hiranumn / deepaccnet-tf Goto Github PK
View Code? Open in Web Editor NEWPython/TF1 implementation of DeepAccNet (https://www.biorxiv.org/content/10.1101/2020.07.17.209643v1)
License: MIT License
Python/TF1 implementation of DeepAccNet (https://www.biorxiv.org/content/10.1101/2020.07.17.209643v1)
License: MIT License
It seems the pyErrorPred.predict not correct
the predict function in DeepAccNet.py
result = pyErrorPred.predict(samples,
modelpath,
args.output,
num_blocks=5,
num_filters=128,
verbose=args.verbose,
ensemble=args.ensemble,
csv = args.csv)
while the function in predict.py looks like
def predict(samples, modelpath, outfolder, num_blocks=5, num_filters=128, ensemble=False, verbose=False):
n_models = 5 if ensemble else 2
for i in range(1, n_models):
modelname = modelpath+"_rep"+str(i)
if verbose: print("Loading", modelname)
model = Model(obt_size = 70,
tbt_size = 33,
prot_size = None,
num_chunks = num_blocks,
channel = num_filters,
optimizer = "adam",
loss_weight = [1.0, 0.25, 10.0],
name = modelname,
label_smoothing = False,
no_last_dilation = True,
partial_instance_norm = True,
bert = False)
model.load()
for j in range(len(samples)):
if verbose: print("Predicting for", samples[j], "(network rep"+str(i)+")")
tmp = join(outfolder, samples[j]+".features.npz")
batch = getData(tmp)
lddt, estogram, mask = model.predict(batch)
if not ensemble:
np.savez_compressed(join(outfolder, samples[j]+".npz"),
lddt = lddt,
estogram = estogram,
mask = mask)
else:
np.savez_compressed(join(outfolder, samples[j]+".rep"+str(i)+".npz"),
lddt = lddt,
estogram = estogram,
mask = mask)
No csv option and no return value.
Please double-check if the code version is correctly uploaded.
Best
Never mind.
It's a very interesting work. The code here can only predict the accuracy. I would appreciate it if you could provide the source code for refinement.
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.