feature_data = read.read()
test_ids = list(feature_data.keys())
for test_id in test_ids:
_train_data, _test_data = read.split(feature_data, test_id)
_train_data, _train_labels = read.flatten(_train_data)
_test_data, _test_labels = read.flatten(_test_data)
_train_data = np.array(_train_data)
_test_data = np.array(_test_data)
_embedding_model, _triplet_model = build_mlp_model((feature_length, ))
_triplet_model.fit_generator(triplet_generator_minibatch(
_train_data, _train_labels, mini_batch_size),
steps_per_epoch=steps_per_epoch,
epochs=epochs,
verbose=1)
_train_preds = _embedding_model.predict(_train_data)
_test_preds = _embedding_model.predict(_test_data)
acc = read.cos_knn(k, _test_preds, _test_labels, _train_preds,
_train_labels)
result = 'prototype_tn_mlp, 3nn,' + str(test_id) + ',' + str(acc)
print(result)
read.write_data('tn_mlp.csv', result)
modelinputs.append(targetembedding)
supportlabels = Input((numsupportset, classes_per_set))
modelinputs.append(supportlabels)
knnsimilarity = MatchCosine(nway=classes_per_set,
n_samp=samples_per_class)(modelinputs)
model = Model(inputs=[input1, supportlabels], outputs=knnsimilarity)
model.compile(optimizer='adam',
loss='categorical_crossentropy',
metrics=['accuracy'])
model.fit([_train_data[0], _train_data[1]],
_train_data[2],
epochs=epochs,
batch_size=batch_size,
verbose=1)
_support_preds = base_network.predict(_support_data)
for _l in list(_test_data[test_id].keys()):
_test_label_data = _test_data[test_id][_l]
_test_labels = [_l for i in range(len(_test_label_data))]
_test_label_data = np.array(_test_label_data)
_test_labels = np.array(_test_labels)
_test_preds = base_network.predict(_test_label_data)
acc = read.cos_knn(k, _test_preds, _test_labels, _support_preds,
_support_labels)
result = 'mn_mlp, 3nn,' + str(test_id) + ',' + str(
a_label) + ',' + str(_l) + ',' + str(acc)
read.write_data('pmn_mlp_oe.csv', result)
pred = [[thigh_train_data[j] for j in i[:kk]] for i in top]
pred = np.array(pred)
pred = np.average(pred, axis=1)
return pred
feature_data = read.read()
test_ids = list(feature_data.keys())
for test_id in test_ids:
_train_data, _test_data = read.split(feature_data, [test_id])
w_train_data, t_train_data, _train_labels = read.flatten(_train_data)
w_test_data, t_test_data, _test_labels = read.flatten(_test_data)
w_train_data = np.array(w_train_data)
t_train_data = np.array(t_train_data)
train_data = np.concatenate([w_train_data, t_train_data], axis=1)
print(train_data.shape)
w_test_data = np.array(w_test_data)
t_test_data = ed_knn(w_test_data, w_train_data, t_train_data)
test_data = np.concatenate([w_test_data, t_test_data], axis=1)
print(test_data.shape)
cos_acc = read.cos_knn(k, test_data, _test_labels, train_data,
_train_labels)
results = 'euclid_t_translator,' + str(k) + ',' + str(
kk) + ',cos_acc,' + str(cos_acc)
print(results)
read.write_data(results_file, results)
ca_test_data = np.concatenate([c_test_data, a_test_data], axis=1)
print(ca_test_data.shape)
ae_model = auto_encoder()
ae_model.compile(optimizer='adam', loss='mse')
ae_model.fit(h_train_data,
c_train_data,
verbose=0,
epochs=100,
shuffle=True)
c_test_data = ae_model.predict(h_test_data)
hc_test_data = np.concatenate([h_test_data, c_test_data], axis=1)
print(ca_test_data.shape)
cos_acc = read.cos_knn(k, ha_test_data, _test_labels, ha_train_data,
_train_labels)
ha_results.append('ha,' + 'a_translator,' + str(k) + ',cos_acc,' +
str(cos_acc))
cos_acc = read.cos_knn(k, ca_test_data, _test_labels, ca_train_data,
_train_labels)
ca_results.append('ca,' + 'a_translator,' + str(k) + ',cos_acc,' +
str(cos_acc))
cos_acc = read.cos_knn(k, hc_test_data, _test_labels, hc_train_data,
_train_labels)
hc_results.append('hc,' + 'c_translator,' + str(k) + ',cos_acc,' +
str(cos_acc))
for item in hc_results:
read.write_data(results_file, item)
ha_train_data = np.concatenate([h_train_data, a_train_data], axis=1)
print(ha_train_data.shape)
h_test_data = np.array(h_test_data)
c_test_data = np.array(c_test_data)
a_test_data = np.array(a_test_data)
test_data = np.concatenate([h_test_data, c_test_data, a_test_data], axis=1)
print(test_data.shape)
hc_test_data = np.concatenate([h_test_data, c_test_data], axis=1)
print(hc_test_data.shape)
ca_test_data = np.concatenate([c_test_data, a_test_data], axis=1)
print(ca_test_data.shape)
ha_test_data = np.concatenate([h_test_data, a_test_data], axis=1)
print(ha_test_data.shape)
cos_acc = read.cos_knn(k, test_data, _test_labels, train_data, _train_labels)
all_results.append('knn,'+str(k)+',cos_acc,'+str(cos_acc))
h_cos_acc = read.cos_knn(k, h_test_data, _test_labels, h_train_data, _train_labels)
h_results.append('h,knn,'+str(k)+',cos_acc,'+str(h_cos_acc))
c_cos_acc = read.cos_knn(k, c_test_data, _test_labels, c_train_data, _train_labels)
c_results.append('c,knn,'+str(k)+',cos_acc,'+str(c_cos_acc))
a_cos_acc = read.cos_knn(k, a_test_data, _test_labels, a_train_data, _train_labels)
a_results.append('a,knn,'+str(k)+',cos_acc,'+str(a_cos_acc))
hc_cos_acc = read.cos_knn(k, hc_test_data, _test_labels, hc_train_data, _train_labels)
hc_results.append('hc,knn,'+str(k)+',cos_acc,'+str(hc_cos_acc))
ha_cos_acc = read.cos_knn(k, ha_test_data, _test_labels, ha_train_data, _train_labels)
ha_results.append('ha,knn,'+str(k)+',cos_acc,'+str(ha_cos_acc))
ca_cos_acc = read.cos_knn(k, ca_test_data, _test_labels, ca_train_data, _train_labels)
ca_results.append('ca,knn,'+str(k)+',cos_acc,'+str(ca_cos_acc))
import numpy as np
import read
feature_data = read.read()
test_ids = list(feature_data.keys())
for test_id in test_ids:
_train_data, _test_data = read.split(feature_data, [test_id])
_test_data, _test_labels = read.flatten(_test_data)
_train_data, _train_labels = read.flatten(_train_data)
_train_data = np.array(_train_data)
print(_train_data.shape)
_train_data = np.reshape(_train_data, (_train_data.shape[0], _train_data.shape[1] * _train_data.shape[2]))
print(_train_data.shape)
_test_data = np.array(_test_data)
print(_test_data.shape)
_test_data = np.reshape(_test_data, (_test_data.shape[0], _test_data.shape[1] * _test_data.shape[2]))
print(_test_data.shape)
acc = read.cos_knn(1, _test_data, _test_labels, _train_data, _train_labels)
print(acc)
acc = read.cos_knn(2, _test_data, _test_labels, _train_data, _train_labels)
print(acc)
acc = read.cos_knn(3, _test_data, _test_labels, _train_data, _train_labels)
print(acc)
acc = read.cos_knn(5, _test_data, _test_labels, _train_data, _train_labels)
print(acc)