SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Updated Tokenw ise in print statement to Token wise

Browse Source
This commit is contained in:
Param bhavsar
2020-03-08 15:10:22 +05:30
committed by Julien Chaumond
parent e03129ad44
commit b29fed790b
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
notebooks/02-transformers.ipynb
View File

@@ -238,7 +238,7 @@
"Tokens: ['This', 'is', 'an', 'input', 'example']\n",
"Tokens id: [1188, 1110, 1126, 7758, 1859]\n",
"Tokens PyTorch: tensor([[ 101, 1188, 1110, 1126, 7758, 1859, 102]])\n",
"Tokenw ise output: torch.Size([1, 7, 768]), Pooled output: torch.Size([1, 768])\n"
"Token wise output: torch.Size([1, 7, 768]), Pooled output: torch.Size([1, 768])\n"
]
}
],
@@ -261,7 +261,7 @@
"\n",
"# Now we're ready to go through BERT with out input\n",
"outputs, pooled = model(tokens_pt)\n",
"print(\"Tokenw ise output: {}, Pooled output: {}\".format(outputs.shape, pooled.shape))"
"print(\"Token wise output: {}, Pooled output: {}\".format(outputs.shape, pooled.shape))"
]
},
{