yuanboot / intrinsic_garment_space Goto Github PK
View Code? Open in Web Editor NEWLicense: Mozilla Public License 2.0
License: Mozilla Public License 2.0
Hi there, I'm interested in giving this technique a try, but it looks like the data_set folder is empty. Are there more updates we can expect in order to run these examples?
Thanks!
-- Paul
Hello, I am trying to use your code for my project, but I find something not working as expected in 05.mie_train.py.
The function is get_same_material_list()
.
def get_same_material_list(flist_train, batchsize):
blst = np.random.permutation(len(flist_train))
xlst = []
t = 0
for i in range(len(blst)):
if flist_train[blst[i]][1] == flist_train[blst[0]][1]:
xlst.append(blst[i])
t=t+1
if t == batchsize: break
return xlst
If I understand correctly, the file list is a list of string of file information with the form "case_01 XX 123" "case_01 YY 234", where XX and YY correspond to the simulation parameter and the number indicates the frame number.
In line if flist_train[blst[i]][1] == flist_train[blst[0]][1]
, we try to find mesh files with the same simulation parameter.
However, the indexed flist_train[blst[i]] is a string, the second element (use [1] to index) is essentially a character 'a', not XX or YY. The function is trying to get four random data in the training set.
Thanks for your attention.
Hi there, it's me again. First, I wanted to thank you for providing this working implementation, I was able to run all the example scripts and produce very high quality results! Once I got the networks trained, I've been experimenting a bit to see how well they work on new inputs. Unfortunately, running 06.mie_eval.py on new data, even just a copy of data_set/anim/anim_01/Dude.anim.npy with slight perturbations, created very unstable results. I was digging in to debug the problem, when it occurred to me that 05.mie_train.py is only training on the 800 frames of animation in Dude.anim.py. This doesn't seem like enough data to allow much if any generalization to new motions. Checking the original paper, 30,000 frames of animation was used, which I imagine leads to much better results. Is there any chance you can provide that data set?
Thanks!
-- Paul
When generating cloth with new human motions, what is the input? I found the npy_path at line 98 in 06.mie_eval.py is the eval mesh corresponding to the new motion, which means the ground truth. Is it a bug? So what is the input when testing new motions? Maybe a random selected model which has the same material to the ground truth (eval mesh) from the training dataset, but different input may get various result.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ 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. ๐๐๐
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 โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.