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

Jump to bottom

Enhance/update meta-sl #77

Merged
merged 16 commits into from
Jun 19, 2022
Merged

Enhance/update meta-sl #77

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
16 commits
Select commit Hold shift + click to select a range
ccb5c13
..
dongminlee94 Jun 18, 2022
5f8ecc7
..
dongminlee94 Jun 18, 2022
92b434b
..
dongminlee94 Jun 18, 2022
f12f7e5
..
dongminlee94 Jun 18, 2022
e463daa
..
dongminlee94 Jun 18, 2022
b3530dc
.
dongminlee94 Jun 18, 2022
0779a01
.
dongminlee94 Jun 18, 2022
c961d0a
.
dongminlee94 Jun 18, 2022
e443bb5
.
dongminlee94 Jun 18, 2022
e7aaddb
.
dongminlee94 Jun 18, 2022
4a0ebaa
.
dongminlee94 Jun 18, 2022
155a3a5
.
dongminlee94 Jun 19, 2022
8cafdcb
.
dongminlee94 Jun 19, 2022
f1f40e2
.
dongminlee94 Jun 19, 2022
cbe268b
.
dongminlee94 Jun 19, 2022
ee3717b
.
dongminlee94 Jun 19, 2022
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
Prev Previous commit
Next Next commit
.
  • Loading branch information
@dongminlee94
dongminlee94 committed Jun 19, 2022
commit f1f40e25ced6bdac6b7a6c862007531f80c6daf6
108 changes: 52 additions & 56 deletions src/meta_sl/metric-based/matching_network.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -75,60 +75,6 @@
" return train_dataloader, val_dataloader, test_dataloader"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "akpdFZpQAFih"
},
"outputs": [],
"source": [
"def save_model(output_folder: str, model: nn.Module, title: str) -> None:\n",
" if not os.path.isdir(output_folder):\n",
" os.mkdir(output_folder)\n",
" filename = os.path.join(output_folder, title)\n",
"\n",
" with open(filename, \"wb\") as f:\n",
" state_dict = model.state_dict()\n",
" torch.save(state_dict, f)\n",
" print(\"Model is saved in\", filename)\n",
"\n",
"\n",
"def load_model(output_folder: str, model: nn.Module, title: str) -> None:\n",
" filename = os.path.join(output_folder, title)\n",
" model.load_state_dict(torch.load(filename))\n",
" print(\"Model is loaded\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "ofLJ458NAIOK"
},
"outputs": [],
"source": [
"def print_graph(\n",
" train_accuracies: List[float],\n",
" val_accuracies: List[float],\n",
" train_losses: List[float],\n",
" val_losses: List[float],\n",
") -> None:\n",
" fig, axs = plt.subplots(1, 2, figsize=(14, 6))\n",
"\n",
" axs[0].plot(train_accuracies, label=\"train_acc\")\n",
" axs[0].plot(val_accuracies, label=\"test_acc\")\n",
" axs[0].set_title(\"Accuracy\")\n",
" axs[0].legend()\n",
"\n",
" axs[1].plot(train_losses, label=\"train_loss\")\n",
" axs[1].plot(val_losses, label=\"test_loss\")\n",
" axs[1].set_title(\"Loss\")\n",
" axs[1].legend()\n",
"\n",
" fig.show()"
]
},
{
"cell_type": "code",
"execution_count": null,
Expand Down Expand Up @@ -264,7 +210,7 @@
" num_ways: int,\n",
" device: str,\n",
" task_batch: Dict[str, List[torch.Tensor]],\n",
" model: nn.Module,\n",
" model: MatchingNet,\n",
" criterion: nn.CrossEntropyLoss,\n",
" optimizer: torch.optim.Adam,\n",
") -> Tuple[float, float]:\n",
Expand Down Expand Up @@ -306,7 +252,7 @@
" num_ways: int,\n",
" device: str,\n",
" task_batch: Dict[str, List[torch.Tensor]],\n",
" model: nn.Module,\n",
" model: MatchingNet,\n",
" criterion: nn.CrossEntropyLoss,\n",
") -> Tuple[float, float]:\n",
" model.eval()\n",
Expand All @@ -329,6 +275,56 @@
" return accuracy.item(), loss.item()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"def save_model(output_folder: str, model: MatchingNet, title: str) -> None:\n",
" if not os.path.isdir(output_folder):\n",
" os.mkdir(output_folder)\n",
" filename = os.path.join(output_folder, title)\n",
"\n",
" with open(filename, \"wb\") as f:\n",
" state_dict = model.state_dict()\n",
" torch.save(state_dict, f)\n",
" print(\"Model is saved in\", filename)\n",
"\n",
"\n",
"def load_model(output_folder: str, model: MatchingNet, title: str) -> None:\n",
" filename = os.path.join(output_folder, title)\n",
" model.load_state_dict(torch.load(filename))\n",
" print(\"Model is loaded\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"def print_graph(\n",
" train_accuracies: List[float],\n",
" val_accuracies: List[float],\n",
" train_losses: List[float],\n",
" val_losses: List[float],\n",
") -> None:\n",
" fig, axs = plt.subplots(1, 2, figsize=(14, 6))\n",
"\n",
" axs[0].plot(train_accuracies, label=\"train_acc\")\n",
" axs[0].plot(val_accuracies, label=\"test_acc\")\n",
" axs[0].set_title(\"Accuracy\")\n",
" axs[0].legend()\n",
"\n",
" axs[1].plot(train_losses, label=\"train_loss\")\n",
" axs[1].plot(val_losses, label=\"test_loss\")\n",
" axs[1].set_title(\"Loss\")\n",
" axs[1].legend()\n",
"\n",
" fig.show()"
]
},
{
"cell_type": "code",
"execution_count": null,
Expand Down
108 changes: 52 additions & 56 deletions src/meta_sl/metric-based/prototypical_network.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -75,60 +75,6 @@
" return train_dataloader, val_dataloader, test_dataloader"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "1YZB1tTtUivT"
},
"outputs": [],
"source": [
"def save_model(output_folder: str, model: nn.Module, title: str) -> None:\n",
" if not os.path.isdir(output_folder):\n",
" os.mkdir(output_folder)\n",
" filename = os.path.join(output_folder, title)\n",
"\n",
" with open(filename, \"wb\") as f:\n",
" state_dict = model.state_dict()\n",
" torch.save(state_dict, f)\n",
" print(\"Model is saved in\", filename)\n",
"\n",
"\n",
"def load_model(output_folder: str, model: nn.Module, title: str) -> None:\n",
" filename = os.path.join(output_folder, title)\n",
" model.load_state_dict(torch.load(filename))\n",
" print(\"Model is loaded\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "8Q1AMYvaUmtX"
},
"outputs": [],
"source": [
"def print_graph(\n",
" train_accuracies: List[float],\n",
" val_accuracies: List[float],\n",
" train_losses: List[float],\n",
" val_losses: List[float],\n",
") -> None:\n",
" fig, axs = plt.subplots(1, 2, figsize=(14, 6))\n",
"\n",
" axs[0].plot(train_accuracies, label=\"train_acc\")\n",
" axs[0].plot(val_accuracies, label=\"test_acc\")\n",
" axs[0].set_title(\"Accuracy\")\n",
" axs[0].legend()\n",
"\n",
" axs[1].plot(train_losses, label=\"train_loss\")\n",
" axs[1].plot(val_losses, label=\"test_loss\")\n",
" axs[1].set_title(\"Loss\")\n",
" axs[1].legend()\n",
"\n",
" fig.show()"
]
},
{
"cell_type": "code",
"execution_count": null,
Expand Down Expand Up @@ -200,7 +146,7 @@
"def train_proto(\n",
" device: str,\n",
" task_batch: Dict[str, List[torch.Tensor]],\n",
" model: nn.Module,\n",
" model: PrototypicalNet,\n",
" criterion: nn.CrossEntropyLoss,\n",
" optimizer: torch.optim.Adam,\n",
") -> Tuple[float, float]:\n",
Expand Down Expand Up @@ -239,7 +185,7 @@
"def test_proto(\n",
" device: str,\n",
" task_batch: Dict[str, List[torch.Tensor]],\n",
" model: nn.Module,\n",
" model: PrototypicalNet,\n",
" criterion: nn.CrossEntropyLoss,\n",
") -> Tuple[float, float]:\n",
" model.eval()\n",
Expand All @@ -260,6 +206,56 @@
" return accuracy.item(), loss.item()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"def save_model(output_folder: str, model: PrototypicalNet, title: str) -> None:\n",
" if not os.path.isdir(output_folder):\n",
" os.mkdir(output_folder)\n",
" filename = os.path.join(output_folder, title)\n",
"\n",
" with open(filename, \"wb\") as f:\n",
" state_dict = model.state_dict()\n",
" torch.save(state_dict, f)\n",
" print(\"Model is saved in\", filename)\n",
"\n",
"\n",
"def load_model(output_folder: str, model: PrototypicalNet, title: str) -> None:\n",
" filename = os.path.join(output_folder, title)\n",
" model.load_state_dict(torch.load(filename))\n",
" print(\"Model is loaded\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"def print_graph(\n",
" train_accuracies: List[float],\n",
" val_accuracies: List[float],\n",
" train_losses: List[float],\n",
" val_losses: List[float],\n",
") -> None:\n",
" fig, axs = plt.subplots(1, 2, figsize=(14, 6))\n",
"\n",
" axs[0].plot(train_accuracies, label=\"train_acc\")\n",
" axs[0].plot(val_accuracies, label=\"test_acc\")\n",
" axs[0].set_title(\"Accuracy\")\n",
" axs[0].legend()\n",
"\n",
" axs[1].plot(train_losses, label=\"train_loss\")\n",
" axs[1].plot(val_losses, label=\"test_loss\")\n",
" axs[1].set_title(\"Loss\")\n",
" axs[1].legend()\n",
"\n",
" fig.show()"
]
},
{
"cell_type": "code",
"execution_count": null,
Expand Down
Loading