我正在尝试根据 GitHub 存储库中显示的内容运行预训练的神经网络进行对象检测：Deformable-DETR，在 Ubuntu 20.04.6 的 Python（版本 3.10.9）终端中使用此命令长期支持：
./configs/r50_deformable_detr_plus_iterative_bbox_refinement_plus_plus_two_stage.sh --resume ./pre-trained models/r50_deformable_detr_plus_iterative_bbox_refinement_plus_plus_two_stage-checkpoint.pth --eval
我遵循存储库中显示的相同结构：
<path to config file> --resume <path to pre-trained model> --eval
我下载了预训练的神经网络：Deformable DET ++ two-stage Deformable DETR，以及来自COCO数据集的验证集（在数据文件夹中），并遵循结构，如图所示GitHub 存储库：
code_root/
└── data/
└── coco/
├── train2017/
├── val2017/
└── annotations/
├── instances_train2017.json
└── instances_val2017.json
但是，当我在终端中运行命令从预训练的神经网络中进行预测后，我收到以下错误消息：
./configs/r50_deformable_detr_plus_iterative_bbox_refinement_plus_plus_two_stage.sh --resume ./pre-trained models/r50_deformable_detr_plus_iterative_bbox_refinement_plus_plus_two_stage-checkpoint.pth --eval
+ EXP_DIR=exps/r50_deformable_detr_plus_iterative_bbox_refinement_plus_plus_two_stage
+ PY_ARGS='--resume ./pre-trained models/r50_deformable_detr_plus_iterative_bbox_refinement_plus_plus_two_stage-checkpoint.pth --eval'
+ python -u main.py --output_dir exps/r50_deformable_detr_plus_iterative_bbox_refinement_plus_plus_two_stage --with_box_refine --two_stage --resume ./pre-trained models/r50_deformable_detr_plus_iterative_bbox_refinement_plus_plus_two_stage-checkpoint.pth --eval
/home/tarsier/anaconda3/lib/python3.10/site-packages/torchvision/io/image.py:13: UserWarning: Failed to load image Python extension: /home/tarsier/anaconda3/lib/python3.10/site-packages/torchvision/image.so: undefined symbol: _ZN5torch3jit17parseSchemaOrNameERKNSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEE
warn(f"Failed to load image Python extension: {e}")
Traceback (most recent call last):
File "/home/tarsier/Documents/Walaris/Tasks/Task 2: Ground-based Object Detection/Code/Deformable-DETR/main.py", line 21, in <module>
import datasets
File "/home/tarsier/Documents/Walaris/Tasks/Task 2: Ground-based Object Detection/Code/Deformable-DETR/datasets/__init__.py", line 13, in <module>
from .coco import build as build_coco
File "/home/tarsier/Documents/Walaris/Tasks/Task 2: Ground-based Object Detection/Code/Deformable-DETR/datasets/coco.py", line 22, in <module>
from util.misc import get_local_rank, get_local_size
File "/home/tarsier/Documents/Walaris/Tasks/Task 2: Ground-based Object Detection/Code/Deformable-DETR/util/misc.py", line 32, in <module>
from torchvision.ops.misc import _NewEmptyTensorOp
ImportError: cannot import name '_NewEmptyTensorOp' from 'torchvision.ops.misc' (/home/tarsier/anaconda3/lib/python3.10/site-packages/torchvision/ops/misc.py)
错误信息似乎提示代码中存在导入错误。具体来说，似乎模块 torchvision.ops.misc 无法导入 _NewEmptyTensorOp 类.
此问题可能是由于 torchvision 库与您环境中的其他依赖项之间的版本不兼容引起的。
我运行命令
conda list torch# packages in environment at /home/tarsier/anaconda3:
#
# Name Version Build Channel
torch 2.0.1 pypi_0 pypi
torchvision 0.15.2 pypi_0 pypi
这是通过运行命令
pip listPackage Version
----------------------------- ---------------
alabaster 0.7.12
anaconda-client 1.11.2
anaconda-navigator 2.4.0
anaconda-project 0.11.1
anyio 3.5.0
appdirs 1.4.4
argon2-cffi 21.3.0
argon2-cffi-bindings 21.2.0
arrow 1.2.3
astroid 2.14.2
astropy 5.1
asttokens 2.0.5
atomicwrites 1.4.0
attrs 22.1.0
Automat 20.2.0
autopep8 1.6.0
Babel 2.11.0
backcall 0.2.0
backports.functools-lru-cache 1.6.4
backports.tempfile 1.0
backports.weakref 1.0.post1
bcrypt 3.2.0
beautifulsoup4 4.11.1
binaryornot 0.4.4
black 22.6.0
bleach 4.1.0
bokeh 2.4.3
boltons 23.0.0
Bottleneck 1.3.5
brotlipy 0.7.0
certifi 2023.5.7
cffi 1.15.1
chardet 4.0.0
charset-normalizer 2.0.4
click 8.0.4
cloudpickle 2.0.0
clyent 1.2.2
cmake 3.26.3
colorama 0.4.6
colorcet 3.0.1
comm 0.1.2
conda 23.3.1
conda-build 3.24.0
conda-content-trust 0.1.3
conda-pack 0.6.0
conda-package-handling 2.0.2
conda_package_streaming 0.7.0
conda-repo-cli 1.0.41
conda-token 0.4.0
conda-verify 3.4.2
constantly 15.1.0
contourpy 1.0.5
cookiecutter 1.7.3
cryptography 39.0.1
cssselect 1.1.0
cycler 0.11.0
Cython 0.29.34
cytoolz 0.12.0
daal4py 2023.0.2
dask 2022.7.0
datashader 0.14.4
datashape 0.5.4
debugpy 1.5.1
decorator 5.1.1
defusedxml 0.7.1
diff-match-patch 20200713
dill 0.3.6
distributed 2022.7.0
docstring-to-markdown 0.11
docutils 0.18.1
entrypoints 0.4
et-xmlfile 1.1.0
executing 0.8.3
fastjsonschema 2.16.2
filelock 3.9.0
flake8 6.0.0
Flask 2.2.2
flit_core 3.6.0
fonttools 4.25.0
fsspec 2022.11.0
fst-pso 1.8.1
future 0.18.3
FuzzyTM 2.0.5
gensim 4.3.1
glob2 0.7
gmpy2 2.1.2
greenlet 2.0.1
h5py 3.7.0
HeapDict 1.0.1
holoviews 1.15.4
huggingface-hub 0.10.1
hvplot 0.8.2
hyperlink 21.0.0
idna 3.4
imagecodecs 2021.8.26
imageio 2.26.0
imagesize 1.4.1
imbalanced-learn 0.10.1
importlib-metadata 4.11.3
incremental 21.3.0
inflection 0.5.1
iniconfig 1.1.1
intake 0.6.7
intervaltree 3.1.0
ipykernel 6.19.2
ipython 8.10.0
ipython-genutils 0.2.0
ipywidgets 7.6.5
isort 5.9.3
itemadapter 0.3.0
itemloaders 1.0.4
itsdangerous 2.0.1
jedi 0.18.1
jeepney 0.7.1
jellyfish 0.9.0
Jinja2 3.1.2
jinja2-time 0.2.0
jmespath 0.10.0
joblib 1.1.1
json5 0.9.6
jsonpatch 1.32
jsonpointer 2.1
jsonschema 4.17.3
jupyter 1.0.0
jupyter_client 7.3.4
jupyter-console 6.6.2
jupyter_core 5.2.0
jupyter-server 1.23.4
jupyterlab 3.5.3
jupyterlab-pygments 0.1.2
jupyterlab_server 2.19.0
jupyterlab-widgets 1.0.0
keyring 23.4.0
kiwisolver 1.4.4
lazy-object-proxy 1.6.0
libarchive-c 2.9
lit 16.0.3
llvmlite 0.39.1
locket 1.0.0
lxml 4.9.1
lz4 3.1.3
Markdown 3.4.1
MarkupSafe 2.1.1
matplotlib 3.7.0
matplotlib-inline 0.1.6
mccabe 0.7.0
miniful 0.0.6
mistune 0.8.4
mkl-fft 1.3.1
mkl-random 1.2.2
mkl-service 2.4.0
mock 4.0.3
mpmath 1.2.1
msgpack 1.0.3
multipledispatch 0.6.0
munkres 1.1.4
mypy-extensions 0.4.3
navigator-updater 0.3.0
nbclassic 0.5.2
nbclient 0.5.13
nbconvert 6.5.4
nbformat 5.7.0
nest-asyncio 1.5.6
networkx 2.8.4
nltk 3.7
notebook 6.5.2
notebook_shim 0.2.2
numba 0.56.4
numexpr 2.8.4
numpy 1.23.5
numpydoc 1.5.0
nvidia-cublas-cu11 11.10.3.66
nvidia-cuda-cupti-cu11 11.7.101
nvidia-cuda-nvrtc-cu11 11.7.99
nvidia-cuda-runtime-cu11 11.7.99
nvidia-cudnn-cu11 8.5.0.96
nvidia-cufft-cu11 10.9.0.58
nvidia-curand-cu11 10.2.10.91
nvidia-cusolver-cu11 11.4.0.1
nvidia-cusparse-cu11 11.7.4.91
nvidia-nccl-cu11 2.14.3
nvidia-nvtx-cu11 11.7.91
openpyxl 3.0.10
packaging 22.0
pandas 1.5.3
pandocfilters 1.5.0
panel 0.14.3
param 1.12.3
parsel 1.6.0
parso 0.8.3
partd 1.2.0
pathlib 1.0.1
pathspec 0.10.3
patsy 0.5.3
pep8 1.7.1
pexpect 4.8.0
pickleshare 0.7.5
Pillow 9.4.0
pip 22.3.1
pkginfo 1.9.6
platformdirs 2.5.2
plotly 5.9.0
pluggy 1.0.0
ply 3.11
pooch 1.4.0
poyo 0.5.0
prometheus-client 0.14.1
prompt-toolkit 3.0.36
Protego 0.1.16
psutil 5.9.0
ptyprocess 0.7.0
pure-eval 0.2.2
py 1.11.0
pyasn1 0.4.8
pyasn1-modules 0.2.8
pycocotools 2.0.6
pycodestyle 2.10.0
pycosat 0.6.4
pycparser 2.21
pyct 0.5.0
pycurl 7.45.1
PyDispatcher 2.0.5
pydocstyle 6.3.0
pyerfa 2.0.0
pyflakes 3.0.1
pyFUME 0.2.25
Pygments 2.11.2
PyHamcrest 2.0.2
PyJWT 2.4.0
pylint 2.16.2
pylint-venv 2.3.0
pyls-spyder 0.4.0
pyodbc 4.0.34
pyOpenSSL 23.0.0
pyparsing 3.0.9
PyQt5-sip 12.11.0
pyrsistent 0.18.0
PySocks 1.7.1
pytest 7.1.2
python-dateutil 2.8.2
python-lsp-black 1.2.1
python-lsp-jsonrpc 1.0.0
python-lsp-server 1.7.1
python-slugify 5.0.2
python-snappy 0.6.1
pytoolconfig 1.2.5
pytz 2022.7
pyviz-comms 2.0.2
PyWavelets 1.4.1
pyxdg 0.27
PyYAML 6.0
pyzmq 23.2.0
QDarkStyle 3.0.2
qstylizer 0.2.2
QtAwesome 1.2.2
qtconsole 5.4.0
QtPy 2.2.0
queuelib 1.5.0
regex 2022.7.9
requests 2.28.1
requests-file 1.5.1
requests-toolbelt 0.9.1
rope 1.7.0
Rtree 1.0.1
ruamel.yaml 0.17.21
ruamel.yaml.clib 0.2.6
ruamel-yaml-conda 0.17.21
scikit-image 0.19.3
scikit-learn 1.2.1
scikit-learn-intelex 20230228.214242
scipy 1.10.1
Scrapy 2.8.0
seaborn 0.12.2
SecretStorage 3.3.1
Send2Trash 1.8.0
service-identity 18.1.0
setuptools 65.6.3
simpful 2.11.0
sip 6.6.2
six 1.16.0
smart-open 5.2.1
sniffio 1.2.0
snowballstemmer 2.2.0
sortedcontainers 2.4.0
soupsieve 2.3.2.post1
Sphinx 5.0.2
sphinxcontrib-applehelp 1.0.2
sphinxcontrib-devhelp 1.0.2
sphinxcontrib-htmlhelp 2.0.0
sphinxcontrib-jsmath 1.0.1
sphinxcontrib-qthelp 1.0.3
sphinxcontrib-serializinghtml 1.1.5
spyder 5.4.1
spyder-kernels 2.4.1
SQLAlchemy 1.4.39
stack-data 0.2.0
statsmodels 0.13.5
sympy 1.11.1
tables 3.7.0
tabulate 0.8.10
TBB 0.2
tblib 1.7.0
tenacity 8.0.1
terminado 0.17.1
text-unidecode 1.3
textdistance 4.2.1
threadpoolctl 2.2.0
three-merge 0.1.1
tifffile 2021.7.2
tinycss2 1.2.1
tldextract 3.2.0
tokenizers 0.11.4
toml 0.10.2
tomli 2.0.1
tomlkit 0.11.1
toolz 0.12.0
torch 2.0.1
torchvision 0.15.2
tornado 6.1
tqdm 4.65.0
traitlets 5.7.1
transformers 4.24.0
triton 2.0.0
Twisted 22.2.0
typing_extensions 4.4.0
ujson 5.4.0
Unidecode 1.2.0
urllib3 1.26.14
w3lib 1.21.0
watchdog 2.1.6
wcwidth 0.2.5
webencodings 0.5.1
websocket-client 0.58.0
Werkzeug 2.2.2
whatthepatch 1.0.2
wheel 0.38.4
widgetsnbextension 3.5.2
wrapt 1.14.1
wurlitzer 3.0.2
xarray 2022.11.0
yapf 0.31.0
zict 2.1.0
zipp 3.11.0
zope.interface 5.4.0
zstandard 0.19.0
我试图通过运行以下命令来检查我是否安装了最新版本的torch和torchvision：
pip install torch torchvision --upgrade我试图将torchvision版本降级到0.13.2版本。但是，我在从 GitHub 存储库的 coco.py 中从 torchvision 导入数据集时出错：
from .torchvision_datasets import CocoDetection as TvCocoDetection这是coco.py代码：
# ------------------------------------------------------------------------
# Deformable DETR
# Copyright (c) 2020 SenseTime. All Rights Reserved.
# Licensed under the Apache License, Version 2.0 [see LICENSE for details]
# ------------------------------------------------------------------------
# Modified from DETR (https://github.com/facebookresearch/detr)
# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
# ------------------------------------------------------------------------
"""
COCO dataset which returns image_id for evaluation.
Mostly copy-paste from https://github.com/pytorch/vision/blob/13b35ff/references/detection/coco_utils.py
"""
from pathlib import Path
import torch
import torch.utils.data
from pycocotools import mask as coco_mask
from .torchvision_datasets import CocoDetection as TvCocoDetection
from util.misc import get_local_rank, get_local_size
import datasets.transforms as T
class CocoDetection(TvCocoDetection):
def __init__(self, img_folder, ann_file, transforms, return_masks, cache_mode=False, local_rank=0, local_size=1):
super(CocoDetection, self).__init__(img_folder, ann_file,
cache_mode=cache_mode, local_rank=local_rank, local_size=local_size)
self._transforms = transforms
self.prepare = ConvertCocoPolysToMask(return_masks)
def __getitem__(self, idx):
img, target = super(CocoDetection, self).__getitem__(idx)
image_id = self.ids[idx]
target = {'image_id': image_id, 'annotations': target}
img, target = self.prepare(img, target)
if self._transforms is not None:
img, target = self._transforms(img, target)
return img, target
def convert_coco_poly_to_mask(segmentations, height, width):
masks = []
for polygons in segmentations:
rles = coco_mask.frPyObjects(polygons, height, width)
mask = coco_mask.decode(rles)
if len(mask.shape) < 3:
mask = mask[..., None]
mask = torch.as_tensor(mask, dtype=torch.uint8)
mask = mask.any(dim=2)
masks.append(mask)
if masks:
masks = torch.stack(masks, dim=0)
else:
masks = torch.zeros((0, height, width), dtype=torch.uint8)
return masks
class ConvertCocoPolysToMask(object):
def __init__(self, return_masks=False):
self.return_masks = return_masks
def __call__(self, image, target):
w, h = image.size
image_id = target["image_id"]
image_id = torch.tensor([image_id])
anno = target["annotations"]
anno = [obj for obj in anno if 'iscrowd' not in obj or obj['iscrowd'] == 0]
boxes = [obj["bbox"] for obj in anno]
# guard against no boxes via resizing
boxes = torch.as_tensor(boxes, dtype=torch.float32).reshape(-1, 4)
boxes[:, 2:] += boxes[:, :2]
boxes[:, 0::2].clamp_(min=0, max=w)
boxes[:, 1::2].clamp_(min=0, max=h)
classes = [obj["category_id"] for obj in anno]
classes = torch.tensor(classes, dtype=torch.int64)
if self.return_masks:
segmentations = [obj["segmentation"] for obj in anno]
masks = convert_coco_poly_to_mask(segmentations, h, w)
keypoints = None
if anno and "keypoints" in anno[0]:
keypoints = [obj["keypoints"] for obj in anno]
keypoints = torch.as_tensor(keypoints, dtype=torch.float32)
num_keypoints = keypoints.shape[0]
if num_keypoints:
keypoints = keypoints.view(num_keypoints, -1, 3)
keep = (boxes[:, 3] > boxes[:, 1]) & (boxes[:, 2] > boxes[:, 0])
boxes = boxes[keep]
classes = classes[keep]
if self.return_masks:
masks = masks[keep]
if keypoints is not None:
keypoints = keypoints[keep]
target = {}
target["boxes"] = boxes
target["labels"] = classes
if self.return_masks:
target["masks"] = masks
target["image_id"] = image_id
if keypoints is not None:
target["keypoints"] = keypoints
# for conversion to coco api
area = torch.tensor([obj["area"] for obj in anno])
iscrowd = torch.tensor([obj["iscrowd"] if "iscrowd" in obj else 0 for obj in anno])
target["area"] = area[keep]
target["iscrowd"] = iscrowd[keep]
target["orig_size"] = torch.as_tensor([int(h), int(w)])
target["size"] = torch.as_tensor([int(h), int(w)])
return image, target
def make_coco_transforms(image_set):
normalize = T.Compose([
T.ToTensor(),
T.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
])
scales = [480, 512, 544, 576, 608, 640, 672, 704, 736, 768, 800]
if image_set == 'train':
return T.Compose([
T.RandomHorizontalFlip(),
T.RandomSelect(
T.RandomResize(scales, max_size=1333),
T.Compose([
T.RandomResize([400, 500, 600]),
T.RandomSizeCrop(384, 600),
T.RandomResize(scales, max_size=1333),
])
),
normalize,
])
if image_set == 'val':
return T.Compose([
T.RandomResize([800], max_size=1333),
normalize,
])
raise ValueError(f'unknown {image_set}')
def build(image_set, args):
root = Path(args.coco_path)
assert root.exists(), f'provided COCO path {root} does not exist'
mode = 'instances'
PATHS = {
"train": (root / "train2017", root / "annotations" / f'{mode}_train2017.json'),
"val": (root / "val2017", root / "annotations" / f'{mode}_val2017.json'),
}
img_folder, ann_file = PATHS[image_set]
dataset = CocoDetection(img_folder, ann_file, transforms=make_coco_transforms(image_set), return_masks=args.masks,
cache_mode=args.cache_mode, local_rank=get_local_rank(), local_size=get_local_size())
return dataset