output=Dense(3, activation='softmax', name="output"), params=params_spc, attention=ATTENTION) model.build() model_sent.build() #model.model().load_weights("/data/sent_nosent07_F1_0.8949_catAcc_0.8921_trainable_LSTM_300X300_ATT_DROPOUT_0.2X0.5_120__.hdf5") # old model.model().load_weights( "spc_07_F1_0.9506_catAcc_0.9176_trainable_LSTM_256X256_ATT_DROPOUT_0.3X0.5_None__.hdf5" ) model_sent.model().load_weights( "/data/spc_02_F1_0.9540_catAcc_0.9496_trainable_LSTM_300X300_ATT_DROPOUT_0.4X0.4_None__.hdf5" ) model.compile() model_sent.compile() # old #X_val = [value for value in tqdm(sem_eval_dataset_global.iterate_test_x(max_len=MAX_LEN, one_hot=True))] #X_val_text = [value for value in tqdm(sem_eval_dataset_global.iterate_test_x(max_len=MAX_LEN, one_hot=False))] X = [ value for value in tqdm( sem_eval_dataset.iterate_train_x(max_len=MAX_LEN, one_hot=True)) ] X_text = [ value for value in tqdm( sem_eval_dataset.iterate_train_x(max_len=MAX_LEN, one_hot=False)) ] X_val_spc = [
features: List[Feature] = [manual_features, glove_features, elmo_features] params = RNNModelParams(layers_size=LAYERS_SIZE, spatial_dropout=SPATIAL_DROPOUT, recurrent_dropout=RECURRENT_DROPOUT, dropout_dense=DROPOUT_DENSE, dense_encoder_size=DENSE) model = RNNModel(inputs=[input, text_input], features=features, output=Dense(3, activation='softmax', name="output"), params=params, attention=ATTENTION) model.build() model.compile() X = [ value for value in tqdm( sem_eval_dataset.iterate_train_x(max_len=MAX_LEN, one_hot=True)) ] X_text = [ value for value in tqdm( sem_eval_dataset.iterate_train_x(max_len=MAX_LEN, one_hot=False)) ] X_val = [ value for value in tqdm( sem_eval_dataset_dev.iterate_x(max_len=MAX_LEN, one_hot=True)) ] X_val_text = [