为什么亚

最新推荐文章于 2023-03-17 15:48:13 发布
最新推荐文章于 2023-03-17 15:48:13 发布
阅读量403 收藏
点赞数
版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
本文链接：https://blog.csdn.net/z_6_2_0_s/article/details/107381585
版权

这是什么情况
谁能救我？？？？？？？？？？？

(pytracking) zs@zsG3:~/project/pytracking-Old（复件）/pytracking$ python run_webcam.py dimp dimp50    
Traceback (most recent call last):
  File "run_webcam.py", line 41, in <module>
    main()
  File "run_webcam.py", line 37, in main
    run_webcam(args.tracker_name, args.tracker_param, args.debug, visdom_info)
  File "run_webcam.py", line 22, in run_webcam
    tracker.run_webcam(debug, visdom_info)
  File "../pytracking/evaluation/tracker.py", line 101, in run_webcam
    tracker.track_webcam()
  File "../pytracking/tracker/base/basetracker.py", line 242, in track_webcam
    self.initialize_features()
  File "../pytracking/tracker/dimp/dimp.py", line 17, in initialize_features
    self.params.net.initialize()
  File "../pytracking/features/net_wrappers.py", line 41, in initialize
    super().initialize()
  File "../pytracking/features/net_wrappers.py", line 34, in initialize
    self.load_network()
  File "../pytracking/features/net_wrappers.py", line 28, in load_network
    self.net = load_network(self.net_path)
  File "../pytracking/utils/loading.py", line 23, in load_network
    net, _ = ltr_loading.load_network(path_full, backbone_pretrained=False)
  File "../ltr/admin/loading.py", line 73, in load_network
    net_fun = getattr(importlib.import_module(net_constr.fun_module), net_constr.fun_name)
  File "/home/zs/miniconda3/envs/pytracking/lib/python3.7/importlib/__init__.py", line 127, in import_module
    return _bootstrap._gcd_import(name[level:], package, level)
  File "<frozen importlib._bootstrap>", line 1006, in _gcd_import
  File "<frozen importlib._bootstrap>", line 983, in _find_and_load
  File "<frozen importlib._bootstrap>", line 967, in _find_and_load_unlocked
  File "<frozen importlib._bootstrap>", line 677, in _load_unlocked
  File "<frozen importlib._bootstrap_external>", line 728, in exec_module
  File "<frozen importlib._bootstrap>", line 219, in _call_with_frames_removed
  File "../ltr/models/tracking/dimpnet.py", line 6, in <module>
    import ltr.models.target_classifier.features as clf_features
  File "../ltr/models/target_classifier/features.py", line 4, in <module>
    from torchvision.models.resnet import BasicBlock, Bottleneck
  File "/home/zs/.local/lib/python3.7/site-packages/torchvision/__init__.py", line 3, in <module>
    from torchvision import models
  File "/home/zs/.local/lib/python3.7/site-packages/torchvision/models/__init__.py", line 12, in <module>
    from . import detection
  File "/home/zs/.local/lib/python3.7/site-packages/torchvision/models/detection/__init__.py", line 1, in <module>
    from .faster_rcnn import *
  File "/home/zs/.local/lib/python3.7/site-packages/torchvision/models/detection/faster_rcnn.py", line 13, in <module>
    from .rpn import AnchorGenerator, RPNHead, RegionProposalNetwork
  File "/home/zs/.local/lib/python3.7/site-packages/torchvision/models/detection/rpn.py", line 11, in <module>
    from . import _utils as det_utils
  File "/home/zs/.local/lib/python3.7/site-packages/torchvision/models/detection/_utils.py", line 19, in <module>
    class BalancedPositiveNegativeSampler(object):
  File "/home/zs/miniconda3/envs/pytracking/lib/python3.7/site-packages/torch/jit/__init__.py", line 1219, in script
    _compile_and_register_class(obj, _rcb, qualified_name)
  File "/home/zs/miniconda3/envs/pytracking/lib/python3.7/site-packages/torch/jit/__init__.py", line 1076, in _compile_and_register_class
    _jit_script_class_compile(qualified_name, ast, rcb)
  File "/home/zs/miniconda3/envs/pytracking/lib/python3.7/site-packages/torch/jit/_recursive.py", line 222, in try_compile_fn
    return torch.jit.script(fn, _rcb=rcb)
  File "/home/zs/miniconda3/envs/pytracking/lib/python3.7/site-packages/torch/jit/__init__.py", line 1226, in script
    fn = torch._C._jit_script_compile(qualified_name, ast, _rcb, get_default_args(obj))
RuntimeError: 
builtin cannot be used as a value:
at /home/zs/.local/lib/python3.7/site-packages/torchvision/models/detection/_utils.py:14:56
def zeros_like(tensor, dtype):
    # type: (Tensor, int) -> Tensor
    return torch.zeros_like(tensor, dtype=dtype, layout=tensor.layout,
                                                        ~~~~~~~~~~~~~ <--- HERE
                            device=tensor.device, pin_memory=tensor.is_pinned())
'zeros_like' is being compiled since it was called from '__torch__.torchvision.models.detection._utils.BalancedPositiveNegativeSampler.__call__'
at /home/zs/.local/lib/python3.7/site-packages/torchvision/models/detection/_utils.py:72:12

            # randomly select positive and negative examples
            perm1 = torch.randperm(positive.numel(), device=positive.device)[:num_pos]
            perm2 = torch.randperm(negative.numel(), device=negative.device)[:num_neg]

            pos_idx_per_image = positive[perm1]
            neg_idx_per_image = negative[perm2]

            # create binary mask from indices
            pos_idx_per_image_mask = zeros_like(
            ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~...  <--- HERE
                matched_idxs_per_image, dtype=torch.uint8
            )
            neg_idx_per_image_mask = zeros_like(
                matched_idxs_per_image, dtype=torch.uint8
            )

            pos_idx_per_image_mask[pos_idx_per_image] = torch.tensor(1, dtype=torch.uint8)
            neg_idx_per_image_mask[neg_idx_per_image] = torch.tensor(1, dtype=torch.uint8)

(pytracking) zs@zsG3:~/project/pytracking-Old（复件）/pytracking$ python run_webcam.py dimp dimp50    
Traceback (most recent call last):
  File "run_webcam.py", line 41, in <module>
    main()
  File "run_webcam.py", line 37, in main
    run_webcam(args.tracker_name, args.tracker_param, args.debug, visdom_info)
  File "run_webcam.py", line 22, in run_webcam
    tracker.run_webcam(debug, visdom_info)
  File "../pytracking/evaluation/tracker.py", line 101, in run_webcam
    tracker.track_webcam()
  File "../pytracking/tracker/base/basetracker.py", line 242, in track_webcam
    self.initialize_features()
  File "../pytracking/tracker/dimp/dimp.py", line 17, in initialize_features
    self.params.net.initialize()
  File "../pytracking/features/net_wrappers.py", line 41, in initialize
    super().initialize()
  File "../pytracking/features/net_wrappers.py", line 34, in initialize
    self.load_network()
  File "../pytracking/features/net_wrappers.py", line 28, in load_network
    self.net = load_network(self.net_path)
  File "../pytracking/utils/loading.py", line 23, in load_network
    net, _ = ltr_loading.load_network(path_full, backbone_pretrained=False)
  File "../ltr/admin/loading.py", line 73, in load_network
    net_fun = getattr(importlib.import_module(net_constr.fun_module), net_constr.fun_name)
  File "/home/zs/miniconda3/envs/pytracking/lib/python3.7/importlib/__init__.py", line 127, in import_module
    return _bootstrap._gcd_import(name[level:], package, level)
  File "<frozen importlib._bootstrap>", line 1006, in _gcd_import
  File "<frozen importlib._bootstrap>", line 983, in _find_and_load
  File "<frozen importlib._bootstrap>", line 967, in _find_and_load_unlocked
  File "<frozen importlib._bootstrap>", line 677, in _load_unlocked
  File "<frozen importlib._bootstrap_external>", line 728, in exec_module
  File "<frozen importlib._bootstrap>", line 219, in _call_with_frames_removed
  File "../ltr/models/tracking/dimpnet.py", line 6, in <module>
    import ltr.models.target_classifier.features as clf_features
  File "../ltr/models/target_classifier/features.py", line 4, in <module>
    from torchvision.models.resnet import BasicBlock, Bottleneck
  File "/home/zs/.local/lib/python3.7/site-packages/torchvision/__init__.py", line 3, in <module>
    from torchvision import models
  File "/home/zs/.local/lib/python3.7/site-packages/torchvision/models/__init__.py", line 12, in <module>
    from . import detection
  File "/home/zs/.local/lib/python3.7/site-packages/torchvision/models/detection/__init__.py", line 1, in <module>
    from .faster_rcnn import *
  File "/home/zs/.local/lib/python3.7/site-packages/torchvision/models/detection/faster_rcnn.py", line 13, in <module>
    from .rpn import AnchorGenerator, RPNHead, RegionProposalNetwork
  File "/home/zs/.local/lib/python3.7/site-packages/torchvision/models/detection/rpn.py", line 11, in <module>
    from . import _utils as det_utils
  File "/home/zs/.local/lib/python3.7/site-packages/torchvision/models/detection/_utils.py", line 19, in <module>
    class BalancedPositiveNegativeSampler(object):
  File "/home/zs/miniconda3/envs/pytracking/lib/python3.7/site-packages/torch/jit/__init__.py", line 1219, in script
    _compile_and_register_class(obj, _rcb, qualified_name)
  File "/home/zs/miniconda3/envs/pytracking/lib/python3.7/site-packages/torch/jit/__init__.py", line 1076, in _compile_and_register_class
    _jit_script_class_compile(qualified_name, ast, rcb)
  File "/home/zs/miniconda3/envs/pytracking/lib/python3.7/site-packages/torch/jit/_recursive.py", line 222, in try_compile_fn
    return torch.jit.script(fn, _rcb=rcb)
  File "/home/zs/miniconda3/envs/pytracking/lib/python3.7/site-packages/torch/jit/__init__.py", line 1226, in script
    fn = torch._C._jit_script_compile(qualified_name, ast, _rcb, get_default_args(obj))
RuntimeError: 
builtin cannot be used as a value:
at /home/zs/.local/lib/python3.7/site-packages/torchvision/models/detection/_utils.py:14:56
def zeros_like(tensor, dtype):
    # type: (Tensor, int) -> Tensor
    return torch.zeros_like(tensor, dtype=dtype, layout=tensor.layout,
                                                        ~~~~~~~~~~~~~ <--- HERE
                            device=tensor.device, pin_memory=tensor.is_pinned())
'zeros_like' is being compiled since it was called from '__torch__.torchvision.models.detection._utils.BalancedPositiveNegativeSampler.__call__'
at /home/zs/.local/lib/python3.7/site-packages/torchvision/models/detection/_utils.py:72:12

            # randomly select positive and negative examples
            perm1 = torch.randperm(positive.numel(), device=positive.device)[:num_pos]
            perm2 = torch.randperm(negative.numel(), device=negative.device)[:num_neg]

            pos_idx_per_image = positive[perm1]
            neg_idx_per_image = negative[perm2]

            # create binary mask from indices
            pos_idx_per_image_mask = zeros_like(
            ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~...  <--- HERE
                matched_idxs_per_image, dtype=torch.uint8
            )
            neg_idx_per_image_mask = zeros_like(
                matched_idxs_per_image, dtype=torch.uint8
            )

            pos_idx_per_image_mask[pos_idx_per_image] = torch.tensor(1, dtype=torch.uint8)
            neg_idx_per_image_mask[neg_idx_per_image] = torch.tensor(1, dtype=torch.uint8)

(pytracking) zs@zsG3:~/project/pytracking-Old（复件）/pytracking$ conda deactivate
(base) zs@zsG3:~/project/pytracking-Old（复件）/pytracking$ conda activate pytracking2
(pytracking2) zs@zsG3:~/project/pytracking-Old（复件）/pytracking$ python run_webcam.py dimp dimp50    
Traceback (most recent call last):
  File "run_webcam.py", line 41, in <module>
    main()
  File "run_webcam.py", line 37, in main
    run_webcam(args.tracker_name, args.tracker_param, args.debug, visdom_info)
  File "run_webcam.py", line 22, in run_webcam
    tracker.run_webcam(debug, visdom_info)
  File "../pytracking/evaluation/tracker.py", line 101, in run_webcam
    tracker.track_webcam()
  File "../pytracking/tracker/base/basetracker.py", line 242, in track_webcam
    self.initialize_features()
  File "../pytracking/tracker/dimp/dimp.py", line 17, in initialize_features
    self.params.net.initialize()
  File "../pytracking/features/net_wrappers.py", line 41, in initialize
    super().initialize()
  File "../pytracking/features/net_wrappers.py", line 34, in initialize
    self.load_network()
  File "../pytracking/features/net_wrappers.py", line 28, in load_network
    self.net = load_network(self.net_path)
  File "../pytracking/utils/loading.py", line 23, in load_network
    net, _ = ltr_loading.load_network(path_full, backbone_pretrained=False)
  File "../ltr/admin/loading.py", line 73, in load_network
    net_fun = getattr(importlib.import_module(net_constr.fun_module), net_constr.fun_name)
  File "/home/zs/miniconda3/envs/pytracking2/lib/python3.7/importlib/__init__.py", line 127, in import_module
    return _bootstrap._gcd_import(name[level:], package, level)
  File "<frozen importlib._bootstrap>", line 1006, in _gcd_import
  File "<frozen importlib._bootstrap>", line 983, in _find_and_load
  File "<frozen importlib._bootstrap>", line 967, in _find_and_load_unlocked
  File "<frozen importlib._bootstrap>", line 677, in _load_unlocked
  File "<frozen importlib._bootstrap_external>", line 728, in exec_module
  File "<frozen importlib._bootstrap>", line 219, in _call_with_frames_removed
  File "../ltr/models/tracking/dimpnet.py", line 6, in <module>
    import ltr.models.target_classifier.features as clf_features
  File "../ltr/models/target_classifier/features.py", line 4, in <module>
    from torchvision.models.resnet import BasicBlock, Bottleneck
  File "/home/zs/.local/lib/python3.7/site-packages/torchvision/__init__.py", line 3, in <module>
    from torchvision import models
  File "/home/zs/.local/lib/python3.7/site-packages/torchvision/models/__init__.py", line 12, in <module>
    from . import detection
  File "/home/zs/.local/lib/python3.7/site-packages/torchvision/models/detection/__init__.py", line 1, in <module>
    from .faster_rcnn import *
  File "/home/zs/.local/lib/python3.7/site-packages/torchvision/models/detection/faster_rcnn.py", line 13, in <module>
    from .rpn import AnchorGenerator, RPNHead, RegionProposalNetwork
  File "/home/zs/.local/lib/python3.7/site-packages/torchvision/models/detection/rpn.py", line 11, in <module>
    from . import _utils as det_utils
  File "/home/zs/.local/lib/python3.7/site-packages/torchvision/models/detection/_utils.py", line 19, in <module>
    class BalancedPositiveNegativeSampler(object):
  File "/home/zs/miniconda3/envs/pytracking2/lib/python3.7/site-packages/torch/jit/__init__.py", line 1219, in script
    _compile_and_register_class(obj, _rcb, qualified_name)
  File "/home/zs/miniconda3/envs/pytracking2/lib/python3.7/site-packages/torch/jit/__init__.py", line 1076, in _compile_and_register_class
    _jit_script_class_compile(qualified_name, ast, rcb)
  File "/home/zs/miniconda3/envs/pytracking2/lib/python3.7/site-packages/torch/jit/_recursive.py", line 222, in try_compile_fn
    return torch.jit.script(fn, _rcb=rcb)
  File "/home/zs/miniconda3/envs/pytracking2/lib/python3.7/site-packages/torch/jit/__init__.py", line 1226, in script
    fn = torch._C._jit_script_compile(qualified_name, ast, _rcb, get_default_args(obj))
RuntimeError: 
builtin cannot be used as a value:
at /home/zs/.local/lib/python3.7/site-packages/torchvision/models/detection/_utils.py:14:56
def zeros_like(tensor, dtype):
    # type: (Tensor, int) -> Tensor
    return torch.zeros_like(tensor, dtype=dtype, layout=tensor.layout,
                                                        ~~~~~~~~~~~~~ <--- HERE
                            device=tensor.device, pin_memory=tensor.is_pinned())
'zeros_like' is being compiled since it was called from '__torch__.torchvision.models.detection._utils.BalancedPositiveNegativeSampler.__call__'
at /home/zs/.local/lib/python3.7/site-packages/torchvision/models/detection/_utils.py:72:12

            # randomly select positive and negative examples
            perm1 = torch.randperm(positive.numel(), device=positive.device)[:num_pos]
            perm2 = torch.randperm(negative.numel(), device=negative.device)[:num_neg]

            pos_idx_per_image = positive[perm1]
            neg_idx_per_image = negative[perm2]

            # create binary mask from indices
            pos_idx_per_image_mask = zeros_like(
            ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~...  <--- HERE
                matched_idxs_per_image, dtype=torch.uint8
            )
            neg_idx_per_image_mask = zeros_like(
                matched_idxs_per_image, dtype=torch.uint8
            )

            pos_idx_per_image_mask[pos_idx_per_image] = torch.tensor(1, dtype=torch.uint8)
            neg_idx_per_image_mask[neg_idx_per_image] = torch.tensor(1, dtype=torch.uint8)

真是奇怪亚，conda list显示torchvision版本是0.4.2
torchvision 0.4.2 cuda100py37hecfc37a_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
卸载torchvision时候 居然：
Found existing installation: torchvision 0.5.0
Uninstalling torchvision-0.5.0:
那么为什么ide里面没有把0.5.0版本展示出来亚，为什么运行程序时候import torchvision报错不提示是0.5.0版本
老错误终于解决，出现新错误啦！！

Traceback (most recent call last):
  File "run_webcam.py", line 41, in <module>
    main()
  File "run_webcam.py", line 37, in main
    run_webcam(args.tracker_name, args.tracker_param, args.debug, visdom_info)
  File "run_webcam.py", line 22, in run_webcam
    tracker.run_webcam(debug, visdom_info)
  File "../pytracking/evaluation/tracker.py", line 101, in run_webcam
    tracker.track_webcam()
  File "../pytracking/tracker/base/basetracker.py", line 242, in track_webcam
    self.initialize_features()
  File "../pytracking/tracker/dimp/dimp.py", line 17, in initialize_features
    self.params.net.initialize()
  File "../pytracking/features/net_wrappers.py", line 41, in initialize
    super().initialize()
  File "../pytracking/features/net_wrappers.py", line 34, in initialize
    self.load_network()
  File "../pytracking/features/net_wrappers.py", line 28, in load_network
    self.net = load_network(self.net_path)
  File "../pytracking/utils/loading.py", line 23, in load_network
    net, _ = ltr_loading.load_network(path_full, backbone_pretrained=False)
  File "../ltr/admin/loading.py", line 73, in load_network
    net_fun = getattr(importlib.import_module(net_constr.fun_module), net_constr.fun_name)
  File "/home/zs/miniconda3/envs/pytracking2/lib/python3.7/importlib/__init__.py", line 127, in import_module
    return _bootstrap._gcd_import(name[level:], package, level)
  File "<frozen importlib._bootstrap>", line 1006, in _gcd_import
  File "<frozen importlib._bootstrap>", line 983, in _find_and_load
  File "<frozen importlib._bootstrap>", line 967, in _find_and_load_unlocked
  File "<frozen importlib._bootstrap>", line 677, in _load_unlocked
  File "<frozen importlib._bootstrap_external>", line 728, in exec_module
  File "<frozen importlib._bootstrap>", line 219, in _call_with_frames_removed
  File "../ltr/models/tracking/dimpnet.py", line 6, in <module>
    import ltr.models.target_classifier.features as clf_features
  File "../ltr/models/target_classifier/features.py", line 4, in <module>
    from torchvision.models.resnet import BasicBlock, Bottleneck
  File "/home/zs/miniconda3/envs/pytracking2/lib/python3.7/site-packages/torchvision/__init__.py", line 4, in <module>
    from torchvision import datasets
  File "/home/zs/miniconda3/envs/pytracking2/lib/python3.7/site-packages/torchvision/datasets/__init__.py", line 9, in <module>
    from .fakedata import FakeData
  File "/home/zs/miniconda3/envs/pytracking2/lib/python3.7/site-packages/torchvision/datasets/fakedata.py", line 3, in <module>
    from .. import transforms
  File "/home/zs/miniconda3/envs/pytracking2/lib/python3.7/site-packages/torchvision/transforms/__init__.py", line 1, in <module>
    from .transforms import *
  File "/home/zs/miniconda3/envs/pytracking2/lib/python3.7/site-packages/torchvision/transforms/transforms.py", line 17, in <module>
    from . import functional as F
  File "/home/zs/miniconda3/envs/pytracking2/lib/python3.7/site-packages/torchvision/transforms/functional.py", line 5, in <module>
    from PIL import Image, ImageOps, ImageEnhance, PILLOW_VERSION
ImportError: cannot import name 'PILLOW_VERSION' from 'PIL' (/home/zs/.local/lib/python3.7/site-packages/PIL/__init__.py)


conda uninstall pillow
Found existing installation: Pillow 7.0.0
Uninstalling Pillow-7.0.0:

conda install pillow=6.1
OK了！
coding.....
关注
使用detectron2 出现 RuntimeError: object has no attribute nms 报错记录
G果的博客
07-12 2057
代码环境： python = 3.6 torch = 1.6.0 torchvision = 0.7.0 cuda = 9.2 detectron2 = 0.4 安装torch和torchvision命令（来自pytorch官网V1.6.0） conda install pytorch==1.6.0 torchvision==0.7.0 cudatoolkit=9.2 -c pytorch 安装detectron2命令对应torch1.6.0版本（来自detectron2官网的installation教
TORCHVISION 目标检测微调教程
Shiraka的博客
08-08 873
TORCHVISION 目标检测微调教程 前言 前四节，我们初步掌握了通过PyTorch构建神经网络模型，以及优化参数，模型集成等问题，本章程将微调Penn-Fudan 数据库中用于行人检测和分割的预训练Mask R-CNN模型。它包含 170 张图像和 345 个行人实例，我们将用它来说明如何使用 torchvision 中的新功能在自定义数据集上训练实例分割模型。 定义数据集 用于训练对象检测、实例分割和人物关键点检测的参考脚本允许轻松支持添加新的自定义数据集。数据集应该继承自标准 torch.ut
PyTorch 源码解读之即时编译篇
weixin_36896856的博客
06-19 2344
点击上方“AI遇见机器学习”，选择“星标”公众号重磅干货，第一时间送达作者丨OpenMMLab来源丨https://zhuanlan.zhihu.com/p/361101354转自丨Gia...
【Torch API】pytorch 中torch.ones_like和torch.zeros_like函数详解
devil_son1234的博客
03-17 594
pytorch 中torch.ones_like和torch.zero_like函数详解
pytorch torchvision 实现的keypoint rcnn使用python进行预测并显示预测结果
不解不惑
07-15 2080
深度学习中，完成模型训练后，需要编写测试文件，读取输入数据和模型进行推理，对推理结果进行输出和显示，这里整理了一个keypoint rcnn的推理和结果显示代码。
亚稳态
littbi的博客
02-27 1703
在同步电路当中，数据和时钟总是有着固定的关系，所以当这种关系在满足器件的建立和保持时间的要求时，输出就会在一段延时之后输出一个稳定的值。在同步电路中，满足时序要求的电路是不会有亚稳态出现的。但是，在异步电路中，由于数据和时钟有着不固定的关系，当这种关系违背了时序要求的时候，就会出现亚稳态。 亚稳态是由于违背了触发器的建立时间和保持时间而产生的。设计中的每个触发器都...
亚阈值区电路mos管特性
Carol0630的博客
01-17 3722
亚阈值区-eetop 1.关于亚阈区sub-threshold
亚像素检测_图像处理亚像素检测_
10-04
在标准像素级别的检测中，每个像素被视为图像的基本单位，而亚像素检测则能够识别出位于像素边界之间的位置，从而提供比单个像素更精确的测量结果。这在很多应用中至关重要，比如精密测量、目标跟踪、图像分割以及...
ICD-10亚目表.xls
08-16
指四位数编码，包括一个字母、三位数字和一个小数点。例如：A01.0 伤害。有的亚目为若干个3位数类目的共同亚目，此时无论在第一卷或第三卷中，都会列出一个表，以避免重复。
GFPGAN源码分析—第八篇
Vaifer233的博客
12-26 1082
2021SC@SDUSC 源码： models\init.py models\gfpgan_model.py 本篇主要分析init.py与models\gfpgan_model.py下的 class GFPGANModel(BaseModel) 类init(self, opt) 方法 目录 init.py gfpgan_model.py class GFPGANModel(BaseModel) init(self, opt) init_training_settings(self)
Pytorch C++部署 之 TorchScript 踩坑记录
ll_cookie的博客
04-04 1万+
小白一枚，最近尝试用c++调pytorch模型，网上搜了一对资料，大同小异，都是需要先将模型文件转换成torch script。 pytorch官网提供两种方式，1：trace 2：注释。 这两种方式怎么操作，官网以及很多博客都有详细介绍，不细扣，我也扣不明白，毕竟我是个小白，放链接供参考： https://blog.csdn.net/dou3516/article/details/829124...
torch版本的降维和升维
aboy2018的博客
05-27 1万+
原文地址：http://www.mamicode.com/info-detail-2561432.html unsqueeze（arg）是增添第arg个维度为1，以插入的形式填充 squeeze（arg）是删除第arg个维度(如果当前维度不为1，则不会进行删除) ...
pytorch之torch.ones_like
weixin_42797179的博客
02-08 3万+
torch.ones_like(input, dtype=None, layout=None, device=None, requires_grad=False) → Tensor 返回一个填充了标量值1的张量，其大小与之相同 input。torch.ones_like(input)相当于 。torch.ones(input.size(), dtype=input.dtype, layout=in...
C++部署Pytorch（Libtorch）出现问题、错误汇总
zzz_zzz12138的博客
10-17 3万+
错误汇总1、 error C2440: “初始化”: 无法从“torch::jit::script::Module”转换为“std::shared_ptr” 1、 error C2440: “初始化”: 无法从“torch::jit::script::Module”转换为“std::shared_ptrtorch::jit::script::Module” 如果采用网络上流行的libtorch测试代码： #include <torch/script.h> // One-stop header.
torch.zeros_like()函数的用法
写代码的高酱
09-10 8873
1.torch.zeros_like()函数的用法 官方API传送门：https://pytorch.org/docs/stable/generated/torch.zeros_like.html?highlight=zeros_like#torch.zeros_like
Windows 10系统Pip方式安装Pytorch1.4-CUDA10.1的记录
Leemon323的博客
02-11 5968
1. 基础环境 Windows 10系统+独显（支持CUDA），我已有的环境是python3.6 + pip + （numpy + pillow + six + 其他一些科学计算库）+ VC++ 2019/2015 build tool 环境。 需要CUDA tool kit + cuDNN（深度学习） 的GPU加速框架。其中CUDA安装最费劲，2.5G-10.1版本，并且需要有visual ...
PyTorch源码解读之torchvision.models
热门推荐
AI之路
01-21 10万+
PyTorch框架中有一个非常重要且好用的包：torchvision，该包主要由3个子包组成，分别是：torchvision.datasets、torchvision.models、torchvision.transforms。这3个子包的具体介绍可以参考官网：http://pytorch.org/docs/master/torchvision/index.html。具体代码可以参考github：
pytorch之inception_v3的实现
朴素.无恙的博客
01-03 5239
pytorch之inception_v3的实现 from __future__ import print_function from __future__ import division import torch import torch.nn as nn import torch.optim as optim import numpy as np import torchvision from...
HoughLinesP 函数是否为亚像素
最新发布
05-24
在普通的HoughLines函数中，直线被表示为(x, y)坐标系中的极坐标(r,θ)，但是在HoughLinesP函数中，直线被表示为(x1, y1)和(x2, y2)两个端点的坐标。这使得HoughLinesP函数能够更准确地检测直线，并且能够检测到比...
评论 5
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值