Comments (8)
doomx1
commented on August 13, 2024
2
val_loss has decreased quite normally; it's just a problem with dataset.py loading data.
At 2023-07-20 15:42:41, "Jiacheng Ruan" ***@***.***> wrote:
I may have encountered some issues while simplifying the code. I will check it as soon as possible. Below is the log from my local training.
2023-03-05 11:36:01 - flops: 0.072096256, params: 0.045806, Total params: : 0.0534
2023-03-05 11:36:05 - train: epoch 1, iter:0, loss: 5.5605, lr: 0.001
2023-03-05 11:36:12 - train: epoch 1, iter:20, loss: 3.1776, lr: 0.001
2023-03-05 11:36:19 - train: epoch 1, iter:40, loss: 2.6720, lr: 0.001
2023-03-05 11:36:27 - train: epoch 1, iter:60, loss: 2.3416, lr: 0.001
2023-03-05 11:36:34 - train: epoch 1, iter:80, loss: 2.1528, lr: 0.001
2023-03-05 11:36:43 - train: epoch 1, iter:100, loss: 2.0301, lr: 0.001
2023-03-05 11:36:54 - train: epoch 1, iter:120, loss: 1.9409, lr: 0.001
2023-03-05 11:37:04 - train: epoch 1, iter:140, loss: 1.8605, lr: 0.001
2023-03-05 11:37:17 - train: epoch 1, iter:160, loss: 1.7968, lr: 0.001
2023-03-05 11:37:28 - train: epoch 1, iter:180, loss: 1.7363, lr: 0.001
2023-03-05 11:38:09 - val epoch: 1, loss: 1.5486
2023-03-05 11:38:10 - train: epoch 2, iter:0, loss: 2.4030, lr: 0.0009990232305719944
2023-03-05 11:38:21 - train: epoch 2, iter:20, loss: 1.2788, lr: 0.0009990232305719944
2023-03-05 11:38:32 - train: epoch 2, iter:40, loss: 1.2590, lr: 0.0009990232305719944
2023-03-05 11:38:43 - train: epoch 2, iter:60, loss: 1.2346, lr: 0.0009990232305719944
2023-03-05 11:38:54 - train: epoch 2, iter:80, loss: 1.2320, lr: 0.0009990232305719944
2023-03-05 11:39:04 - train: epoch 2, iter:100, loss: 1.1950, lr: 0.0009990232305719944
2023-03-05 11:39:15 - train: epoch 2, iter:120, loss: 1.1730, lr: 0.0009990232305719944
2023-03-05 11:39:27 - train: epoch 2, iter:140, loss: 1.1663, lr: 0.0009990232305719944
2023-03-05 11:39:38 - train: epoch 2, iter:160, loss: 1.1528, lr: 0.0009990232305719944
2023-03-05 11:39:50 - train: epoch 2, iter:180, loss: 1.1635, lr: 0.0009990232305719944
2023-03-05 11:40:35 - val epoch: 2, loss: 1.2181
2023-03-05 11:40:36 - train: epoch 3, iter:0, loss: 0.9906, lr: 0.0009960967771506664
2023-03-05 11:40:46 - train: epoch 3, iter:20, loss: 1.1580, lr: 0.0009960967771506664
2023-03-05 11:40:57 - train: epoch 3, iter:40, loss: 1.1086, lr: 0.0009960967771506664
2023-03-05 11:41:07 - train: epoch 3, iter:60, loss: 1.0769, lr: 0.0009960967771506664
2023-03-05 11:41:16 - train: epoch 3, iter:80, loss: 1.0212, lr: 0.0009960967771506664
2023-03-05 11:41:27 - train: epoch 3, iter:100, loss: 1.0082, lr: 0.0009960967771506664
2023-03-05 11:41:37 - train: epoch 3, iter:120, loss: 0.9982, lr: 0.0009960967771506664
2023-03-05 11:41:47 - train: epoch 3, iter:140, loss: 0.9815, lr: 0.0009960967771506664
2023-03-05 11:41:58 - train: epoch 3, iter:160, loss: 0.9774, lr: 0.0009960967771506664
2023-03-05 11:42:08 - train: epoch 3, iter:180, loss: 0.9918, lr: 0.0009960967771506664
2023-03-05 11:42:53 - val epoch: 3, loss: 1.1650
......
2023-03-05 23:33:11 - train: epoch 298, iter:0, loss: 0.3359, lr: 0.0009912321891107007
2023-03-05 23:33:22 - train: epoch 298, iter:20, loss: 0.4601, lr: 0.0009912321891107007
2023-03-05 23:33:33 - train: epoch 298, iter:40, loss: 0.4977, lr: 0.0009912321891107007
2023-03-05 23:33:43 - train: epoch 298, iter:60, loss: 0.4977, lr: 0.0009912321891107007
2023-03-05 23:33:53 - train: epoch 298, iter:80, loss: 0.4880, lr: 0.0009912321891107007
2023-03-05 23:34:05 - train: epoch 298, iter:100, loss: 0.4792, lr: 0.0009912321891107007
2023-03-05 23:34:15 - train: epoch 298, iter:120, loss: 0.4688, lr: 0.0009912321891107007
2023-03-05 23:34:25 - train: epoch 298, iter:140, loss: 0.4707, lr: 0.0009912321891107007
2023-03-05 23:34:36 - train: epoch 298, iter:160, loss: 0.4735, lr: 0.0009912321891107007
2023-03-05 23:34:47 - train: epoch 298, iter:180, loss: 0.4699, lr: 0.0009912321891107007
2023-03-05 23:35:30 - val epoch: 298, loss: 0.8062
2023-03-05 23:35:31 - train: epoch 299, iter:0, loss: 0.5131, lr: 0.0009960967771506662
2023-03-05 23:35:42 - train: epoch 299, iter:20, loss: 0.4751, lr: 0.0009960967771506662
2023-03-05 23:35:52 - train: epoch 299, iter:40, loss: 0.4622, lr: 0.0009960967771506662
2023-03-05 23:36:03 - train: epoch 299, iter:60, loss: 0.4449, lr: 0.0009960967771506662
2023-03-05 23:36:13 - train: epoch 299, iter:80, loss: 0.4550, lr: 0.0009960967771506662
2023-03-05 23:36:23 - train: epoch 299, iter:100, loss: 0.4477, lr: 0.0009960967771506662
2023-03-05 23:36:33 - train: epoch 299, iter:120, loss: 0.4465, lr: 0.0009960967771506662
2023-03-05 23:36:42 - train: epoch 299, iter:140, loss: 0.4537, lr: 0.0009960967771506662
2023-03-05 23:36:52 - train: epoch 299, iter:160, loss: 0.4554, lr: 0.0009960967771506662
2023-03-05 23:37:02 - train: epoch 299, iter:180, loss: 0.4635, lr: 0.0009960967771506662
2023-03-05 23:37:47 - val epoch: 299, loss: 0.7665
2023-03-05 23:37:48 - train: epoch 300, iter:0, loss: 0.7507, lr: 0.000999023230571994
2023-03-05 23:37:59 - train: epoch 300, iter:20, loss: 0.4676, lr: 0.000999023230571994
2023-03-05 23:38:10 - train: epoch 300, iter:40, loss: 0.4551, lr: 0.000999023230571994
2023-03-05 23:38:20 - train: epoch 300, iter:60, loss: 0.4597, lr: 0.000999023230571994
2023-03-05 23:38:30 - train: epoch 300, iter:80, loss: 0.4990, lr: 0.000999023230571994
2023-03-05 23:38:40 - train: epoch 300, iter:100, loss: 0.5389, lr: 0.000999023230571994
2023-03-05 23:38:50 - train: epoch 300, iter:120, loss: 0.5292, lr: 0.000999023230571994
2023-03-05 23:38:59 - train: epoch 300, iter:140, loss: 0.5175, lr: 0.000999023230571994
2023-03-05 23:39:09 - train: epoch 300, iter:160, loss: 0.5094, lr: 0.000999023230571994
2023-03-05 23:39:20 - train: epoch 300, iter:180, loss: 0.5005, lr: 0.000999023230571994
2023-03-05 23:40:11 - val epoch: 300, loss: 0.7782, miou: 0.7897381571263946, f1_or_dsc: 0.8825180979483602, accuracy: 0.9617934945913461, specificity: 0.9828152506790888, sensitivity: 0.8572381350106618, confusion_matrix: [[34857880 609498]
[ 1018038 6112984]]
2023-03-05 23:40:59 - test of best model, loss: 0.7001,miou: 0.7990738105577411, f1_or_dsc: 0.8883168726801883, accuracy: 0.9631241548978365, specificity: 0.9806291573061872, sensitivity: 0.8760599813042226, confusion_matrix: [[34780345 687033]
[ 883819 6247203]]
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you commented.Message ID: ***@***.***>
from ege-unet.
JCruan519
commented on August 13, 2024
Hi, do you utilize the data we provided in the readme file?
from ege-unet.
doomx1
commented on August 13, 2024
I have also encountered this situation. I used the data connection provided in the official readme document and downloaded it for training.
from ege-unet.
JCruan519
commented on August 13, 2024
I may have encountered some issues while simplifying the code. I will check it as soon as possible. Below is the log from my local training.
2023-03-05 11:36:01 - flops: 0.072096256, params: 0.045806, Total params: : 0.0534
2023-03-05 11:36:05 - train: epoch 1, iter:0, loss: 5.5605, lr: 0.001
2023-03-05 11:36:12 - train: epoch 1, iter:20, loss: 3.1776, lr: 0.001
2023-03-05 11:36:19 - train: epoch 1, iter:40, loss: 2.6720, lr: 0.001
2023-03-05 11:36:27 - train: epoch 1, iter:60, loss: 2.3416, lr: 0.001
2023-03-05 11:36:34 - train: epoch 1, iter:80, loss: 2.1528, lr: 0.001
2023-03-05 11:36:43 - train: epoch 1, iter:100, loss: 2.0301, lr: 0.001
2023-03-05 11:36:54 - train: epoch 1, iter:120, loss: 1.9409, lr: 0.001
2023-03-05 11:37:04 - train: epoch 1, iter:140, loss: 1.8605, lr: 0.001
2023-03-05 11:37:17 - train: epoch 1, iter:160, loss: 1.7968, lr: 0.001
2023-03-05 11:37:28 - train: epoch 1, iter:180, loss: 1.7363, lr: 0.001
2023-03-05 11:38:09 - val epoch: 1, loss: 1.5486
2023-03-05 11:38:10 - train: epoch 2, iter:0, loss: 2.4030, lr: 0.0009990232305719944
2023-03-05 11:38:21 - train: epoch 2, iter:20, loss: 1.2788, lr: 0.0009990232305719944
2023-03-05 11:38:32 - train: epoch 2, iter:40, loss: 1.2590, lr: 0.0009990232305719944
2023-03-05 11:38:43 - train: epoch 2, iter:60, loss: 1.2346, lr: 0.0009990232305719944
2023-03-05 11:38:54 - train: epoch 2, iter:80, loss: 1.2320, lr: 0.0009990232305719944
2023-03-05 11:39:04 - train: epoch 2, iter:100, loss: 1.1950, lr: 0.0009990232305719944
2023-03-05 11:39:15 - train: epoch 2, iter:120, loss: 1.1730, lr: 0.0009990232305719944
2023-03-05 11:39:27 - train: epoch 2, iter:140, loss: 1.1663, lr: 0.0009990232305719944
2023-03-05 11:39:38 - train: epoch 2, iter:160, loss: 1.1528, lr: 0.0009990232305719944
2023-03-05 11:39:50 - train: epoch 2, iter:180, loss: 1.1635, lr: 0.0009990232305719944
2023-03-05 11:40:35 - val epoch: 2, loss: 1.2181
2023-03-05 11:40:36 - train: epoch 3, iter:0, loss: 0.9906, lr: 0.0009960967771506664
2023-03-05 11:40:46 - train: epoch 3, iter:20, loss: 1.1580, lr: 0.0009960967771506664
2023-03-05 11:40:57 - train: epoch 3, iter:40, loss: 1.1086, lr: 0.0009960967771506664
2023-03-05 11:41:07 - train: epoch 3, iter:60, loss: 1.0769, lr: 0.0009960967771506664
2023-03-05 11:41:16 - train: epoch 3, iter:80, loss: 1.0212, lr: 0.0009960967771506664
2023-03-05 11:41:27 - train: epoch 3, iter:100, loss: 1.0082, lr: 0.0009960967771506664
2023-03-05 11:41:37 - train: epoch 3, iter:120, loss: 0.9982, lr: 0.0009960967771506664
2023-03-05 11:41:47 - train: epoch 3, iter:140, loss: 0.9815, lr: 0.0009960967771506664
2023-03-05 11:41:58 - train: epoch 3, iter:160, loss: 0.9774, lr: 0.0009960967771506664
2023-03-05 11:42:08 - train: epoch 3, iter:180, loss: 0.9918, lr: 0.0009960967771506664
2023-03-05 11:42:53 - val epoch: 3, loss: 1.1650
......
2023-03-05 23:33:11 - train: epoch 298, iter:0, loss: 0.3359, lr: 0.0009912321891107007
2023-03-05 23:33:22 - train: epoch 298, iter:20, loss: 0.4601, lr: 0.0009912321891107007
2023-03-05 23:33:33 - train: epoch 298, iter:40, loss: 0.4977, lr: 0.0009912321891107007
2023-03-05 23:33:43 - train: epoch 298, iter:60, loss: 0.4977, lr: 0.0009912321891107007
2023-03-05 23:33:53 - train: epoch 298, iter:80, loss: 0.4880, lr: 0.0009912321891107007
2023-03-05 23:34:05 - train: epoch 298, iter:100, loss: 0.4792, lr: 0.0009912321891107007
2023-03-05 23:34:15 - train: epoch 298, iter:120, loss: 0.4688, lr: 0.0009912321891107007
2023-03-05 23:34:25 - train: epoch 298, iter:140, loss: 0.4707, lr: 0.0009912321891107007
2023-03-05 23:34:36 - train: epoch 298, iter:160, loss: 0.4735, lr: 0.0009912321891107007
2023-03-05 23:34:47 - train: epoch 298, iter:180, loss: 0.4699, lr: 0.0009912321891107007
2023-03-05 23:35:30 - val epoch: 298, loss: 0.8062
2023-03-05 23:35:31 - train: epoch 299, iter:0, loss: 0.5131, lr: 0.0009960967771506662
2023-03-05 23:35:42 - train: epoch 299, iter:20, loss: 0.4751, lr: 0.0009960967771506662
2023-03-05 23:35:52 - train: epoch 299, iter:40, loss: 0.4622, lr: 0.0009960967771506662
2023-03-05 23:36:03 - train: epoch 299, iter:60, loss: 0.4449, lr: 0.0009960967771506662
2023-03-05 23:36:13 - train: epoch 299, iter:80, loss: 0.4550, lr: 0.0009960967771506662
2023-03-05 23:36:23 - train: epoch 299, iter:100, loss: 0.4477, lr: 0.0009960967771506662
2023-03-05 23:36:33 - train: epoch 299, iter:120, loss: 0.4465, lr: 0.0009960967771506662
2023-03-05 23:36:42 - train: epoch 299, iter:140, loss: 0.4537, lr: 0.0009960967771506662
2023-03-05 23:36:52 - train: epoch 299, iter:160, loss: 0.4554, lr: 0.0009960967771506662
2023-03-05 23:37:02 - train: epoch 299, iter:180, loss: 0.4635, lr: 0.0009960967771506662
2023-03-05 23:37:47 - val epoch: 299, loss: 0.7665
2023-03-05 23:37:48 - train: epoch 300, iter:0, loss: 0.7507, lr: 0.000999023230571994
2023-03-05 23:37:59 - train: epoch 300, iter:20, loss: 0.4676, lr: 0.000999023230571994
2023-03-05 23:38:10 - train: epoch 300, iter:40, loss: 0.4551, lr: 0.000999023230571994
2023-03-05 23:38:20 - train: epoch 300, iter:60, loss: 0.4597, lr: 0.000999023230571994
2023-03-05 23:38:30 - train: epoch 300, iter:80, loss: 0.4990, lr: 0.000999023230571994
2023-03-05 23:38:40 - train: epoch 300, iter:100, loss: 0.5389, lr: 0.000999023230571994
2023-03-05 23:38:50 - train: epoch 300, iter:120, loss: 0.5292, lr: 0.000999023230571994
2023-03-05 23:38:59 - train: epoch 300, iter:140, loss: 0.5175, lr: 0.000999023230571994
2023-03-05 23:39:09 - train: epoch 300, iter:160, loss: 0.5094, lr: 0.000999023230571994
2023-03-05 23:39:20 - train: epoch 300, iter:180, loss: 0.5005, lr: 0.000999023230571994
2023-03-05 23:40:11 - val epoch: 300, loss: 0.7782, miou: 0.7897381571263946, f1_or_dsc: 0.8825180979483602, accuracy: 0.9617934945913461, specificity: 0.9828152506790888, sensitivity: 0.8572381350106618, confusion_matrix: [[34857880 609498]
[ 1018038 6112984]]
2023-03-05 23:40:59 - test of best model, loss: 0.7001,miou: 0.7990738105577411, f1_or_dsc: 0.8883168726801883, accuracy: 0.9631241548978365, specificity: 0.9806291573061872, sensitivity: 0.8760599813042226, confusion_matrix: [[34780345 687033]
[ 883819 6247203]]
from ege-unet.
doomx1
commented on August 13, 2024
yes,Your dataset.py code should add sorting to the list, otherwise it will cause the image to not match the corresponding mask. I have already modified the code.
from ege-unet.
doomx1
commented on August 13, 2024
from ege-unet.
JCruan519
commented on August 13, 2024
@doomx1
Thank you for identifying the issue. The code for the dataset has been updated.
from ege-unet.
zhoudong9630
commented on August 13, 2024
Thank you for updating! I close the issue. @JCruan519 @doomx1
from ege-unet.
Related Issues (20)
- IndexError: index 1 is out of bounds for axis 1 with size 1 HOT 1
- hello, can you upload both the trained weights or the predicted results of EGE-UNet and MALUNet ? It may not cost your extra time. Becasue we will compare your results at qualitative and quantitative aspects. Thanks!
- About Dataset
- Can you improve the code for the test? Thank you so much！ HOT 7
- Trainning in other datasets and deploy HOT 13
- gt_ds layer
- 训练耗时 HOT 2
- 对比实验数据偏差大
- The mask in the released dataset is Not binary value.
- model_cfg ------ 'gt_ds': False----------error
- 数据结果不对
- 请问能将对比的模型的代码也开源一下吗？
- gt_ds设置为False报错
- myNormalize class
- 论文提到DW深度可分离卷积，但在代码中却使用普通卷积
- Input size
- 参数数据不对 HOT 6
- the best checkpoint
- ValueError: height and width must be > 0 HOT 1
- 模型转换和优化的错误
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 ege-unet.