def main():
path = input('Enter file path of your model:')
with open(RAW_META_PATH, 'rb') as f:
meta = msgpack.load(f, encoding='utf8')
embedding = load_pickle(EMB_PATH)
model = models.AttentionModel(path)
w2id = {w: i for i, w in enumerate(meta['vocab'])}
tag2id = {w: i for i, w in enumerate(meta['vocab_tag'])}
ent2id = {w: i for i, w in enumerate(meta['vocab_ent'])}
while True:
id_ = 0
try:
while True:
context = input('Enter context: ')
if context.strip():
break
while True:
question = input('Enter question: ')
if question.strip():
break
except EOFError:
break
id_ += 1
annotated = annotate(('interact-{}'.format(id_), context, question),
meta['wv_cased'])
model_in_raw = to_id(annotated, w2id, tag2id, ent2id)
model_in = generate_batch(model_in_raw)
start_probas, end_probas = model.model.predict(model_in)
answ_pair = get_preds2(start_probas, end_probas, MAX_ANSW_LEN)
print('Answer:', end=' ')
for i in range(answ_pair[0][0], answ_pair[0][1] + 1):
print(model_in_raw[6][model_in_raw[7][i][0]:model_in_raw[7][i][1] +
1],
end='')
print('\n\n\n-------------|||-------------\n\n\n')
img_dim=X.shape[2],
n_outputs=10)
results = {}
for i in range(10):
model.fit(X, y, epochs=1, batch_size=50, verbose=0)
# EVALUATE TRAIN AND TEST CLASSIFICATION
yhat = np.argmax(model.predict(X), axis=1)
trainscore = (yhat == y).mean()
yhat = np.argmax(model.predict(Xtest), axis=1)
testscore = (yhat == ytest).mean()
print("%d - Train score = %.3f" % (i, trainscore))
print("%d - Test score = %.3f\n" % (i, testscore))
# BASELINE TEST score IS 91%
elif part == '7':
X, y = du.load_dataset("boat_images", as_image=False)
# TRAIN NETWORK
model = models.AttentionModel(n_channels=3, n_outputs=1)
model.fit(X, y, batch_size=23, epochs=100)
show = lambda m, i: iu.show(m.get_heatmap(X)[i], X[i])
import pdb
pdb.set_trace() # breakpoint 387f960a //
show(model, 1)
def main():
path = input('Enter file path of your model:')
att_model = models.AttentionModel(path)
att_model.quality()
def main():
epochs = input('Enter amount of epochs')
att_model = models.AttentionModel()
att_model.train(n_epochs=epochs)