diff --git a/preprocessing/01D_raw_to_numpy_news-19.ipynb b/preprocessing/01D_raw_to_numpy_news-19.ipynb index 71cf923..bd7cf54 100644 --- a/preprocessing/01D_raw_to_numpy_news-19.ipynb +++ b/preprocessing/01D_raw_to_numpy_news-19.ipynb @@ -2,7 +2,7 @@ "cells": [ { "cell_type": "code", - "execution_count": 12, + "execution_count": 1, "metadata": {}, "outputs": [], "source": [ @@ -14,7 +14,7 @@ }, { "cell_type": "code", - "execution_count": 13, + "execution_count": 2, "metadata": {}, "outputs": [], "source": [ @@ -49,22 +49,22 @@ }, { "cell_type": "code", - "execution_count": 14, + "execution_count": 3, "metadata": {}, "outputs": [], "source": [ "# name_dataset = 'news-19_paragraph_swap-random-1m'\n", "# name_dataset = 'headline_swap_news_v2'\n", - "name_dataset = 'headline_swap_news_v2.5'\n", + "# name_dataset = 'headline_swap_news_v2.5'\n", "# name_dataset = 'headline_swap_news_v2.5_mf8'\n", - "# name_dataset = 'paragraph_swap_news_v2.5'\n", + "name_dataset = 'paragraph_swap_news_v2.5'\n", "path_raw_data = '../data/raw/' + name_dataset + '/'\n", "path_processed_data = '../data/' + name_dataset + '/whole/'" ] }, { "cell_type": "code", - "execution_count": 25, + "execution_count": 4, "metadata": {}, "outputs": [], "source": [ @@ -99,17 +99,14 @@ }, { "cell_type": "code", - "execution_count": 5, + "execution_count": null, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "2020-05-30T14:24:45.691755\n", - "100000 200000 300000 400000 500000 600000 700000 800000 900000 1000000 1100000 1200000 1300000 1347097 Done\n", - "2020-05-30T14:30:48.563996\n", - "voca size : 2988107\n" + "2020-05-30T21:44:39.779162\n" ] } ], @@ -432,16 +429,16 @@ }, { "cell_type": "code", - "execution_count": 16, + "execution_count": 5, "metadata": {}, "outputs": [ { "data": { "text/plain": [ - "188095" + "196381" ] }, - "execution_count": 16, + "execution_count": 5, "metadata": {}, "output_type": "execute_result" } @@ -475,7 +472,7 @@ }, { "cell_type": "code", - "execution_count": 17, + "execution_count": 6, "metadata": {}, "outputs": [], "source": [ @@ -485,7 +482,7 @@ }, { "cell_type": "code", - "execution_count": 18, + "execution_count": 7, "metadata": {}, "outputs": [], "source": [ @@ -498,16 +495,16 @@ }, { "cell_type": "code", - "execution_count": 19, + "execution_count": 8, "metadata": {}, "outputs": [ { "data": { "text/plain": [ - "188095" + "196381" ] }, - "execution_count": 19, + "execution_count": 8, "metadata": {}, "output_type": "execute_result" } @@ -518,7 +515,7 @@ }, { "cell_type": "code", - "execution_count": 20, + "execution_count": 9, "metadata": {}, "outputs": [ { @@ -737,7 +734,7 @@ }, { "cell_type": "code", - "execution_count": 21, + "execution_count": 12, "metadata": {}, "outputs": [], "source": [ @@ -1225,16 +1222,16 @@ }, { "cell_type": "code", - "execution_count": 23, + "execution_count": 13, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "2020-05-30T19:24:03.243950\n", + "2020-05-30T21:46:32.079525\n", "10000 20000 30000 40000 50000 60000 70000 80000 90000 100000 110000 120000 130000 140000 150000 160000 170000 178019 Done\n", - "2020-05-30T19:24:47.646848\n" + "2020-05-30T21:47:15.293565\n" ] } ], @@ -1274,15 +1271,15 @@ }, { "cell_type": "code", - "execution_count": 24, + "execution_count": 14, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "2020-05-30T19:24:47.656803\n", - "2020-05-30T19:25:19.275346\n" + "2020-05-30T21:47:15.302178\n", + "2020-05-30T21:47:47.505548\n" ] } ], @@ -1294,15 +1291,15 @@ }, { "cell_type": "code", - "execution_count": 26, + "execution_count": 15, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "2020-05-30T19:25:27.741204\n", - "2020-05-30T19:25:28.417751\n" + "2020-05-30T21:47:47.517646\n", + "2020-05-30T21:47:48.151477\n" ] } ], diff --git a/src_whole/eval_AHDE.sh b/src_whole/eval_AHDE.sh index c71cc2b..fed0a6d 100755 --- a/src_whole/eval_AHDE.sh +++ b/src_whole/eval_AHDE.sh @@ -3,5 +3,12 @@ -CUDA_VISIBLE_DEVICES=1 python eval_AHDE.py --model_path "model_ahde-TEST" --batch_size 100 --encoder_size 170 --context_size 44 --encoderR_size 22 --num_layer 1 --hidden_dim 200 --num_layer_con 1 --hidden_dim_con 100 --embed_size 300 --corpus 'news-19_whole' --data_path '../data/headline_swap_news_v2.5/whole/' + +# CUDA_VISIBLE_DEVICES=1 python eval_AHDE.py --model_path "model_ahde-head-v2.5-TEST" --batch_size 400 --encoder_size 170 --context_size 44 --encoderR_size 22 --num_layer 1 --hidden_dim 200 --num_layer_con 1 --hidden_dim_con 100 --embed_size 300 --corpus 'news-19_whole' --data_path '../data/headline_swap_news_v2.5/whole/' + + + + + +CUDA_VISIBLE_DEVICES=1 python eval_AHDE.py --model_path "model_ahde-para-v2.5-TEST" --batch_size 400 --encoder_size 170 --context_size 44 --encoderR_size 22 --num_layer 1 --hidden_dim 200 --num_layer_con 1 --hidden_dim_con 100 --embed_size 300 --corpus 'news-19_whole' --data_path '../data/paragraph_swap_news_v2.5/whole/'