datasets.py 文件源码

def get_train_data(n_pos = 46443, n_neg = 206940,k=12):        
        '''
        megre positive and negative examples
        '''
        suff = str(k)        
        X_name = 'train_data_'+ suff + '.npz'
        y_name = 'labels_'+ suff + '.npz' 
        if not(os.path.exists(X_name) and os.path.exists(y_name)):
            X_pos = []            
#            X_train_face,y_train_face  = Datasets.get_train_face_wider_data(k = k)
#            X_pos = X_train_face[y_train_face==1]
#            X_pos = X_train_face
            X_aflw,y_train_face_aflw  = Datasets.get_aflw_face_data(k = k)
#            if len(X_pos) > 0:
#                X_pos = sp.vstack( [X_pos,X_aflw] )
#            else:
#                X_pos = X_aflw
            X_pos = X_aflw
            X_train_non_face,y_train_non_face =  Datasets.get_train_non_face_data(k = k)
            print('c1_pos:',len(X_pos))
            #print((X_train_face[y_train_face==0].shape,X_train_non_face.shape))
#            if len(X_train_face[y_train_face==0]) > 0:
#                X_neg = sp.vstack( (X_train_face[y_train_face==0],X_train_non_face) )
#            else:
#                X_neg = X_train_non_face
            X_neg = X_train_non_face
            X_pos = shuffle(X_pos,random_state=42)
            X_neg = shuffle(X_neg,random_state=42)
            X_pos = X_pos[:n_pos]
            X_neg = X_neg[:n_neg]

            n_neg = len(X_neg)
            n_pos = len(X_pos)
            y_pos = sp.ones(n_pos,int)
            y_neg = sp.zeros(n_neg,int)
            X = sp.vstack((X_pos,X_neg))
            y = sp.hstack( (y_pos,y_neg) )
            X,y = shuffle(X,y,random_state=42)
            sp.savez(X_name,X)
            sp.savez(y_name,y)