jaeoh2 / road-lane-instance-segmentation-pytorch Goto Github PK
View Code? Open in Web Editor NEWtuSimple dataset road lane instance segmentation with PyTorch, ROS, ENet, SegNet and Discriminative Loss.
License: MIT License
tuSimple dataset road lane instance segmentation with PyTorch, ROS, ENet, SegNet and Discriminative Loss.
License: MIT License
What are the files in the train path directory? Why is the loss value Nan when I train
Road-Lane-Instance-Segmentation-PyTorch/enet.py
Lines 378 to 416 in ddf2a19
Is this wrong?
# Binary Segmentation
# Stage3
x1 = self.semBottleNeck3_0(x)
x1 = self.semBottleNeck3_1(x1)
x1 = self.semBottleNeck3_2(x1)
x1 = self.semBottleNeck3_3(x1)
x1 = self.semBottleNeck3_4(x1)
x1 = self.semBottleNeck3_5(x1)
x1 = self.semBottleNeck3_6(x1)
x1 = self.semBottleNeck3_7(x1)
# Stage4
x1 = self.semBottleNeck4_0(x1, ind_2)
x1 = self.semBottleNeck4_1(x1)
x1 = self.semBottleNeck4_2(x1)
# Stage5
x1 = self.semBottleNeck5_0(x1, ind_1)
x1 = self.semBottleNeck5_1(x1)
# Instance Segmentation
# Stage3
x2 = self.insBottleNeck3_0(x)
x2 = self.insBottleNeck3_1(x2)
x2 = self.insBottleNeck3_2(x2)
x2 = self.insBottleNeck3_3(x2)
x2 = self.insBottleNeck3_4(x2)
x2 = self.insBottleNeck3_5(x2)
x2 = self.insBottleNeck3_6(x2)
x2 = self.insBottleNeck3_7(x2)
# Stage4
x2 = self.insBottleNeck4_0(x2, ind_2)
x2 = self.insBottleNeck4_1(x2)
x2 = self.insBottleNeck4_2(x2)
# Stage5
x2 = self.insBottleNeck5_0(x2, ind_1)
x2 = self.insBottleNeck5_1(x2)
Thank you for your contribution. Can you provide a trained segnet model?
Have you tried generating your own dataset similar to Tusimple Dataset?
If yes, how?
What's the proper format for both binary and instance segmentation image labels?
Thanks for ur diles. if I just want to predict on tusimple dataset .I don’t want to use ros, Is there a corresponding file?
hello,thanks for your code. have you tried the enet by tensorflow?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.