| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566 |
- import random
- from torch.nn import L1Loss
- import numpy as np
- from fast_adapt import fast_adapt
- from sklearn.metrics import ndcg_score
-
-
- def hyper_test(embedding, head, total_dataset, adaptation_step):
- test_set_size = len(total_dataset)
- random.shuffle(total_dataset)
- a, b, c, d = zip(*total_dataset)
- losses_q = []
- ndcgs11 = []
- ndcgs33 = []
-
- head.eval()
-
- for iterator in range(test_set_size):
-
- try:
- supp_xs = a[iterator].cuda()
- supp_ys = b[iterator].cuda()
- query_xs = c[iterator].cuda()
- query_ys = d[iterator].cuda()
- except IndexError:
- print("index error in test method")
- continue
-
- learner = head.clone()
- temp_sxs = embedding(supp_xs)
- temp_qxs = embedding(query_xs)
-
- evaluation_error, predictions = fast_adapt(learner,
- temp_sxs,
- temp_qxs,
- supp_ys,
- query_ys,
- adaptation_step,
- get_predictions=True)
-
- l1 = L1Loss(reduction='mean')
- loss_q = l1(predictions.view(-1), query_ys)
- losses_q.append(float(loss_q))
- predictions = predictions.view(-1)
- y_true = query_ys.cpu().detach().numpy()
- y_pred = predictions.cpu().detach().numpy()
- ndcgs11.append(float(ndcg_score([y_true], [y_pred], k=1, sample_weight=None, ignore_ties=False)))
- ndcgs33.append(float(ndcg_score([y_true], [y_pred], k=3, sample_weight=None, ignore_ties=False)))
-
- del supp_xs, supp_ys, query_xs, query_ys, predictions, y_true, y_pred, loss_q
-
- # calculate metrics
- try:
- losses_q = np.array(losses_q).mean()
- except:
- losses_q = 100
-
- try:
- ndcg1 = np.array(ndcgs11).mean()
- ndcg3 = np.array(ndcgs33).mean()
- except:
- ndcg1 = 0
- ndcg3 = 0
-
- head.train()
- return losses_q, ndcg1, ndcg3
|
