Spaces:
Sleeping
Sleeping
File size: 1,377 Bytes
1d7c63d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 |
from sklearn.decomposition import PCA
import pickle as pk
import numpy as np
import pandas as pd
pca_fossils = pk.load(open('pca_fossils_170_finer.pkl','rb'))
pca_leaves = pk.load(open('pca_leaves_170_finer.pkl','rb'))
embedding_fossils = np.load('embedding_fossils_170_finer.npy')
#embedding_leaves = np.load('embedding_leaves.npy')
fossils_pd= pd.read_csv('fossils_paths.csv')
def pca_distance(pca,sample,embedding):
s = pca.transform(sample.reshape(1,-1))
all = pca.transform(embedding[:,-1])
distances = np.linalg.norm(all - s, axis=1)
print(distances)
return np.argsort(distances)[:5]
def return_paths(argsorted,files):
paths= []
for i in argsorted:
paths.append(files[i])
return paths
def get_images(embedding):
#pca_embedding_fossils = pca_fossils.transform(embedding_fossils[:,-1])
pca_d =pca_distance(pca_fossils,embedding,embedding_fossils)
fossils_paths = fossils_pd['file_name'].values
paths = return_paths(pca_d,fossils_paths)
print(paths)
paths= [path.replace('/gpfs/data/tserre/irodri15/Fossils/new_data/leavesdb-v1_1/images/Fossil/Florissant_Fossil/512/full/jpg/',
'/media/data_cifs/projects/prj_fossils/data/processed_data/leavesdb-v1_1/images/Fossil/Florissant_Fossil/original/full/jpg/') for path in paths]
print(paths)
return paths |