Comments (7)
你可以重新克隆下我的代码,我已经把这个问题修复了,主要问题是在使用torch.tensor()这个方法(我怀疑是没有指认设备的原因),我直接把这个方法替换成对应常数了,例如:
torch.tensor(0)
替换成
0
from deep-learning-for-image-processing.
谢谢!问题已解决
from deep-learning-for-image-processing.
看了你的视频收获很多。弱弱问一句,faster-rcnn的视频什么时候更新?
from deep-learning-for-image-processing.
可能本周吧
from deep-learning-for-image-processing.
features = list(features.values())
# 计算每个预测特征层上的预测目标概率和bboxes regression参数
# objectness和pred_bbox_deltas都是list
objectness, pred_bbox_deltas = self.head(features)
# 生成一个batch图像的所有anchors信息,list(tensor)元素个数等于batch_size
anchors = self.anchor_generator(images, features)
关于这个地方我有两点不理解:(1)骨架网络学习到的特征图包含gt框的信息吗?(2)经过head函数对特征图进行33卷积操作,然后经过2个11卷积分别学习目标前景分数和边界框回归参数,但是这个时候原图上还没有生成anchor,网络是怎么学习的目标前景分数和边界框回归参数的?
from deep-learning-for-image-processing.
anchors假想是一直存在的,刚开始训练预测时你可以理解为网络瞎预测的(最开始网络并不知道anchors的存在),但计算损失时,由于是已anchors作为参考的,所以在反向传播误差时,网络才慢慢开始理解anchors的存在,并已anchors作为参照进行预测回归参数。
from deep-learning-for-image-processing.
讲的很明白,谢谢!
from deep-learning-for-image-processing.
Related Issues (20)
- mask rcnn lr_scheduler
- 我在使用vit模型的时候,加载vit_base_patch16_224_in21k()模型的预训练权重,显示和某些层和预训练权重不符合,怎么解决呢 HOT 1
- 为什么EfficientNetB7的depth_coefficient设置为3.1?
- KeyError: 'mask' --- gt_mask = instance['mask']
- 目录结构怎么变得呀大佬,pytorch_learning文件夹怎么没了啊 HOT 1
- 训练自己数据集检测时出现画图颜色的错误 HOT 1
- Vit的flops使用方法即将在未来的 PyTorch版本中删除 HOT 2
- 使用swin-transformer里的predict.py和官方swin_tiny_patch4_window7_224.pth模型预测没结果; HOT 2
- yolov3_spp运行报错,运行到datasets.py中line259报错:
- yolov3_spp运行报错,运行到datasets.py中line259报错: HOT 1
- PPT放一个地方不好吗? 一个个分开,整理也够累的 HOT 2
- FileNotFoundError: Found no valid file for the classes roses, sunflowers, tulips. Supported extensions are: .jpg, .jpeg, .png, .ppm, .bmp, .pgm, .tif, .tiff, .webp
- 在torch >= 2.0中移除了名为“torch._six”的模块 coco_eval.py文件可能需要一些修改 HOT 2
- 请问大家这是我训练10个epoch后的结果,可能是些什么原因出错了 HOT 1
- yolov3_spp的导入包错误
- 你好作者,关于EffiectentV2模型pytorch版本,预训练权重使用的是什么数据集进行预训练的呢?
- 针对于自己 的模型生成Grad-Cam
- 不理解这里的架构,是有问题吗
- swin_transformer export onnx : Process finished with exit code 136 (interrupted by signal 8: SIGFPE)
- FCN网络代码中,是否有pool3,pool4,pool5的特征融合过程呢
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 deep-learning-for-image-processing.