Comments (4)
我在训练时设置batch_size = 1,CPU_NUM = 1。为什么在利用vis.py画图或eval.py执行评估时,代码test_prog = test_prog.clone(for_test = True)不加for_test = True得效果要比加入for_test是因为batch_norm的缘故吗?难道不是设置batch_size = 1,batch_norm就可以失效了吗?求大神帮忙解答以下。
在测试中,batch_size是不会影响预测结果的。
在卷积运算中,bn是针对每一个通道进行计算的,所以并不能通过将batch_size = 1设置成1让其失效的。
test_prog = test_prog.clone(for_test = True)和不加for_test = True的实验,你能提供一下相关结果吗?以及相应的配置
from paddleseg.
我也遇到了相同的问题,loss和miou都差好多。我选用的配置是pspnet,layers:101
将for_test设置为False的结果:loss=0.09,acc=0.9968,IOU=0.8845
将for_test设置为true的结果:loss=1.417,acc=0.9196,IOU=0.4760
from paddleseg.
你好,能提供一下具体的运行场景和运行日志吗?
from paddleseg.
请问你们在运行可视化时,出现这种情况没?
Traceback (most recent call last):
File "vis.py", line 212, in
visualize(cfg, **args.dict)
File "vis.py", line 133, in visualize
for imgs, grts, img_names, valid_shapes, org_shapes in test_reader:
File "/PaddleSeg-release-v0.7.0/pdseg/reader.py", line 136, in batch_reader
for img, grt, img_name, valid_shape, org_shape in reader():
File "/PaddleSeg-release-v0.7.0/pdseg/reader.py", line 81, in generator
yield self.process_image(line, self.data_dir, self.mode)
File "/PaddleSeg-release-v0.7.0/pdseg/reader.py", line 251, in process_image
line, data_dir, mode=mode)
File "/PaddleSeg-release-v0.7.0/pdseg/reader.py", line 205, in load_image
grt_height = grt.shape[0]
IndexError: tuple index out of range
from paddleseg.
Related Issues (20)
- 关于PP-HumanSeg14K数据集 HOT 2
- SegmentAngthing 出现引用gradio错误 HOT 2
- 训练自己的数据集,推理结果收到batch size影响很大 HOT 1
- TypeError: __init__() got an unexpected keyword argument 'to_static_training' HOT 5
- eiseg标注的jason文件怎么转换成COCO格式,我用labelme保存的jason文件可以用脚本转换的,但是转eiseg的jason就报错 HOT 1
- Assignment error in RandomPaddingCrop HOT 3
- EISeg闪退 HOT 1
- getting raw logits from trained model HOT 1
- About PP-LiteSeg: What's the official flops? HOT 1
- 关于CPS的数据导入问题dataloader StopIteration HOT 1
- PP_humansegv2预训练模型微调
- 自定义数据集出现 TypeError: Config.__init__() got an unexpected keyword argument 'to_static_training' HOT 4
- 出现IndexError: too many indices for array: array is 0-dimensional, but 1 were indexed 的原因 HOT 17
- paddleseg模型部署,开启服务后。正常运行两天左右,服务便会自动终止,输出日志中没有找到终止原因 HOT 2
- Run inference from Python script HOT 2
- pip install paddleseg install 2.8.0 version instead of 2.9.0 HOT 2
- C2Fnet训练问题 HOT 1
- 想通过paddleseg训练和分割4通道的影像 HOT 1
- 关于安装paddleseg过程中出现的包版本不兼容问题 HOT 3
- Paddle Inference在Linux上部署PaddleSeg模型时遇到的问题
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 paddleseg.