D_LEARNING_RATE = 0.001 G_LEARNING_RATE = 0.01 BETA = OUTPUT_DIM / 8.0 GAMMA = 0.1 WORKDIR = '../mir/' GEN_MODEL_BEST_FILE = './model/gan_best_nn_' + str(OUTPUT_DIM) + '.model' DIS_MODEL_BEST_FILE = './model/dis_best_nn_' + str(OUTPUT_DIM) + '.model' GEN_MODEL_NEWEST_FILE = './model/gan_newest_nn_' + str(OUTPUT_DIM) + '.model' DIS_MODEL_NEWEST_FILE = './model/dis_newest_nn_' + str(OUTPUT_DIM) + '.model' DIS_MODEL_PRETRAIN_FILE = './model/dis_pretrain_nn_' + str( OUTPUT_DIM) + '.model' train_i2t, train_i2t_pos, train_i2t_neg, train_t2i, train_t2i_pos, train_t2i_neg, test_i2t, test_i2t_pos, test_t2i, test_t2i_pos = ut.load_all_query_url( WORKDIR + 'list/', CLASS_DIM) feature_dict = ut.load_all_feature(WORKDIR + 'list/', WORKDIR + 'feature/') label_dict = ut.load_all_label(WORKDIR + 'list/') record_file = open('record_' + str(OUTPUT_DIM) + '.txt', 'w') record_file.close() def generate_samples(sess, generator, train_list, train_pos, train_neg, flag): data = [] for query in train_pos: pos_list = train_pos[query] candidate_neg_list = train_neg[query] candidate_list = train_list[query]
HIDDEN_DIM = 8192 CLASS_DIM = 24 BATCH_SIZE = 256 WEIGHT_DECAY = 0.01 D_LEARNING_RATE = 0.01 LAMBDA = 0 BETA = OUTPUT_DIM / 8.0 GAMMA = 0.1 # WORKDIR = '../mir/' DIS_MODEL_BEST_FILE = '/....../teacher_best_pretrain' + str( OUTPUT_DIM) + '.model' #DIS_MODEL_BEST_I2I_FILE = '/home/huhengtong/UKD/teacher_UGACH/OL_teacher_best_i2i_' + str(OUTPUT_DIM) + '.model' # DIS_MODEL_NEWEST_FILE = './model/dis_newest_nn_' + str(OUTPUT_DIM) + '.model' train_i2t, train_i2t_pos, train_i2t_neg, train_t2i, train_t2i_pos, train_t2i_neg = ut.load_all_query_url( ) # pdb.set_trace() feature_dict = ut.load_all_feature() label_dict = ut.load_all_label() #print(len(feature_dict), len(label_dict)) def generate_samples(train_pos, train_neg, flag): data = [] for query in train_pos: pos_list = train_pos[query] candidate_neg_list = train_neg[query] random.shuffle(pos_list)
CLASS_DIM = 20 MODAL_NUM = 5 TRAIN_NUM = 4000 BATCH_SIZE = 16 WEIGHT_DECAY = 0.0005 D_LEARNING_RATE = 0.01 LAMBDA = 0 BETA = 1.0 GAMMA = 0.1 WORKDIR = '../xmedia/' DIS_MODEL_BEST_FILE = './model/dis_best_nn_' + str(OUTPUT_DIM) + '.model' DIS_MODEL_NEWEST_FILE = './model/dis_newest_nn_' + str(OUTPUT_DIM) + '.model' #test_feature,database_feature,test_label,database_label = ut.load_all_query_url(WORKDIR + 'feature/',WORKDIR + 'list/', CLASS_DIM) test_feature, database_feature, test_label, database_label = ut.load_all_query_url( WORKDIR + 'feature_znorm/', WORKDIR + 'list/', CLASS_DIM) # pdb.set_trace() train_feature = ut.load_train_feature(WORKDIR + 'feature_znorm/') # label_dict = ut.load_all_label(WORKDIR + 'list/') knn_idx = ut.load_knn(WORKDIR + 'python/xmedia/') # record_file_name = 'record_' + str(OUTPUT_DIM) + '.txt', #record_file = open('record_' + str(OUTPUT_DIM) + '.txt', 'w') #record_file.close() def generate_samples(fix): data = []