diff --git a/helpers.py b/helpers.py
index b093f62f25a9dce7913cca5373141f13f1753554..4bfee0e45f20a618bfb19046260ca2946ac0b025 100644
--- a/helpers.py
+++ b/helpers.py
@@ -172,13 +172,19 @@ class Chronometer:
from keras.callbacks import Callback
+import pandas as pd
import time
+import os
class EpochTimer(Callback):
def __init__(self,log_filename):
self.epoch = 0
self.timer = time.time()
- self.output = open(log_filename,'w')
+ if os.path.exists(log_filename):
+ self.output = open(log_filename,'a')
+ self.epoch = pd.read_csv(log_filename).Epoch.max()
+ else:
+ self.output = open(log_filename,'w')
self.output.write("{0},{1}\n".format("Epoch","Execution Time"))
self.output.flush()
diff --git a/parser_config/toponym_combination_embedding_v3.json b/parser_config/toponym_combination_embedding_v3.json
index 507e9c5123fcf2df11ff8c7e5348f3a50ce32dd4..12bfcefaf50e9be36289e76624bc47d36884df20 100644
--- a/parser_config/toponym_combination_embedding_v3.json
+++ b/parser_config/toponym_combination_embedding_v3.json
@@ -15,6 +15,8 @@
{ "short": "-e", "long": "--epochs", "type": "int", "default": 100 },
{ "short": "-d", "long": "--dimension", "type": "int", "default": 256 },
{ "short": "-l", "long": "--lstm-layer", "type": "int", "default": 2, "choices": [1, 2] },
- { "long": "--tokenization-method", "type": "str", "default": "char-level", "choices": ["char-level", "word-level", "bert"] }
+ { "long": "--tokenization-method", "type": "str", "default": "char-level", "choices": ["char-level", "word-level", "bert"] },
+ { "long": "--previous-state", "type": "str", "help": "If the model was trained before, give the path here" }
+
]
}
\ No newline at end of file
diff --git a/train_geocoder_v2.py b/train_geocoder_v2.py
index b44fada124eba4215d899f4350a68d1719d52956..4b7bfc3c94a20e19b44cac248b98538c44774ce2 100644
--- a/train_geocoder_v2.py
+++ b/train_geocoder_v2.py
@@ -61,6 +61,7 @@ DATASET_NAME = args.dataset_name
PREFIX_OUTPUT_FN = DATASET_NAME
PREFIX_OUTPUT_FN+="_{0}".format(NGRAM_SIZE)
+EMBEDDING_FN = "outputs/{0}_embedding.npy".format(PREFIX_OUTPUT_FN)
PREFIX_OUTPUT_FN+="_{0}".format(EPOCHS)
if args.adjacency:
@@ -74,6 +75,7 @@ MODEL_OUTPUT_FN = "outputs/{0}.h5".format(PREFIX_OUTPUT_FN)
INDEX_FN = "outputs/{0}_index".format(PREFIX_OUTPUT_FN)
HISTORY_FN = "outputs/{0}.csv".format(PREFIX_OUTPUT_FN)
+
#############################################################################################
################################# LOAD DATA #################################################
#############################################################################################
@@ -121,9 +123,16 @@ logging.info("Done !")
################################# NGRAM EMBEDDINGS ##########################################
#############################################################################################
-logging.info("Generating N-GRAM Embedding...")
-embedding_weights = index.get_embedding_layer([index.encode(p) for p in np.concatenate((pairs_of_toponym.toponym.unique(),pairs_of_toponym.toponym_context.unique()))],dim= EMBEDDING_DIM,iter=WORDVEC_ITER)
-logging.info("Embedding generated !")
+
+if os.path.exists(EMBEDDING_FN):
+ logging.info("Load previous N-GRAM Embedding...")
+ embedding_weights = np.load(EMBEDDING_FN)
+ logging.info("Embedding loaded ! ")
+else:
+ logging.info("Generating N-GRAM Embedding...")
+ embedding_weights = index.get_embedding_layer([index.encode(p) for p in np.concatenate((pairs_of_toponym.toponym.unique(),pairs_of_toponym.toponym_context.unique()))],dim= EMBEDDING_DIM,iter=WORDVEC_ITER)
+ np.save(EMBEDDING_FN,embedding_weights)
+ logging.info("Embedding generated !")
#############################################################################################
################################# BUILD TRAIN/TEST DATASETS #################################
@@ -132,31 +141,6 @@ logging.info("Preparing Input and Output data...")
training_generator = DataGenerator(pairs_of_toponym[pairs_of_toponym.split == "train"],index)
validation_generator = DataGenerator(pairs_of_toponym[pairs_of_toponym.split == "test"],index)
-# X_1_train,X_2_train=[],[]
-# X_1_test,X_2_test=[],[]
-# y_train,y_test = [],[]
-
-# for couple in pairs_of_toponym["toponym toponym_context split longitude latitude".split()].itertuples():
-# top,top_c,split_ = couple[1], couple[2], couple[3]
-# coord = zero_one_encoding(couple[-2],couple[-1]) # 0 and 1 encoding
-# enc_top, enc_top_c = index.encode(top),index.encode(top_c)
-# if split_ == "train":
-# X_1_train.append(enc_top)
-# X_2_train.append(enc_top_c)
-# y_train.append(list(coord))
-# else:
-# X_1_test.append(enc_top)
-# X_2_test.append(enc_top_c)
-# y_test.append(list(coord))
-
-# # "NUMPYZE" inputs and output lists
-# X_1_train = np.array(X_1_train)
-# X_2_train = np.array(X_2_train)
-# y_train = np.array(y_train)
-
-# X_1_test = np.array(X_1_test)
-# X_2_test = np.array(X_2_test)
-# y_test = np.array(y_test)
logging.info("Data prepared !")
@@ -178,31 +162,38 @@ embedding_layer = Embedding(num_words, EMBEDDING_DIM,input_length=index.max_len,
x1 = embedding_layer(input_1)
x2 = embedding_layer(input_2)
+if not args.previous_state:
#Â Each LSTM learn on a permutation of the input toponyms
-if args.lstm_layer == 2:
- x1 = Bidirectional(LSTM(100))(x1)
- x2 = Bidirectional(LSTM(100))(x2)
- x = concatenate([x1,x2])
-else:
- lstm_unique_layer = Bidirectional(LSTM(100))
- x1 = lstm_unique_layer(x1)
- x2 = lstm_unique_layer(x2)
- x = concatenate([x1,x2])
+ if args.lstm_layer == 2:
+ x1 = Bidirectional(LSTM(100))(x1)
+ x2 = Bidirectional(LSTM(100))(x2)
+ x = concatenate([x1,x2])
+ else:
+ lstm_unique_layer = Bidirectional(LSTM(100))
+ x1 = lstm_unique_layer(x1)
+ x2 = lstm_unique_layer(x2)
+ x = concatenate([x1,x2])
-x1 = Dense(500,activation="relu")(x)
-x1 = Dense(500,activation="relu")(x1)
+ x1 = Dense(500,activation="relu")(x)
+ x1 = Dense(500,activation="relu")(x1)
-x2 = Dense(500,activation="relu")(x)
-x2 = Dense(500,activation="relu")(x2)
+ x2 = Dense(500,activation="relu")(x)
+ x2 = Dense(500,activation="relu")(x2)
-output_lon = Dense(1,activation="sigmoid",name="Output_LON")(x1)
-output_lat = Dense(1,activation="sigmoid",name="Output_LAT")(x2)
+ output_lon = Dense(1,activation="sigmoid",name="Output_LON")(x1)
+ output_lat = Dense(1,activation="sigmoid",name="Output_LAT")(x2)
-output_coord = concatenate([output_lon,output_lat],name="output_coord")
+ output_coord = concatenate([output_lon,output_lat],name="output_coord")
-model = Model(inputs = [input_1,input_2], outputs = output_coord)#input_3
-model.compile(loss={"output_coord":haversine_tf_1circle}, optimizer='adam',metrics={"output_coord":accuracy_k(ACCURACY_TOLERANCE)})
+ model = Model(inputs = [input_1,input_2], outputs = output_coord)#input_3
+ model.compile(loss={"output_coord":haversine_tf_1circle}, optimizer='adam',metrics={"output_coord":accuracy_k(ACCURACY_TOLERANCE)})
+else:
+ if not os.path.exists(args.previous_state):
+ print("Model previous state was not found ! ")
+ sys.exit(1)
+ print("Load Previous state of the model...")
+ model = tf.keras.models.load_model(args.previous_state,custom_objects={"haversine_tf_1circle":haversine_tf_1circle,"compute_metric":accuracy_k(100)})
print("Neural Network Architecture : ")
print(model.summary())
#############################################################################################
@@ -220,12 +211,6 @@ history = model.fit(training_generator,verbose=True,
validation_data=validation_generator,
callbacks=[checkpoint,epoch_timer],epochs=EPOCHS)
-# history = model.fit(x=[X_1_train,X_2_train],
-# y=y_train,
-# verbose=True, batch_size=100,
-# epochs=EPOCHS,
-# validation_data=([X_1_test,X_2_test],y_test),#[y_lon_test,y_lat_test]),
-# callbacks=[checkpoint,epoch_timer])
hist_df = pd.DataFrame(history.history)