Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Update AnnotatedTransformer.ipynb #115

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Update AnnotatedTransformer.ipynb #115

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
138 changes: 22 additions & 116 deletions AnnotatedTransformer.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1514,37 +1514,13 @@
"output_type": "stream",
"text": [
"Example Untrained Model Prediction: tensor([[ 0, 10, 0, 10, 0, 0, 0, 0, 0, 10]])\n",
"Example Untrained Model Prediction: tensor([[ 0, 8, 1, 10, 0, 8, 1, 10, 0, 8]])\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Example Untrained Model Prediction: tensor([[ 0, 8, 1, 10, 0, 8, 1, 10, 0, 8]])\n",
"Example Untrained Model Prediction: tensor([[ 0, 9, 0, 10, 4, 5, 3, 2, 4, 3]])\n",
"Example Untrained Model Prediction: tensor([[0, 5, 5, 5, 5, 5, 5, 5, 5, 5]])\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Example Untrained Model Prediction: tensor([[0, 5, 5, 5, 5, 5, 5, 5, 5, 5]])\n",
"Example Untrained Model Prediction: tensor([[0, 2, 8, 3, 8, 5, 0, 4, 0, 4]])\n",
"Example Untrained Model Prediction: tensor([[ 0, 10, 3, 10, 2, 9, 0, 3, 10, 3]])\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Example Untrained Model Prediction: tensor([[ 0, 10, 3, 10, 2, 9, 0, 3, 10, 3]])\n",
"Example Untrained Model Prediction: tensor([[0, 3, 3, 3, 3, 3, 3, 3, 3, 3]])\n",
"Example Untrained Model Prediction: tensor([[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]])\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Example Untrained Model Prediction: tensor([[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]])\n",
"Example Untrained Model Prediction: tensor([[0, 3, 2, 2, 2, 4, 0, 3, 1, 3]])\n",
"Example Untrained Model Prediction: tensor([[0, 6, 6, 6, 6, 6, 6, 6, 6, 6]])\n"
]
Expand Down Expand Up @@ -2209,7 +2185,9 @@
" [0, 0.2, 0.7, 0.1, 0],\n",
" ]\n",
" )\n",
" crit(x=predict.log(), target=torch.LongTensor([2, 1, 0, 3, 3]))\n",
" crit(x=log_softmax(predict), target=torch.LongTensor([2, 1, 0, 3, 3]))\n",
" \n",
" \n",
" LS_data = pd.concat(\n",
" [\n",
" pd.DataFrame(\n",
Expand Down Expand Up @@ -2337,8 +2315,8 @@
"def loss(x, crit):\n",
" d = x + 3 * 1\n",
" predict = torch.FloatTensor([[0, x / d, 1 / d, 1 / d, 1 / d]])\n",
" return crit(predict.log(), torch.LongTensor([1])).data\n",
"\n",
" return crit( log_softmax(predict), torch.LongTensor([1])).data\n",
" \n",
"\n",
"def penalization_visualization():\n",
" crit = LabelSmoothing(5, 0, 0.1)\n",
Expand Down Expand Up @@ -3566,38 +3544,14 @@
"name": "stdout",
"output_type": "stream",
"text": [
"Preparing Data ...\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Loading Trained Model ...\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Preparing Data ...\n",
"Loading Trained Model ...\n",
"Checking Model Outputs:\n",
"\n",
"Example 0 ========\n",
"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"Source Text (Input) : <s> Mehrere Kinder heben die Hände , während sie auf einem bunten Teppich in einem Klassenzimmer sitzen . </s>\n",
"Target Text (Ground Truth) : <s> Several children are raising their hands while sitting on a colorful rug in a classroom . </s>\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Target Text (Ground Truth) : <s> Several children are raising their hands while sitting on a colorful rug in a classroom . </s>\n",
"Model Output : <s> A group of children are in their hands while sitting on a colorful carpet . </s>\n"
]
},
Expand Down Expand Up @@ -3716,38 +3670,14 @@
"name": "stdout",
"output_type": "stream",
"text": [
"Preparing Data ...\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Loading Trained Model ...\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Preparing Data ...\n",
"Loading Trained Model ...\n",
"Checking Model Outputs:\n",
"\n",
"Example 0 ========\n",
"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"Source Text (Input) : <s> Drei Menschen wandern auf einem stark verschneiten Weg . </s>\n",
"Target Text (Ground Truth) : <s> A <unk> of people are hiking throughout a heavily snowed path . </s>\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Target Text (Ground Truth) : <s> A <unk> of people are hiking throughout a heavily snowed path . </s>\n",
"Model Output : <s> Three people hiking on a busy <unk> . </s>\n"
]
},
Expand Down Expand Up @@ -3869,38 +3799,14 @@
"name": "stdout",
"output_type": "stream",
"text": [
"Preparing Data ...\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Loading Trained Model ...\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Preparing Data ...\n",
"Loading Trained Model ...\n",
"Checking Model Outputs:\n",
"\n",
"Example 0 ========\n",
"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"Source Text (Input) : <s> Baby sieht sich die Blätter am Zweig eines Baumes an . </s>\n",
"Target Text (Ground Truth) : <s> Baby looking at the leaves on a branch of a tree . </s>\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Target Text (Ground Truth) : <s> Baby looking at the leaves on a branch of a tree . </s>\n",
"Model Output : <s> A baby is looking at the leaves at a tree . </s>\n"
]
},
Expand Down Expand Up @@ -4035,7 +3941,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.8.10"
"version": "3.10.9"
}
},
"nbformat": 4,
Expand Down