Comments (2)
Hello, thanks for your questions. May I kindly ask what's the learning rate you used in batch_size=12?
from transunet.
The following is the start message
(base) user@pc1:~/project_TransUNet/TransUNet$ python train.py --dataset owndataset --vit_name R50-ViT-B_16 --batch_size 12 --max_iterations 1000 --max_epochs 350
Namespace(base_lr=0.005, batch_size=12, dataset='Owndataset', deterministic=1, exp='TU_Owndataset224', img_size=224, is_pretrain=True, list_dir='./lists/lists_Owndataset', max_epochs=350, max_iterations=1000, n_gpu=1, n_skip=3, num_classes=2, root_path='../data/Owndataset/train_npz', seed=1234, vit_name='R50-ViT-B_16', vit_patches_size=16)
The length of train set is: 234
20 iterations per epoch. 7000 max iterations
0%| | 0/350 [00:00<?, ?it/s]iteration 1 : loss : 0.541960, loss_ce: 0.527893
I realized that I changed the train.py file in order to match the test.py
I added the following lines:
< if args.batch_size != 24 and args.batch_size % 6 == 0:
< args.base_lr *= args.batch_size / 24
=> Maybe it would be better if you didn't have to specify all the individual parameters for training again during the test, but only the checkpoint directory for the specific model values? My starting point was that due to the different LR treatment, the same command line arguments did not allow me to run a training and then a test.
from transunet.
Related Issues (20)
- "ZeroDivisionError: integer division or modulo by zero" when vit_patches_size=8 HOT 3
- Need R50+ViT-B_16 rather than R50-ViT-B_16! HOT 1
- 当我在运行TransUNet-main的train.py时出现错误:KeyError: 'Transformer/encoderblock_0/Multi5HeadDotProductAttention_1/query/kernel is not a file in the archive' 这是在我进行KeyError: 'Transformer/encoderblock_0/MultiHeadDotProductAttention_1/query\\kernel is not a file in the archive'后的更改出现的错误,csdn说这是os.path.join 合并路径的时候出现的问题,更改后仍然出现以上错误 HOT 4
- Even if we fix the seed, the results change for each training. HOT 3
- asking for you help
- ACDC dataset 100 cases of data HOT 1
- Training for three-channel dataset
- Need R50+ViT-L_16 pretrained model rather than R50+ViT-L_32 HOT 1
- 导入包报错,文件夹重名导致的坑 HOT 2
- Data preprocessing HOT 2
- Training with different image size HOT 1
- Is the Synapse multi-organ segmentation dataset experimental result obtained from is the 20 samples official test set?
- change patch_size during test
- PreActBottleneck
- Training performance issues on small-sized targets
- The issue arises from the absence of the "lists_Synapse" folder.
- ACDC dataset HOT 1
- About the solution of problems like "have 3 channels, but got 1000 channels instead"
- Error in test file
- Where is the CNN that they claim in the paper? 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 transunet.