# In[33]:
model.fit(x=X_train,
y=Y_train,
batch_size=32,
validation_data=(X_test, Y_test),
epochs=3,
verbose=1)
# In[34]:
model.save('./')
# In[77]:
model.evaluate(X_test, Y_test)
# In[124]:
# Preprocessing User Input
def word_to_idx(words_predict):
words_idx = np.full((max_len, ), len(words) - 1)
i = 0
for w in words_predict:
words_idx[i] = wordtoidx[w]
i += 1
return words_idx
input_sentence = "I want to fly in an Airbus. I am planning a trip to London"
metrics=["accuracy"])
from tensorflow.keras.callbacks import ModelCheckpoint, EarlyStopping
from livelossplot.tf_keras import PlotLossesCallback
# chkpt = ModelCheckpoint("model_weights.h5", monitor='val_loss',verbose=1, save_best_only=True, save_weights_only=True, mode='min')
#
# early_stopping = EarlyStopping(monitor='val_accuracy', min_delta=0, patience=1, verbose=0, mode='max', baseline=None, restore_best_weights=False)
#
# callbacks = [PlotLossesCallback(), chkpt, early_stopping]
#
# history = model.fit(
# x=x_train,
# y=y_train,
# validation_data=(x_test,y_test),
# batch_size=32,
# epochs=3,
# callbacks=callbacks,
# verbose=1
# )
model.evaluate(x_test, y_test)
i = np.random.randint(0, x_test.shape[0]) #659
p = model.predict(np.array([x_test[i]]))
p = np.argmax(p, axis=-1)
y_true = y_test[i]
print("{:15}{:5}\t {}\n".format("Word", "True", "Pred"))
print("-" * 30)
for w, true, pred in zip(x_test[i], y_true, p[0]):
print("{:15}{}\t{}".format(words[w - 1], tags[true], tags[pred]))
# In[52]:
y = np.array(y_train)
y.shape
# In[53]:
get_ipython().run_cell_magic(
'time', '',
'\nchkpt = ModelCheckpoint("model_weights.h5", monitor=\'val_loss\',verbose=1, save_best_only=True, save_weights_only=True, mode=\'min\')\n\nearly_stopping = EarlyStopping(monitor=\'val_accuracy\', min_delta=0, patience=1, verbose=0, mode=\'max\', baseline=None, restore_best_weights=False)\n\ncallbacks = [PlotLossesCallback(), chkpt, early_stopping]\n\nhistory = model.fit(\n x=x_train,\n y=np.array(y_train),\n validation_split=0.2,\n batch_size=32, \n epochs=10,\n callbacks=callbacks,\n verbose=1\n)'
)
# ### Evaluate Named Entity Recognition Model
# In[55]:
model.evaluate(x_test, np.array(y_test))
# In[61]:
i = np.random.randint(0, x_test.shape[0])
p = model.predict(np.array([x_test[i]]))
p = np.argmax(p, axis=-1)
y_true = np.argmax(np.array(y_test), axis=-1)[i]
print("{:15}{:5}\t {}\n".format("Word", "True", "Pred"))
print("-" * 30)
for w, true, pred in zip(x_test[i], y_true, p[0]):
print("{:15}{}\t{}".format(words[w - 1], tags[true], tags[pred]))
# In[ ]: