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.

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

example run #2

Merged
merged 2 commits into from
Apr 10, 2024
Merged
Changes from 1 commit
Commits
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
Next Next commit
example run
kzaleskaa committed Apr 10, 2024
commit d17d02189ad5e78565e6e4ca19e471ca39676ea6
4 changes: 3 additions & 1 deletion README.md
Original file line number Diff line number Diff line change
@@ -11,9 +11,11 @@ ______________________________________________________________________

</div>

<img src="https://github.com/kzaleskaa/depth-estimation-with-compression/assets/62251989/747c72d8-e096-4113-9951-5886213187bc" />

## Description

This project entails the development and optimization of a depth estimation model based on a UNET architecture enhanced with **Bi-directional Feature Pyramid Network** (BIFPN) and **EfficientNet** components. This project was implemented within the scope of the "Neural Network Compression with Applications" subject.
This project entails the development and optimization of a depth estimation model based on a UNET architecture enhanced with **Bi-directional Feature Pyramid Network** (BIFPN) and **EfficientNet** components. The model is trained on the NYU Depth V2 dataset and evaluated on the Structural Similarity Index (SSIM) metric.

## Installation

13 changes: 2 additions & 11 deletions notebooks/data_analysis.ipynb
Original file line number Diff line number Diff line change
@@ -53,15 +53,6 @@
"df_train.shape, df_test.shape"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"50688 + 654"
]
},
{
"cell_type": "code",
"execution_count": null,
@@ -118,8 +109,8 @@
"metadata": {},
"outputs": [],
"source": [
"img_path = df_train.iloc[0][\"img\"]\n",
"depth_path = df_train.iloc[0][\"depth\"]\n",
"img_path = df_train.iloc[1150][\"img\"]\n",
"depth_path = df_train.iloc[1150][\"depth\"]\n",
"\n",
"visualize_example(img_path, depth_path)"
]
148 changes: 148 additions & 0 deletions notebooks/example_model_results.ipynb
Original file line number Diff line number Diff line change
@@ -0,0 +1,148 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import torch\n",
"import matplotlib.pyplot as plt\n",
"import pytorch_lightning as pl\n",
"from src.models.unet_module import UNETLitModule\n",
"from src.data.components.nyu_dataset import NYUDataset\n",
"from src.data.components.custom_transforms import NormalizeData, BilinearInterpolation\n",
"from torchvision.transforms import transforms"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"model_ckpt = \"./logs/train/runs/2024-04-06_18-37-38/checkpoints/epoch_015.ckpt\""
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"model = UNETLitModule.load_from_checkpoint(model_ckpt)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"model.eval()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"transforms_img = transforms.Compose([transforms.PILToTensor(), transforms.Resize((224, 224))])\n",
"\n",
"transforms_mask = transforms.Compose(\n",
" [\n",
" transforms.PILToTensor(),\n",
" NormalizeData(10_000 * (1 / 255)),\n",
" BilinearInterpolation((56, 56)),\n",
" ]\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"test_dataset = NYUDataset(\"nyu2_test.csv\", \"data/\", transforms_img, transforms_mask)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"outputs = []\n",
"\n",
"for i in range(10):\n",
" img, mask = test_dataset[i]\n",
" img = img.unsqueeze(0)\n",
" mask = mask.unsqueeze(0)\n",
" img = img.to(model.device)\n",
" out = model(img)\n",
" outputs.append(out)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"def visualize_result(img, mask, out):\n",
" _, axs = plt.subplots(1, 3)\n",
" axs[0].imshow(img.squeeze().permute(1, 2, 0))\n",
" axs[0].set_title(\"Input Image\")\n",
" axs[1].imshow(mask.squeeze())\n",
" axs[1].set_title(\"Ground Truth\")\n",
" axs[2].imshow(out.squeeze().detach().cpu())\n",
" axs[2].set_title(\"Predicted Mask\")\n",
"\n",
" for ax in axs:\n",
" ax.axis(\"off\")\n",
"\n",
" plt.show()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"for i in range(5):\n",
" visualize_result(test_dataset[i][0], test_dataset[i][1], outputs[i])"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "venv",
"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": "3.11.3"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
6 changes: 3 additions & 3 deletions src/data/depth_datamodule.py
Original file line number Diff line number Diff line change
@@ -156,7 +156,7 @@ def train_dataloader(self) -> DataLoader[Any]:
num_workers=self.hparams.num_workers,
pin_memory=self.hparams.pin_memory,
shuffle=True,
persistent_workers=True,
# persistent_workers=True,
)

def val_dataloader(self) -> DataLoader[Any]:
@@ -170,7 +170,7 @@ def val_dataloader(self) -> DataLoader[Any]:
num_workers=self.hparams.num_workers,
pin_memory=self.hparams.pin_memory,
shuffle=False,
persistent_workers=True,
# persistent_workers=True,
)

def test_dataloader(self) -> DataLoader[Any]:
@@ -184,7 +184,7 @@ def test_dataloader(self) -> DataLoader[Any]:
num_workers=self.hparams.num_workers,
pin_memory=self.hparams.pin_memory,
shuffle=False,
persistent_workers=True,
# persistent_workers=True,
)

def teardown(self, stage: Optional[str] = None) -> None: