wehub-resource-sync
111 lines
4.2 KiB
Plaintext
111 lines
4.2 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "code",
|
|
"metadata": {},
|
|
"source": [
|
|
"# code by Tae Hwan Jung @graykode\n",
|
|
"import torch\n",
|
|
"import torch.nn as nn\n",
|
|
"import torch.optim as optim\n",
|
|
"\n",
|
|
"def make_batch():\n",
|
|
" input_batch = []\n",
|
|
" target_batch = []\n",
|
|
"\n",
|
|
" for sen in sentences:\n",
|
|
" word = sen.split() # space tokenizer\n",
|
|
" input = [word_dict[n] for n in word[:-1]] # create (1~n-1) as input\n",
|
|
" target = word_dict[word[-1]] # create (n) as target, We usually call this 'casual language model'\n",
|
|
"\n",
|
|
" input_batch.append(input)\n",
|
|
" target_batch.append(target)\n",
|
|
"\n",
|
|
" return input_batch, target_batch\n",
|
|
"\n",
|
|
"# Model\n",
|
|
"class NNLM(nn.Module):\n",
|
|
" def __init__(self):\n",
|
|
" super(NNLM, self).__init__()\n",
|
|
" self.C = nn.Embedding(n_class, m)\n",
|
|
" self.H = nn.Linear(n_step * m, n_hidden, bias=False)\n",
|
|
" self.d = nn.Parameter(torch.ones(n_hidden))\n",
|
|
" self.U = nn.Linear(n_hidden, n_class, bias=False)\n",
|
|
" self.W = nn.Linear(n_step * m, n_class, bias=False)\n",
|
|
" self.b = nn.Parameter(torch.ones(n_class))\n",
|
|
"\n",
|
|
" def forward(self, X):\n",
|
|
" X = self.C(X) # X : [batch_size, n_step, m]\n",
|
|
" X = X.view(-1, n_step * m) # [batch_size, n_step * m]\n",
|
|
" tanh = torch.tanh(self.d + self.H(X)) # [batch_size, n_hidden]\n",
|
|
" output = self.b + self.W(X) + self.U(tanh) # [batch_size, n_class]\n",
|
|
" return output\n",
|
|
"\n",
|
|
"if __name__ == '__main__':\n",
|
|
" n_step = 2 # number of steps, n-1 in paper\n",
|
|
" n_hidden = 2 # number of hidden size, h in paper\n",
|
|
" m = 2 # embedding size, m in paper\n",
|
|
"\n",
|
|
" sentences = [\"i like dog\", \"i love coffee\", \"i hate milk\"]\n",
|
|
"\n",
|
|
" word_list = \" \".join(sentences).split()\n",
|
|
" word_list = list(set(word_list))\n",
|
|
" word_dict = {w: i for i, w in enumerate(word_list)}\n",
|
|
" number_dict = {i: w for i, w in enumerate(word_list)}\n",
|
|
" n_class = len(word_dict) # number of Vocabulary\n",
|
|
"\n",
|
|
" model = NNLM()\n",
|
|
"\n",
|
|
" criterion = nn.CrossEntropyLoss()\n",
|
|
" optimizer = optim.Adam(model.parameters(), lr=0.001)\n",
|
|
"\n",
|
|
" input_batch, target_batch = make_batch()\n",
|
|
" input_batch = torch.LongTensor(input_batch)\n",
|
|
" target_batch = torch.LongTensor(target_batch)\n",
|
|
"\n",
|
|
" # Training\n",
|
|
" for epoch in range(5000):\n",
|
|
" optimizer.zero_grad()\n",
|
|
" output = model(input_batch)\n",
|
|
"\n",
|
|
" # output : [batch_size, n_class], target_batch : [batch_size]\n",
|
|
" loss = criterion(output, target_batch)\n",
|
|
" if (epoch + 1) % 1000 == 0:\n",
|
|
" print('Epoch:', '%04d' % (epoch + 1), 'cost =', '{:.6f}'.format(loss))\n",
|
|
"\n",
|
|
" loss.backward()\n",
|
|
" optimizer.step()\n",
|
|
"\n",
|
|
" # Predict\n",
|
|
" predict = model(input_batch).data.max(1, keepdim=True)[1]\n",
|
|
"\n",
|
|
" # Test\n",
|
|
" print([sen.split()[:2] for sen in sentences], '->', [number_dict[n.item()] for n in predict.squeeze()])"
|
|
],
|
|
"outputs": [],
|
|
"execution_count": null
|
|
}
|
|
],
|
|
"metadata": {
|
|
"anaconda-cloud": {},
|
|
"kernelspec": {
|
|
"display_name": "Python 3",
|
|
"language": "python",
|
|
"name": "python3"
|
|
},
|
|
"language_info": {
|
|
"codemirror_mode": {
|
|
"name": "ipython",
|
|
"version": 3
|
|
},
|
|
"file_extension": ".py",
|
|
"mimetype": "text/x-python",
|
|
"name": "python",
|
|
"nbconvert_exporter": "python",
|
|
"pygments_lexer": "ipython3",
|
|
"version": "3.6.1"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 4
|
|
} |