kulikovv / deepcoloring Goto Github PK
View Code? Open in Web Editor NEWInstance Segmentation by Deep Coloring
License: GNU General Public License v3.0
Instance Segmentation by Deep Coloring
License: GNU General Public License v3.0
Hello, there are some syntax errors when I run your CVPPP notebook.
in the utils.py
,the visualize
function. row291.
IndexError: only integers, slices (`:`), ellipsis (`...`), numpy.newaxis (`None`) and integer or boolean arrays are valid indices
I try to fix it, but I failed.
and the __init__.py
are still some bugs. Do you mean from .halo_loss import halo_loss, ...
hi, thanks for this job. May I ask when will release the cityscapes instance segmentation codes?
Hi! Victor, thank you for your contribution. Question:
In train_cvppp.py you implicitly pass 0.5, 0.5 for mean and std in dc.normalize. Those doesn`t seem like actual values for cvppp, could you please explain how did you get those values and what would be the right way to estimate them for different data?
IndexError Traceback (most recent call last)
in
12 p_numpy = p.detach().cpu().numpy()[0]
13
---> 14 dc.visualize(xo[:,:,:3],p_numpy,65)
~/DeepColoring-master/deepcoloring/utils.py in visualize(x_np, y_np, min_point, draw_text, cmap)
289 cmap = matplotlib.colors.LinearSegmentedColormap.from_list('xxx', [color_map[color_index], color_map[color_index2]])
290 ax[index / 3, index % 3].imshow(y_np[index, :, :], vmin=0, vmax=1, cmap=cmap)
--> 291
292 return f1, f2
293
IndexError: only integers, slices (:
), ellipsis (...
), numpy.newaxis (None
) and integer or boolean arrays are valid indices
Really nice work for instance segmentation!
Could you please tell me how to use your code to train or test?
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.