b")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from datongjie/bevspread, 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.

eval_det_cls Ran
ran; our contract draft was wrong, not the code
konyul/mmdet3d/mmdet3d/core/evaluation/indoor_eval.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from Xianpeng919/MonoCon, is pointer only (licence: NONE) · get_code("2283234eb1863906")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from Xianpeng919/MonoCon, 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.

fast_hist Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
konyul/mmdet3d/mmdet3d/core/evaluation/seg_eval.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from Xianpeng919/MonoCon, is pointer only (licence: NONE) · get_code("7f5f5b45cabc7d55")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from Xianpeng919/MonoCon, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_acc Ran
ran, honoured the contract we drafted
konyul/mmdet3d/mmdet3d/core/evaluation/seg_eval.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from Xianpeng919/MonoCon, is pointer only (licence: NONE) · get_code("fcd32f0316ac7cac")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from Xianpeng919/MonoCon, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_final_epoch Ran
ran, honoured the contract we drafted
jhkim-spa/FVNet_v2/.dev_scripts/gather_models.py
code served (permissive licence) · get_code("6434c4b76548f533")
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

ARGS = {
    'config': 'resnet50_grid_rcnn_2x_coco'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type int, ndim 0, dtype family int, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_model_dataset Ran
ran; our contract draft was wrong, not the code
AllenPeng0209/deeproute_competition/.dev_scripts/gather_models.py
code served (permissive licence) · get_code("da059252c88ecf40")
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 str. 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 os
import tempfile

torch.manual_seed(0)

# Create a temporary directory for testing
temp_dir = tempfile.mkdtemp()

# Create test log JSON paths with dataset keywords
log_json_path_coco = os.path.join(temp_dir, "results_coco_experiment.json")
log_json_path_nus = os.path.join(temp_dir, "nus_detection_log.json")
log_json_path_kitti = os.path.join(temp_dir, "kitti-3d-3class_results.json")
log_json_path_lyft = os.path.join(temp_dir, "lyft_benchmark.json")
log_json_path_scannet_seg = os.path.join(temp_dir, "scannet_seg_output.json")

# Test with a simple coco path
test_log_json_path = os.path.join(temp_dir, "coco_results.json")

ARGS = {
    "log_json_path": test_log_json_path
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
get_thresholds Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
AllenPeng0209/deeproute_competition/mmdet3d/core/evaluation/deeproute_utils/deeproute_eval.py
code served (permissive licence) · get_code("89ab5b12e60b6dc2")
How it ran

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

import numba
import numpy as np

# Create small test arrays for scores and num_gt
scores = np.array([0.9, 0.7, 0.5, 0.3, 0.1, 0.8, 0.6, 0.4, 0.2], dtype=np.float64)
num_gt = 10
num_sample_pts = 41

ARGS = {
    "scores": scores,
    "num_gt": num_gt,
    "num_sample_pts": num_sample_pts
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numba, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
image_box_overlap Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
AllenPeng0209/deeproute_competition/mmdet3d/core/evaluation/deeproute_utils/deeproute_eval.py
code served (permissive licence) · get_code("7131430b63714f53")
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 2, dtype family float, shape (2, 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 numpy as np
import numba

# Construct boxes: N=2 boxes, each with format [x1, y1, x2, y2]
boxes = np.array([
    [0.0, 0.0, 10.0, 10.0],
    [5.0, 5.0, 15.0, 15.0]
], dtype=np.float32)

# Construct query_boxes: K=3 query boxes
query_boxes = np.array([
    [2.0, 2.0, 8.0, 8.0],
    [6.0, 6.0, 12.0, 12.0],
    [20.0, 20.0, 25.0, 25.0]
], dtype=np.float32)

# criterion parameter: -1 for IoU (union), 0 for area of box, 1 for area of query_box
criterion = -1

ARGS = {
    "boxes": boxes,
    "query_boxes": query_boxes,
    "criterion": criterion
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numba, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (2, 3) — shape (2, 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
pairwise_euclidean_distance Ran
ran on a synthesized input
Discover304/MMDetection3D-Eloss/mmdet3d/models/losses/eloss.py
code served (permissive licence) · get_code("3b15102fec2dd1c2")
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, 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

torch.manual_seed(0)

# Create two small tensors with distinct dimensions
# x: [m, d] where m=2, d=4
x = torch.randn(2, 4)

# y: [n, d] where n=3, d=4
y = torch.randn(3, 4)

ARGS = {
    "x": x,
    "y": y,
}
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, 3) — shape (2, 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
per_class_iou Ran
ran, violated the contract we drafted
konyul/mmdet3d/mmdet3d/core/evaluation/seg_eval.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from Xianpeng919/MonoCon, is pointer only (licence: NONE) · get_code("4018d47e1ea5a2ce")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from Xianpeng919/MonoCon, 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.

process_checkpoint Ran
ran; our contract draft was wrong, not the code
AllenPeng0209/deeproute_competition/.dev_scripts/gather_models.py
code served (permissive licence) · get_code("e76a491553cf9fcf")
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 str. 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 tempfile
import os

torch.manual_seed(0)

# Create a temporary directory for checkpoint files
temp_dir = tempfile.mkdtemp()

# Create a minimal checkpoint dict with a model state and optimizer
checkpoint = {
    'model': {
        'layer1.weight': torch.randn(4, 3),
        'layer1.bias': torch.randn(4),
    },
    'optimizer': {
        'state': {},
        'param_groups': [],
    },
    'epoch': 1,
}

# Save the checkpoint to a temporary file
in_file = os.path.join(temp_dir, 'checkpoint.pth')
torch.save(checkpoint, in_file)

# Define output file path
out_file = os.path.join(temp_dir, 'checkpoint_processed.pth')

ARGS = {
    'in_file': in_file,
    'out_file': out_file,
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
eval_map_recall Not yet run
unverified (harvested, no recorded run)
konyul/mmdet3d/mmdet3d/core/evaluation/indoor_eval.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from Xianpeng919/MonoCon, is pointer only (licence: NONE) · get_code("3e68c67f05177852")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from Xianpeng919/MonoCon, 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. No invocation recorded.

get_final_epoch Not yet run
unverified (harvested, no recorded run)
AllenPeng0209/deeproute_competition/.dev_scripts/gather_models.py
code served (permissive licence) · get_code("90f6ae7209cde36f")
How it ran

no invocation recorded.

Also present in other papers' code

Of 22 samples lifted from this paper's linked repositories, 22 carry a function identity and 0 do not. Of the 21 distinct functions with an identity, 18 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 3 the same month, 18 later) and 3 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
process_checkpoint 45 other papers
10 dated earlier, 1 the same month, 33 later, 1 undated
1904.11490 (2019-04)
RepPoints: Point Set Representation for Object Detection
1906.07155 (2019-06)
MMDetection: Open MMLab Detection Toolbox and Benchmark
1908.05612 (2019-08)
R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object
and 42 more not named here
get_final_epoch 35 other papers
7 dated earlier, 1 the same month, 26 later, 1 undated
1904.11490 (2019-04)
RepPoints: Point Set Representation for Object Detection
1906.07155 (2019-06)
MMDetection: Open MMLab Detection Toolbox and Benchmark
1908.05612 (2019-08)
R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object
and 32 more not named here
get_model_dataset 26 other papers
1 the same month, 24 later, 1 undated
2104.06114 (2021-04)
Back-tracing Representative Points for Voting-based 3D Object Detection in Point Clouds
2112.04680 (2021-12)
SimIPU: Simple 2D Image and 3D Point Cloud Unsupervised Pre-Training for Spatial-Aware Visual Representations
2203.07697 (2022-03)
Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimation
and 23 more not named here
box_camera_to_lidar 9 other papers
9 later
136990210 (2022 (year only))
FH-Net: A Fast Hierarchical Network for Scene Flow Estimation on Real-world Point Clouds
2203.10642 (2022-03)
FUTR3D: A Unified Sensor Fusion Framework for 3D Detection
2205.13542 (2022-05)
BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation
and 6 more not named here
camera_to_lidar 9 other papers
9 later
136990210 (2022 (year only))
FH-Net: A Fast Hierarchical Network for Scene Flow Estimation on Real-world Point Clouds
2203.10642 (2022-03)
FUTR3D: A Unified Sensor Fusion Framework for 3D Detection
2205.13542 (2022-05)
BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation
and 6 more not named here
div_up 9 other papers
5 dated earlier, 4 later
1908.09492 (2019-08)
Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection
1911.10194 (2019-11)
Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation
1911.11288 (2019-11)
Autolabeling 3D Objects with Differentiable Rendering of SDF Shape Priors
and 6 more not named here
corners_nd 8 other papers
8 later
2203.10642 (2022-03)
FUTR3D: A Unified Sensor Fusion Framework for 3D Detection
2205.13542 (2022-05)
BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation
2210.05593 (2022-10)
Prototypical VoteNet for Few-Shot 3D Point Cloud Object Detection
and 5 more not named here
average_precision 5 other papers
5 later
2112.04628 (2021-12)
Learning Auxiliary Monocular Contexts Helps Monocular 3D Object Detection
2210.05593 (2022-10)
Prototypical VoteNet for Few-Shot 3D Point Cloud Object Detection
2311.01682 (2023-11)
Flow-Based Feature Fusion for Vehicle-Infrastructure Cooperative 3D Object Detection
and 2 more not named here
eval_det_cls 5 other papers
5 later
2112.04628 (2021-12)
Learning Auxiliary Monocular Contexts Helps Monocular 3D Object Detection
2210.05593 (2022-10)
Prototypical VoteNet for Few-Shot 3D Point Cloud Object Detection
2311.01682 (2023-11)
Flow-Based Feature Fusion for Vehicle-Infrastructure Cooperative 3D Object Detection
and 2 more not named here
eval_map_recall 5 other papers
5 later
2112.04628 (2021-12)
Learning Auxiliary Monocular Contexts Helps Monocular 3D Object Detection
2210.05593 (2022-10)
Prototypical VoteNet for Few-Shot 3D Point Cloud Object Detection
2311.01682 (2023-11)
Flow-Based Feature Fusion for Vehicle-Infrastructure Cooperative 3D Object Detection
and 2 more not named here
bbox3d2result 4 other papers
4 later
2210.05593 (2022-10)
Prototypical VoteNet for Few-Shot 3D Point Cloud Object Detection
2311.01682 (2023-11)
Flow-Based Feature Fusion for Vehicle-Infrastructure Cooperative 3D Object Detection
2411.12452 (2024-11)
GaussianPretrain: A Simple Unified 3D Gaussian Representation for Visual Pre-training in Autonomous Driving
and 1 more not named here
bbox3d2roi 4 other papers
4 later
2210.05593 (2022-10)
Prototypical VoteNet for Few-Shot 3D Point Cloud Object Detection
2311.01682 (2023-11)
Flow-Based Feature Fusion for Vehicle-Infrastructure Cooperative 3D Object Detection
2411.12452 (2024-11)
GaussianPretrain: A Simple Unified 3D Gaussian Representation for Visual Pre-training in Autonomous Driving
and 1 more not named here
bbox3d_mapping_back 4 other papers
4 later
2210.05593 (2022-10)
Prototypical VoteNet for Few-Shot 3D Point Cloud Object Detection
2311.01682 (2023-11)
Flow-Based Feature Fusion for Vehicle-Infrastructure Cooperative 3D Object Detection
2411.12452 (2024-11)
GaussianPretrain: A Simple Unified 3D Gaussian Representation for Visual Pre-training in Autonomous Driving
and 1 more not named here
fast_hist 2 other papers
2 later
2112.04628 (2021-12)
Learning Auxiliary Monocular Contexts Helps Monocular 3D Object Detection
2507.00603 (2025-07)
World4Drive: End-to-End Autonomous Driving via Intention-aware Physical Latent World Model
get_acc 2 other papers
2 later
2112.04628 (2021-12)
Learning Auxiliary Monocular Contexts Helps Monocular 3D Object Detection
2507.00603 (2025-07)
World4Drive: End-to-End Autonomous Driving via Intention-aware Physical Latent World Model
get_thresholds 2 other papers
1 dated earlier, 1 later
2103.15326 (2021-03)
Fooling LiDAR Perception via Adversarial Trajectory Perturbation
2310.07602 (2023-10)
Dual Radar: A Multi-modal Dataset with Dual 4D Radar for Autonomous Driving
per_class_iou 2 other papers
2 later
2112.04628 (2021-12)
Learning Auxiliary Monocular Contexts Helps Monocular 3D Object Detection
2507.00603 (2025-07)
World4Drive: End-to-End Autonomous Driving via Intention-aware Physical Latent World Model
image_box_overlap 1 other paper
1 later
2310.07602 (2023-10)
Dual Radar: A Multi-modal Dataset with Dual 4D Radar for Autonomous Driving

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

Illustration of 2D detection and monocular 3D object detection. Given an input RGB image, a 2D anchor-free detector needs to predict the distance from a foreground point to four box sides. In contrast, a monocular 3D anchor-free detector needs to predict a transformed 3D-center, 3D size, and orientation of the object.

For agents

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

get_harvested_code_for_paper("2104.10956")
get_code_for_paper("2104.10956")
have("2104.10956")

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

curl https://syntology.ai/api/ran/2104.10956.json

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

[![Syntology run record](https://syntology.ai/api/ran/2104.10956.svg)](https://syntology.ai/paper/2104.10956)

Connect an agent — have() is free.