GithubHelp home page GithubHelp logo

detr-pytorch's Introduction

Hi,很高兴遇见你 👋

detr-pytorch's People

Contributors

bubbliiiing avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar

detr-pytorch's Issues

模型未进行梯度更新

b导,我在运行你的代码训练自己的数据集100个epoch后,发现map异常低。在比较第100个epoch和第50个epoch时发现里面的weight都是一样的,并未更新模型的weight(其他epoch都是这样),不知道该问题如何解决。
训练数据集为COCO数据集,数据格式类型并没有问题。
image

【问题--Heatmap可视化】B导,请问如何自己手动将注意力热图可视化模块添加DETR模型的预测文件(predict.py)

毕导您好,
我在参考以往您YOLO系列,其中的注意力热图可视化模块(mode="heatmap")并向DETR模型中手动加入heatmap模块时,遇到如下问题:
R8W$96XYB03T_MS~ SUMMC3
请问,我应该如何将 output的shape 由 [batch_size, 100, num_classes + 1],[batch_size, 100, 4] 转为为YOLO系列(如yolov4-tiny)中的 [b, c, h, w],如下图所示。

8A~62J YUJN(CFQXCC )D

导,请教一下模型训模型不收敛问题!

导你好,想请教一下为什么detr的这个工程不加载与训练模型的话,训练基本不收敛,我尝试了不同的学习策略,但是基本没用,想问一下导有试过不加载预训练模型训练吗?

提交一个bug

class LossHistory():
def init(self, log_dir, model, input_shape):
self.log_dir = log_dir
self.losses = []
self.val_loss = []

    os.makedirs(self.log_dir)
    self.writer     = SummaryWriter(self.log_dir)
    try:
        dummy_input     = torch.randn(2, 3, input_shape[0], input_shape[1])
        self.writer.add_graph(model, dummy_input)
    except:
        pass   这部分代码虽然加载了模型到tensorboard 但是不能正确显示

运行报错

b导,我在跑您的detr代码时,训练10个epoch没问题,但是在每十个epoch计算一次mAP的时候报错:
File "/opt/data/private/detr/utils/utils_bbox.py", line 31, in forward
boxes = boxes * scale_fct[:, None, :]
RuntimeError: expected device cuda:0 and dtype Float but got device cuda:0 and dtype Long
这是怎么回事呢?

RuntimeError

RuntimeError: Error(s) in loading state_dict for DETR:
size mismatch for class_embed.weight: copying a param with shape torch.Size([6, 256]) from checkpoint, the shape in current model is torch.Size([92, 256]).
size mismatch for class_embed.bias: copying a param with shape torch.Size([6]) from checkpoint, the shape in current model is torch.Size([92]).

AttributeError: 'Tensor' object has no attribute 'tensors',您好,运行过程中此处报错,请问是什么原因呢?谢谢

D:\Python37\lib\site-packages\torchvision\models_utils.py:223: UserWarning: Arguments other than a weight enum or None for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing weights=None.
warnings.warn(msg)
Traceback (most recent call last):
File "d:/DETR/detr/Argument_test.py", line 14, in
ys = model(x)
File "D:\Python37\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
return forward_call(*input, **kwargs)
File "d:\DETR\detr\nets\backbone.py", line 173, in forward
xs = self0
File "D:\Python37\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
return forward_call(*input, **kwargs)
File "d:\DETR\detr\nets\backbone.py", line 141, in forward
xs = self.body(tensor_list.tensors)
AttributeError: 'Tensor' object has no attribute 'tensors'

预测框只会在x方向上精度差

导,我看不只有我,好多人反应预测结果有偏移,而且是一个方向,我是只在X方向上有偏移,随图片大小偏移程度不一,Y方向上精度不错,检查推理部分代码也没看出毛病来啊

NestedTensor的含义

您好,这个Detr中的NestedTensor非常令人费解,目前我这里碰到了一个问题,我这里把backbone替换掉了,但是由于backbone输出的特征是个Tensor,所以后续无法参与运算,想问下这个如何解决?

有很多个预测框

导儿~我用你的DETR代码训练,预测结果产生同一个目标出现很多个预测框,需要如何解决呀?这个是端到端的,不用nms,照道理应该不会这样吧

训练VOC数据集中的4个类,报错

L0F}GEC0ABM%P`0HI@ J{BC
B导过年好,我抽取了VOC数据集中的4个类,用这个数据集训练过其他检测器都没有问题,但您DETR报了这个错,请问是什么问题呀

训练map异常过低问题

Hi 大神, 在使用你这个版本的训练自己的数据集,发现map一直都很低。 同样的数据集在使用论文原版代码训练的时候map是正常的。
tmp
tmp_ori

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.