The deepaccnet-tf from hiranumn

deepaccnet-tf's People

Contributors

Stargazers

Watchers

deepaccnet-tf's Issues

pyErrorPred.predict error

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