Comments (7)
Hi, thanks for your work, I have some problem in training.
I find that in TracKit/experiments/train/Ocean.yaml this model train for 50 epoch, but in the paper training for 20 epoch, and the learing rate end_lr also seems for alexnet training.
Another problem is that I only have one 2080ti gpu, will it influence the results a lot? Or should I adjust some parameters.
Thanks.
Hi. 1) The full training is performed for 50 epochs, as detailed in Sec.5.1
in the paper. The Sec.5.3
provides the abolition for training 20 epochs. When conducting your idea on this framework, you could first train 20 epoch for fast evaluation. After getting a good result, then do the full train. 2) One GPU may decrease the performance since the batch size is much smaller than 256. You could try to increase the batch size.
from trackit.
hello, 在数据集一样,用代码中提供的设置文件,用八卡训练的效果。并不能达到论文中的效果,可能是什么原因呢? 相差还比较大
from trackit.
hello, 在数据集一样,用代码中提供的设置文件,用八卡训练的效果。并不能达到论文中的效果,可能是什么原因呢? 相差还比较大
Hi, 请问所有配置都一样么?可以展示下你的log么?另外你epoch test后结果是多少(VOT19)?以及调参后结果是多少?
from trackit.
hello, 在数据集一样,用代码中提供的设置文件,用八卡训练的效果。并不能达到论文中的效果,可能是什么原因呢? 相差还比较大
Hi, 请问所有配置都一样么?可以展示下你的log么?另外你epoch test后结果是多少(VOT19)?以及调参后结果是多少?
配置就用的 experiments/train/Ocean.yaml, 在VOT2018上的结果是 EAO 0.357 (这是没有 tune 参数的结果)
from trackit.
hello, 在数据集一样,用代码中提供的设置文件,用八卡训练的效果。并不能达到论文中的效果,可能是什么原因呢? 相差还比较大
Hi, 请问所有配置都一样么?可以展示下你的log么?另外你epoch test后结果是多少(VOT19)?以及调参后结果是多少?
配置就用的 experiments/train/Ocean.yaml, 在VOT2018上的结果是 EAO 0.357
1)如果方便的话麻烦传给我一份train/epoch test/tune的log,我帮忙check下,如果github不能传的话请发我邮箱[email protected] 2) 请问可以同时反馈一下VOT19的结果么?
from trackit.
hello, 在数据集一样,用代码中提供的设置文件,用八卡训练的效果。并不能达到论文中的效果,可能是什么原因呢? 相差还比较大
Hi, 请问所有配置都一样么?可以展示下你的log么?另外你epoch test后结果是多少(VOT19)?以及调参后结果是多少?
配置就用的 experiments/train/Ocean.yaml, 在VOT2018上的结果是 EAO 0.357
1)如果方便的话麻烦传给我一份train/epoch test/tune的log,我帮忙check下,如果github不能传的话请发我邮箱[email protected] 2) 请问可以同时反馈一下VOT19的结果么?
行 我找时间整理下, 我觉着问题是不是出现在 bn上, 我粗略看了下好像没有用synbn; EAO 0.357是没有 tune para的结果
from trackit.
hello, 在数据集一样,用代码中提供的设置文件,用八卡训练的效果。并不能达到论文中的效果,可能是什么原因呢? 相差还比较大
Hi, 请问所有配置都一样么?可以展示下你的log么?另外你epoch test后结果是多少(VOT19)?以及调参后结果是多少?
配置就用的 experiments/train/Ocean.yaml, 在VOT2018上的结果是 EAO 0.357
1)如果方便的话麻烦传给我一份train/epoch test/tune的log,我帮忙check下,如果github不能传的话请发我邮箱[email protected] 2) 请问可以同时反馈一下VOT19的结果么?
行 我找时间整理下, 我觉着问题是不是出现在 bn上, 我粗略看了下好像没有用synbn; EAO 0.357是没有 tune para的结果
应该不是,我之前复现波动没有这么大,也麻烦你顺便测下19,因为18比较容易过拟合,19和20相对稳定,用来测试可能更容易反映tracker性能(个人经验仅供参考)。也麻烦你整理完邮箱发我下,我也找时间帮你check。
from trackit.
Related Issues (20)
- Ocean模型的pre-trained model 和 数据对应的json文件链接失效 HOT 2
- Could u provide the result file of Ocean-offline? (original link is invalid.) HOT 2
- OTB50、UAV123一些算法的txt测试结果 HOT 2
- 在imageNet上预训练的backbone没法下载
- any possible convert ocean pytorch model to onnx, then to TensorRT?
- Row Results download link is not working
- same problem> Hello and thanks for sharing your work. I want to use your code but I do not have access to pre-trained models like this google drive link [PyTorch model](https://drive.google.com/drive/folders/1XU5wmyC7MsI6C_9Lv-UH1mwDIh57FFf8?usp=sharing). How to access to the models??
- Dataset problem in Ocean
- 关于got10k数据集的使用
- ocean在Google driver中存储的.pth文件几乎全部失效了 HOT 4
- 预训练权重下载链接失效 HOT 1
- 训练时backward出错
- 使用y2b数据集训练时loss nan
- Unable to download pretrained PyTorch model HOT 1
- Raw results
- 请问这个label为啥以 resize之前的图生成的,不是应该对齐到模型输入255*255的图吗?
- Is it useful to have only one convolutional layer in the feature alignment module ? HOT 1
- loss decreasing but model is not working better
- raw result链接失效 HOT 1
- 单卡训练问题 HOT 1
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 trackit.