Comments (2)
It seems that this problem is a pytorch issue when running on windows. You can reference: pytorch/pytorch#5858.
from efficient-computing.
It seems that this problem is a pytorch issue when running on windows. You can reference: pytorch/pytorch#5858.
==================
In Win10 environment, add the following code to solve the problem, thank you! In addition, you need to add a global acc_best。Thank you!
===============
if name == 'main':
main()
"D:\Program Files\Python368\python.exe" B:/PyTorch/DAFL/DAFL-train.py
[Epoch 0/200] [loss_oh: 0.323446] [loss_ie: -0.723433] [loss_a: -1.377360] [loss_kd: 1.624475]
Test Avg. Loss: 0.014621, Accuracy: 0.711200
acc 0.7112 acc_best 0
[Epoch 1/200] [loss_oh: 0.398816] [loss_ie: -0.994161] [loss_a: -1.477517] [loss_kd: 0.681656]
Test Avg. Loss: 0.011073, Accuracy: 0.795800
acc 0.7958 acc_best 0.7112
[Epoch 2/200] [loss_oh: 0.694914] [loss_ie: -0.942158] [loss_a: -1.655259] [loss_kd: 0.491626]
Test Avg. Loss: 0.014511, Accuracy: 0.767200
acc 0.7672 acc_best 0.7958
[Epoch 3/200] [loss_oh: 0.372430] [loss_ie: -0.973961] [loss_a: -1.844167] [loss_kd: 0.325282]
Test Avg. Loss: 0.008011, Accuracy: 0.849000
acc 0.849 acc_best 0.7958
[Epoch 4/200] [loss_oh: 0.338971] [loss_ie: -0.982305] [loss_a: -1.716944] [loss_kd: 0.316894]
Test Avg. Loss: 0.006166, Accuracy: 0.877000
acc 0.877 acc_best 0.849
[Epoch 5/200] [loss_oh: 0.322520] [loss_ie: -0.983168] [loss_a: -1.626730] [loss_kd: 0.278169]
Test Avg. Loss: 0.005701, Accuracy: 0.884200
acc 0.8842 acc_best 0.877
[Epoch 6/200] [loss_oh: 0.296399] [loss_ie: -0.980377] [loss_a: -1.993171] [loss_kd: 0.276820]
Test Avg. Loss: 0.005980, Accuracy: 0.880800
acc 0.8808 acc_best 0.8842
[Epoch 7/200] [loss_oh: 0.310579] [loss_ie: -0.989021] [loss_a: -1.786998] [loss_kd: 0.218293]
Test Avg. Loss: 0.004707, Accuracy: 0.903100
acc 0.9031 acc_best 0.8842
[Epoch 8/200] [loss_oh: 0.324671] [loss_ie: -0.970958] [loss_a: -1.733145] [loss_kd: 0.288907]
Test Avg. Loss: 0.005629, Accuracy: 0.881200
acc 0.8812 acc_best 0.9031
[Epoch 9/200] [loss_oh: 0.370372] [loss_ie: -0.934299] [loss_a: -1.562675] [loss_kd: 0.252697]
Test Avg. Loss: 0.018975, Accuracy: 0.697800
acc 0.6978 acc_best 0.9031
[Epoch 10/200] [loss_oh: 1.752401] [loss_ie: -0.963753] [loss_a: -0.129881] [loss_kd: 0.000000]
Test Avg. Loss: 0.018973, Accuracy: 0.698000
acc 0.698 acc_best 0.9031
[Epoch 11/200] [loss_oh: 1.752401] [loss_ie: -0.963753] [loss_a: -0.129881] [loss_kd: 0.000000]
Test Avg. Loss: 0.018973, Accuracy: 0.698000
acc 0.698 acc_best 0.9031
[Epoch 12/200] [loss_oh: 1.752401] [loss_ie: -0.963753] [loss_a: -0.129881] [loss_kd: 0.000000]
Test Avg. Loss: 0.018973, Accuracy: 0.698000
acc 0.698 acc_best 0.9031
[Epoch 13/200] [loss_oh: 1.752401] [loss_ie: -0.963753] [loss_a: -0.129881] [loss_kd: 0.000000]
Test Avg. Loss: 0.018973, Accuracy: 0.698000
acc 0.698 acc_best 0.9031
[Epoch 14/200] [loss_oh: 1.752401] [loss_ie: -0.963753] [loss_a: -0.129881] [loss_kd: 0.000000]
Test Avg. Loss: 0.018973, Accuracy: 0.698000
acc 0.698 acc_best 0.9031
[Epoch 15/200] [loss_oh: 1.752401] [loss_ie: -0.963753] [loss_a: -0.129881] [loss_kd: 0.000000]
Test Avg. Loss: 0.018973, Accuracy: 0.698000
acc 0.698 acc_best 0.9031
[Epoch 16/200] [loss_oh: 1.752401] [loss_ie: -0.963753] [loss_a: -0.129881] [loss_kd: 0.000000]
Test Avg. Loss: 0.018973, Accuracy: 0.698000
acc 0.698 acc_best 0.9031
[Epoch 17/200] [loss_oh: 1.752401] [loss_ie: -0.963753] [loss_a: -0.129881] [loss_kd: 0.000000]
Test Avg. Loss: 0.018973, Accuracy: 0.698000
acc 0.698 acc_best 0.9031
from efficient-computing.
Related Issues (20)
- missing labels and low evaluation HOT 3
- "_call_impl(self, *input, **kwargs)" forward abnormally。
- Assertion `index >= -sizes[i] && index < sizes[i] && "index out of bounds"` failed. For debugging consider passing CUDA_LAUNCH_BLOCKING=1. HOT 1
- 【Function get_box_metrics(self) 】Unabel to get repr for <class 'torch.Tensor'>
- question about number of layers HOT 1
- Feature map size Question? HOT 2
- The script of generating text for GPT4Image HOT 1
- hyper-parameter "--fuse_ab" in gold-yolo HOT 1
- Creating textual descriptions using BLIP-2 on Cifar-10/100 HOT 1
- Code for DAFL HOT 1
- when I train myself datasets ,a bad question was happened that my iou_loss dfl_loss and ap is zero HOT 2
- 蒸馏的时候问题:AttributeError: 'Trainer' object has no attribute 'loss_items' HOT 1
- 训练报错 HOT 1
- About parameter use_syncbn and fuse_ab in train.py HOT 1
- Gold-YOLO的运行 HOT 1
- gold_yolo怎么训练自己的数据集 HOT 1
- gold_yolo训练自己的数据集失败 HOT 1
- class Inferer 参数webcam, webcam_addr,调用时没赋值? HOT 1
- Gold-yolo推理时的精度非常差
- Does the model support OBB detection? 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 efficient-computing.