"""
Format: directly use cid as the built-in index position; if aid cannot be put in, use the dictionary to search, there are only 50,000 of them anyway
"""
import faiss, numpy as np, os

# ############ If it is an original feature, you need to write save first
inp_root = r"E:\codes\py39\dataset\mi\2-co256"
npys = []
for name in sorted(list(os.listdir(inp_root))):
    phone = np.load("%s/%s" % (inp_root, name))
    npys.append(phone)
big_npy = np.concatenate(npys, 0)
print(big_npy.shape)  # (6196072, 192)#fp32#4.43G
np.save("infer/big_src_feature_mi.npy", big_npy)

##################train+add
# big_npy=np.load("/bili-coeus/jupyter/jupyterhub-liujing04/vits_ch/inference_f0/big_src_feature_mi.npy")
print(big_npy.shape)
index = faiss.index_factory(256, "IVF512,Flat")  # mi
print("training")
index_ivf = faiss.extract_index_ivf(index)  #
index_ivf.nprobe = 9
index.train(big_npy)
faiss.write_index(index, "infer/trained_IVF512_Flat_mi_baseline_src_feat.index")
print("adding")
index.add(big_npy)
faiss.write_index(index, "infer/added_IVF512_Flat_mi_baseline_src_feat.index")
"""
Size (all FP32)
big_src_feature 2.95G
(3098036, 256)
big_emb 4.43G
(6196072, 192)
The double of big_emb is because the feature needs to be repeated and then pitched

"""