From f32d9ed4d6513190e295cd1d0f07309e01cf0f63 Mon Sep 17 00:00:00 2001
From: Claudio Scheer <claudioscheer@protonmail.com>
Date: Mon, 11 May 2020 13:57:57 -0300
Subject: [PATCH] Update notebooks
---
notebooks/dataset.ipynb | 85 +++++++++++++++++++++++------------------
notebooks/network.ipynb | 28 +++++++++-----
src/main.py | 1 -
3 files changed, 65 insertions(+), 49 deletions(-)
diff --git a/notebooks/dataset.ipynb b/notebooks/dataset.ipynb
index 7733be8..d8c4c5d 100644
--- a/notebooks/dataset.ipynb
+++ b/notebooks/dataset.ipynb
@@ -16,7 +16,7 @@
},
{
"cell_type": "code",
- "execution_count": 1,
+ "execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
@@ -25,7 +25,7 @@
},
{
"cell_type": "code",
- "execution_count": 3,
+ "execution_count": 4,
"metadata": {},
"outputs": [
{
@@ -57,42 +57,42 @@
" <tr>\n",
" <th>0</th>\n",
" <td>how are you?</td>\n",
- " <td>good</td>\n",
+ " <td>sad</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
- " <td>how are you?</td>\n",
+ " <td>how re you?</td>\n",
" <td>sad</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
- " <td>how are you?</td>\n",
- " <td>upset</td>\n",
+ " <td>what is your name?</td>\n",
+ " <td>john</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
- " <td>how old are you?</td>\n",
- " <td>23 years old</td>\n",
+ " <td>are you good?</td>\n",
+ " <td>no</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>how old are you?</td>\n",
- " <td>9 years old</td>\n",
+ " <td>47 years old</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
- " question answer\n",
- "0 how are you? good\n",
- "1 how are you? sad\n",
- "2 how are you? upset\n",
- "3 how old are you? 23 years old\n",
- "4 how old are you? 9 years old"
+ " question answer\n",
+ "0 how are you? sad\n",
+ "1 how re you? sad\n",
+ "2 what is your name? john\n",
+ "3 are you good? no\n",
+ "4 how old are you? 47 years old"
]
},
- "execution_count": 3,
+ "execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
@@ -118,6 +118,7 @@
"source": [
"import torch\n",
"from torch.utils.data.dataset import Dataset\n",
+ "import pandas as pd\n",
"import numpy as np\n",
"\n",
"\n",
@@ -127,23 +128,27 @@
" self.questions = self.data[\"question\"]\n",
" self.answers = self.data[\"answer\"]\n",
" self.data_len = len(self.data.index)\n",
- " \n",
+ "\n",
" # Unique characters in the database.\n",
" self.unique_characters = set(\"\".join(self.questions + self.answers))\n",
- " self.unique_characters_length = len(self.unique_characters)\n",
+ " self.unique_characters_length = len(self.unique_characters) # 24\n",
+ "\n",
" # Map int to character.\n",
- " self.int2char = dict(enumerate(self.unique_characters))\n",
+ " self.int2char = {i: char for i, char in enumerate(self.unique_characters)}\n",
" # Map character to int.\n",
- " self.char2int = {char: i for i, char in self.int2char.items()}\n",
- " \n",
+ " self.char2int = {char: i for i, char in enumerate(self.unique_characters)}\n",
+ "\n",
" # Longer question.\n",
- " longer_question_length = len(max(self.questions, key=len))\n",
+ " self.longer_question_length = len(max(self.questions, key=len)) # 24\n",
" # Longer answer.\n",
- " longer_answer_length = len(max(self.answers, key=len))\n",
- " \n",
+ " self.longer_answer_length = self.longer_question_length\n",
+ " # self.longer_answer_length = len(max(self.answers, key=len)) # 14\n",
+ "\n",
" # Pad strings.\n",
- " self.questions = self.questions.str.pad(longer_question_length, side=\"right\")\n",
- " self.answers = self.answers.str.pad(longer_answer_length, side=\"right\")\n",
+ " self.questions = self.questions.str.pad(\n",
+ " self.longer_question_length, side=\"right\"\n",
+ " )\n",
+ " self.answers = self.answers.str.pad(self.longer_answer_length, side=\"right\")\n",
"\n",
" def __getitem__(self, index):\n",
" x = self.questions[index]\n",
@@ -151,39 +156,43 @@
" x = self.text2int(x)\n",
" # One-hot encode x.\n",
" x = self.one_hot_encode(x)\n",
- " x = torch.tensor(x)\n",
- " \n",
+ " x = torch.tensor(x).float().cuda()\n",
+ "\n",
" y = self.answers[index]\n",
" # Map text to int.\n",
" y = self.text2int(y)\n",
- " # One-hot encode y.\n",
- " y = self.one_hot_encode(y)\n",
- " y = torch.tensor(y)\n",
+ " y = torch.tensor(y).float().cuda()\n",
" return x, y\n",
"\n",
" def __len__(self):\n",
" return self.data_len\n",
- " \n",
+ "\n",
" def text2int(self, text):\n",
" \"\"\"\n",
" Convert text to an array of integers.\n",
" \"\"\"\n",
" return [self.char2int[c] for c in text]\n",
- " \n",
+ "\n",
+ " def int2text(self, sequence):\n",
+ " \"\"\"\n",
+ " Convert an array of integers to text.\n",
+ " \"\"\"\n",
+ " return [self.int2char[c] for c in sequence]\n",
+ "\n",
" def one_hot_encode(self, sequence):\n",
" \"\"\"\n",
" Convert an array of integers to a matrix one-hot encoded.\n",
" \"\"\"\n",
- " encoded = np.zeros([self.unique_characters_length, len(sequence)], dtype=int)\n",
+ " encoded = np.zeros([len(sequence), self.unique_characters_length], dtype=int)\n",
" for i, character in enumerate(sequence):\n",
- " encoded[character][i] = 1\n",
+ " encoded[i][character] = 1\n",
" return encoded\n",
- " \n",
+ "\n",
" def one_hot_decode(self, sequence):\n",
" \"\"\"\n",
" sequence: PyTorch tensor.\n",
" \"\"\"\n",
- " return [np.argmax(x) for x in sequence.numpy().T]"
+ " return [np.argmax(x) for x in sequence.numpy()]"
]
},
{
@@ -290,4 +299,4 @@
},
"nbformat": 4,
"nbformat_minor": 4
-}
\ No newline at end of file
+}
diff --git a/notebooks/network.ipynb b/notebooks/network.ipynb
index 534223c..7d055cb 100644
--- a/notebooks/network.ipynb
+++ b/notebooks/network.ipynb
@@ -32,41 +32,49 @@
"\n",
"\n",
"class RNNModel(nn.Module):\n",
- " def __init__(self, input_size, output_size, hidden_dim, n_layers):\n",
+ " def __init__(self, input_size, output_size):\n",
" super(RNNModel, self).__init__()\n",
"\n",
" # Defining some parameters.\n",
- " self.hidden_dim = hidden_dim\n",
- " self.n_layers = n_layers\n",
+ " self.input_size = input_size\n",
+ " self.output_size = output_size\n",
+ " self.hidden_dim = 32\n",
+ " self.n_layers = 1\n",
"\n",
" # region Defining the layers.\n",
" # RNN layer.\n",
" self.rnn = nn.RNN(\n",
- " input_size, hidden_dim, n_layers, batch_first=True, nonlinearity=\"relu\"\n",
+ " self.input_size,\n",
+ " self.hidden_dim,\n",
+ " self.n_layers,\n",
+ " batch_first=True,\n",
+ " nonlinearity=\"relu\",\n",
" )\n",
" # Fully connected layer.\n",
- " self.fc = nn.Linear(hidden_dim, output_size)\n",
+ " self.fc = nn.Linear(self.hidden_dim, self.output_size)\n",
" # endregion\n",
"\n",
" def forward(self, x):\n",
" batch_size = x.size(axis=0)\n",
"\n",
" # Initializing hidden state for first input using method defined below.\n",
- " hidden = self.init_hidden(batch_size) # (1, 3, 12)\n",
+ " hidden = self.init_hidden(batch_size) # (1, 1, 32)\n",
"\n",
" # Passing in the input and hidden state into the model and obtaining outputs.\n",
- " out, hidden = self.rnn(x, hidden) # (3, 14, 12), (1, 3, 12)\n",
+ " out, hidden = self.rnn(\n",
+ " x, hidden\n",
+ " ) # input => (3, 24, 24), (1, 1, 32) | output => (3, 24, 32), (1, 1, 32)\n",
"\n",
" # Reshaping the outputs such that it can be fit into the fully connected layer.\n",
- " out = out.contiguous().view(-1, self.hidden_dim) # (42, 12)\n",
- " out = self.fc(out) # (42, 17)\n",
+ " out = out.contiguous().view(-1, self.hidden_dim) # (72, 32)\n",
+ " out = self.fc(out) # (72, 24)\n",
"\n",
" return out, hidden\n",
"\n",
" def init_hidden(self, batch_size):\n",
" # This method generates the first hidden state of zeros which we will use in the forward pass.\n",
" hidden = torch.zeros(self.n_layers, batch_size, self.hidden_dim).cuda()\n",
- " return hidden\n"
+ " return hidden"
]
}
],
diff --git a/src/main.py b/src/main.py
index d58f583..e046c75 100644
--- a/src/main.py
+++ b/src/main.py
@@ -1,6 +1,5 @@
import torch
import torch.nn as nn
-from torch.utils.data.dataset import Dataset
from torch.utils.data.sampler import SubsetRandomSampler
import numpy as np
from rnn import RNNModel
--
GitLab