Comments (5)
1.应该是版本问题,将P4 = torch.cat([P4,P5_upsample],axis=1) 改为 P4 = torch.cat([P4,P5_upsample],1 应该可以解决)
2. 首先定义一个equla_flag = torch.Tensor(0).cuda() ,然后再 ciou = (1 - box_ciou( pred_boxes_for_ciou[torch.equal(mask,equla_flag)],这个估计是版本问题,tensor中没有bool这个属性了。
不知道上述解决方法是否存在bug,如果有,请告知,谢谢!
from yolov4-pytorch.
你好博主,非常感谢解答,问题已按照上述语句解决,即添加了:
equla_flag = torch.Tensor(0).cuda()
ciou = (1 - box_ciou( pred_boxes_for_ciou[torch.equal(mask,equla_flag)],
t_box[torch.equal(mask,equla_flag)]))*box_loss_scale[torch.equal(mask,equla_flag)]
同时还有2处:
1. ”nets\yolo_training.py", line 79, in box_ciou
center_distance = torch.sum(torch.pow((b1_xy - b2_xy), 2), axis=-1) #需要将axis去掉
2. “\nets\yolo_training.py", line 86, in box_ciou
enclose_diagonal = torch.sum(torch.pow(enclose_wh,2), axis=-1) #需要将axis去掉
请问博主,直接去掉会影响原代码意义吗?
from yolov4-pytorch.
这应该是版本问题吧,我忘了是高还是低的情况下是dim
from yolov4-pytorch.
1.应该是版本问题,将P4 = torch.cat([P4,P5_upsample],axis=1) 改为 P4 = torch.cat([P4,P5_upsample],1 应该可以解决)
2. 首先定义一个equla_flag = torch.Tensor(0).cuda() ,然后再 ciou = (1 - box_ciou( pred_boxes_for_ciou[torch.equal(mask,equla_flag)],这个估计是版本问题,tensor中没有bool这个属性了。不知道上述解决方法是否存在bug,如果有,请告知,谢谢!
equal_flag = torch.Tensor(0).cuda()会不会写错了?我查了PyTorch文档,self.bool() is equivalent to self.to(torch.bool),改成mask.to(torch.bool)会不会更合适?链接:https://pytorch.org/docs/stable/tensors.html
from yolov4-pytorch.
你好博主,非常感谢解答,问题已按照上述语句解决,即添加了:
equla_flag = torch.Tensor(0).cuda() ciou = (1 - box_ciou( pred_boxes_for_ciou[torch.equal(mask,equla_flag)], t_box[torch.equal(mask,equla_flag)]))*box_loss_scale[torch.equal(mask,equla_flag)]同时还有2处:
1. ”nets\yolo_training.py", line 79, in box_ciou
center_distance = torch.sum(torch.pow((b1_xy - b2_xy), 2), axis=-1) #需要将axis去掉
2. “\nets\yolo_training.py", line 86, in box_ciou
enclose_diagonal = torch.sum(torch.pow(enclose_wh,2), axis=-1) #需要将axis去掉
请问博主,直接去掉会影响原代码意义吗?
equla_flag写错了吧,应该得是1,否则的话loss_loc不会被启用。
from yolov4-pytorch.
Related Issues (20)
- 预训练模型问题 HOT 5
- 关于如何在MS coco测试集上验证自己模型的精度的问题
- opencv加载图像进行推理 HOT 5
- train_loss下降正常,val_loss不变,map一直很低,实际预测检测效果很差。 HOT 2
- train_loss下降,val_loss不变,map一直不变,自建数据集预测效果很差。 HOT 9
- 验证损失低于训练损失 HOT 2
- 替换YOLOv4主干网络为ghost或者mobilenetv2/3,检测精度直接为0或者零点几? HOT 14
- 你好,想问下更改预测框的颜色字体粗细大小 要如何更改啊 HOT 3
- 找不到dropblock,SAF等方法的人看这里 HOT 1
- loss计算太慢 HOT 7
- get_map很低
- please help me,why are the images of the validation set used during the training process? HOT 1
- 1
- AP很低 HOT 2
- 导,你的heatmap生成原理是什么?
- 请求 HOT 1
- 求教predict和get_map中detect_image的区别
- 默认参数没有调整,loss一直是nan HOT 2
- 计算量怎么查看? HOT 1
- File "mtrand, pyx", line 934, in numpy.random. mtrand. RandomState. choiceValueError: a cannot be empty unless no samples are taken
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
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.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from yolov4-pytorch.