Comments (10)
I want to train this code for dataset, following as
$ python tools/train.py --data_root /home/my_com/dataset/KITTI/ --batch_size 4
when first epoch is done, I got error
Traceback (most recent call last): File "tools/train.py", line 164, in main() File "tools/train.py", line 157, in main val_loader File "/home/my_com/virtualenv/JMODT/jmodt/utils/train_utils.py", line 198, in train prev_val_loss = val_loss_epoch
Can I get some solution from this problem?
Thanks.
I get the same error. Is there any progress?
from jmodt.
I want to train this code for dataset, following as
$ python tools/train.py --data_root /home/my_com/dataset/KITTI/ --batch_size 4
when first epoch is done, I got error
Traceback (most recent call last): File "tools/train.py", line 164, in main() File "tools/train.py", line 157, in main val_loader File "/home/my_com/virtualenv/JMODT/jmodt/utils/train_utils.py", line 198, in train prev_val_loss = val_loss_epoch
Can I get some solution from this problem?
Thanks.I get the same error. Is there any progress?
I get the same error. Is there any progress? I means how to get the sample2frame.txt & seq2sample.txt in TESTING file
from jmodt.
I have not noticed this problem... The script kitti_converter.py just creates TRAINING file. Maybe we have to create TESTING file by imitating the kitti_converter.py.
@Lemon-L7
from jmodt.
yeap,I check the files, if author‘s code didn't has any trouble, we should create TESTING file, like he sets in his constructor. @Bruce-Si
from jmodt.
yeap,I check the files, if author‘s code didn't has any trouble, we should create TESTING file, like he sets in his constructor. @Bruce-Si
Hello, I also encountered the same problem, have you solved it? How is the testing file created?
from jmodt.
我想为数据集训练此代码,如下所示
$ python 工具/train.py --data_root /home/my_com/dataset/KITTI/ --batch_size 4
当第一个时代完成时,我得到了错误
回溯(最后一次调用): 文件“tools/train.py”,第 164 行,在 main() 文件“tools/train.py”,第 157 行,在 main val_loader 文件“/home/my_com/virtualenv/JMODT/ jmodt/utils/train_utils.py",第 198 行,在火车 prev_val_loss = val_loss_epoch
我可以从这个问题中得到一些解决方案吗?
谢谢。
I have the same problem ,have you solved it? @Kemo-Huang @minho8849
from jmodt.
After I assigned an initial value to "val_loss_epoch", the network can be trained, but there is another problem, the "best_model" will not be updated after the first epoch is trained.
from jmodt.
@Kemo-Huang
Excuse me,I meet same problems.
No.1 ”UnboundLocalError: local variable 'val_loss_epoch' referenced before assignment“;
For this problem I change some code then the problem fixed,but it comes new problem that same with this.
No.2 “best_model.path” is not update.
对不起,我也遇到同样的问题。
第1条问 “UnboundLocalError:赋值前引用的局部变量‘val_loss_epoch’”;对于这个问题,我更改了一些代码,然后问题得到了解决,但随之而来的是新问题。
第2条 “best_model.path”未更新。
from jmodt.
add the following line for solution
def train(self, start_it, start_epoch, n_epochs, train_loader, val_loader=None, stop_thres=5):
eval_frequency = self.eval_frequency if self.eval_frequency > 0 else 1
global val_loss_epoch
global prev_train_loss
global prev_val_loss
in the bottom
else:
prev_train_loss = train_loss_epoch
prev_val_loss = val_loss_epoch
val_loss_epoch =1
if val_loss_epoch < min_val_loss:
min_val_loss = val_loss_epoch
from jmodt.
Any solution for best_model.path???
from jmodt.
Related Issues (15)
- Link to the paper HOT 1
- loss is zero HOT 20
- The parameters for Affinity Compution and data_association.
- About the Train Seq and Val Seq. HOT 1
- Feat Visualization Issues HOT 2
- error: protobuf 3.19.6 is installed but protobuf>=4.21.5 is required by {'ortools'}
- Quite a small sized images (.png) in the jmodt folder for visualization.
- how to use the dataset HOT 1
- Multiple GPUs for training HOT 3
- The problem of finetune the model jmodt.pth HOT 1
- Hello, where can I find these txt files? Or how do I need to create it? thanks!! HOT 2
- How to generate the three files test.txt, sample2frame.txt and seq2sample.txt? HOT 2
- ‘best_model.path’ HOT 5
- val_loss_epoch HOT 2
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 jmodt.