168 lines
8.3 KiB
Plaintext
168 lines
8.3 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"id": "d42ddd87",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import torch\n",
|
|
"from torch import nn"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"id": "dc73124c",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"vocab_size = 20000\n",
|
|
"embed_size = 100\n",
|
|
"\n",
|
|
"class SimpleTrigramNeuralLanguageModel(nn.Module):\n",
|
|
" def __init__(self, vocabulary_size, embedding_size):\n",
|
|
" super(SimpleTrigramNeuralLanguageModel, self).__init__()\n",
|
|
" self.embedding = nn.Embedding(vocabulary_size, embedding_size)\n",
|
|
" self.linear = nn.Linear(embedding_size, vocabulary_size)\n",
|
|
"\n",
|
|
" def forward(self, x):\n",
|
|
" x = self.embedding(x)\n",
|
|
" x = self.linear(x)\n",
|
|
" x = torch.softmax(x, dim=1)\n",
|
|
" return x"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"id": "569b4c88",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import regex as re\n",
|
|
"from itertools import islice, chain\n",
|
|
"from torchtext.vocab import build_vocab_from_iterator\n",
|
|
"from torch.utils.data import IterableDataset\n",
|
|
"\n",
|
|
"def get_words_from_line(line):\n",
|
|
" line = line.rstrip()\n",
|
|
" yield '<s>'\n",
|
|
" for m in re.finditer(r'[\\p{L}0-9\\*]+|\\p{P}+', line):\n",
|
|
" yield m.group(0).lower()\n",
|
|
" yield '</s>'\n",
|
|
"\n",
|
|
"def get_word_lines_from_file(file_name):\n",
|
|
" with open(file_name, 'r') as fh:\n",
|
|
" for line in fh:\n",
|
|
" yield get_words_from_line(line)\n",
|
|
" \n",
|
|
"def look_ahead_iterator(gen):\n",
|
|
" prev = None\n",
|
|
" for item in gen:\n",
|
|
" if prev is not None:\n",
|
|
" yield (prev, item)\n",
|
|
" prev = item"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"id": "f95cb913",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"class Bigrams(IterableDataset):\n",
|
|
" def __init__(self, text_file, vocabulary_size):\n",
|
|
" self.vocab = build_vocab_from_iterator(\n",
|
|
" get_word_lines_from_file(text_file),\n",
|
|
" max_tokens = vocabulary_size,\n",
|
|
" specials = ['<unk>']\n",
|
|
" )\n",
|
|
" self.vocab.set_default_index(self.vocab['<unk>'])\n",
|
|
" self.vocabulary_size = vocabulary_size\n",
|
|
" self.text_file = text_file\n",
|
|
"\n",
|
|
" def __iter__(self):\n",
|
|
" return look_ahead_iterator((self.vocab[t] for t in chain.from_iterable(get_word_lines_from_file(self.text_file))))"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 6,
|
|
"id": "7a51f2b1",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"ename": "NameError",
|
|
"evalue": "name 'SimpleBigramNeuralLanguageModel' is not defined",
|
|
"output_type": "error",
|
|
"traceback": [
|
|
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
|
|
"\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)",
|
|
"\u001b[0;32m/tmp/ipykernel_16179/3272155308.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m 3\u001b[0m \u001b[0mdevice\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m'cuda'\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 4\u001b[0m \u001b[0mtrain_dataset\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mBigrams\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'europarl.txt'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mvocab_size\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 5\u001b[0;31m \u001b[0mmodel\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mSimpleTrigramNeuralLanguageModel\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mvocab_size\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0membed_size\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mto\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdevice\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 6\u001b[0m \u001b[0mdata\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mDataLoader\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtrain_dataset\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mbatch_size\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m2000\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 7\u001b[0m \u001b[0moptimizer\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtorch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0moptim\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mAdam\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmodel\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mparameters\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
|
|
"\u001b[0;32m/tmp/ipykernel_16179/1892442743.py\u001b[0m in \u001b[0;36m__init__\u001b[0;34m(self, vocabulary_size, embedding_size)\u001b[0m\n\u001b[1;32m 4\u001b[0m \u001b[0;32mclass\u001b[0m \u001b[0mSimpleTrigramNeuralLanguageModel\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnn\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mModule\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 5\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0m__init__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mvocabulary_size\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0membedding_size\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 6\u001b[0;31m \u001b[0msuper\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mSimpleBigramNeuralLanguageModel\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__init__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 7\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0membedding\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnn\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mEmbedding\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mvocabulary_size\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0membedding_size\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 8\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlinear\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnn\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mLinear\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0membedding_size\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mvocabulary_size\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
|
|
"\u001b[0;31mNameError\u001b[0m: name 'SimpleBigramNeuralLanguageModel' is not defined"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"from torch.utils.data import DataLoader\n",
|
|
"\n",
|
|
"device = 'cuda'\n",
|
|
"train_dataset = Bigrams('europarl.txt', vocab_size)\n",
|
|
"model = SimpleTrigramNeuralLanguageModel(vocab_size, embed_size).to(device)\n",
|
|
"data = DataLoader(train_dataset, batch_size=2000)\n",
|
|
"optimizer = torch.optim.Adam(model.parameters())\n",
|
|
"criterion = torch.nn.NLLLoss()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "474194ae",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"for epoch in range(1):\n",
|
|
" model.train()\n",
|
|
" for x, y in data:\n",
|
|
" x = x.to(device)\n",
|
|
" y = y.to(device)\n",
|
|
" optimizer.zero_grad()\n",
|
|
" outputs = model(x)\n",
|
|
" loss = criterion(torch.log(outputs), y)\n",
|
|
" if step % 100 == 0:\n",
|
|
" print(step, loss)\n",
|
|
" step += 1\n",
|
|
" loss.backward()\n",
|
|
" optimizer.step()\n",
|
|
" \n",
|
|
"torch.save(model.state_dict(), 'model/model1.bin')"
|
|
]
|
|
}
|
|
],
|
|
"metadata": {
|
|
"kernelspec": {
|
|
"display_name": "Python 3 (ipykernel)",
|
|
"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": "3.8.10"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 5
|
|
}
|