https://github.com/bit-bots/depth-estimation

https://github.com/bit-bots/depth-estimation

Repository

https://github.com/bit-bots/depth-estimation/blob/master/

# Supervised Depth Estimation with PyTorch

Original Repo: https://github.com/milesial/Pytorch-UNet

![image](https://user-images.githubusercontent.com/15075613/153616192-3a6f7825-907b-4d64-98f4-67cfe1a106f1.png)
![image](https://user-images.githubusercontent.com/15075613/153616132-672ab604-88eb-4719-8a58-d911a4c2d425.png)

![image](https://user-images.githubusercontent.com/15075613/153617219-18f7cefd-b415-4f34-b1f7-fc9dde87d510.png)
![image](https://user-images.githubusercontent.com/15075613/153617262-7f83517f-af66-4784-ae31-1173808b8b60.png)

## Description
This model was trained from scratch with the simulation part of the [TORSO-21 Dataset](https://github.com/bit-bots/TORSO_21_dataset) and predicts dense absolute depth estimations.

## Usage

### Training

```console
> python train.py -h
usage: train.py [-h] [--epochs E] [--batch-size B] [--learning-rate LR]
                [--load LOAD] [--scale SCALE] [--validation VAL] [--amp]

Train the UNet on images and target masks

optional arguments:
  -h, --help            show this help message and exit
  --epochs E, -e E      Number of epochs
  --batch-size B, -b B  Batch size
  --learning-rate LR, -l LR
                        Learning rate
  --load LOAD, -f LOAD  Load model from a .pth file
  --scale SCALE, -s SCALE
                        Downscaling factor of the images
  --validation VAL, -v VAL
                        Percent of the data that is used as validation (0-100)
  --amp                 Use mixed precision
```

By default, the `scale` is 0.5, so if you wish to obtain better results (but use more memory), set it to 1.

Automatic mixed precision is also available with the `--amp` flag. [Mixed precision](https://arxiv.org/abs/1710.03740) allows the model to use less memory and to be faster on recent GPUs by using FP16 arithmetic. Enabling AMP is recommended.


### Prediction

After training your model and saving it to `MODEL.pth`, you can easily test the output masks on your images via the CLI.

To predict a single image and save it:

`python predict.py -i image.jpg -o output.jpg`

To predict a multiple images and show them without saving them:

`python predict.py -i image1.jpg image2.jpg --viz --no-save`

```console
> python predict.py -h
usage: predict.py [-h] [--model FILE] --input INPUT [INPUT ...] 
                  [--output INPUT [INPUT ...]] [--viz] [--no-save]
                  [--mask-threshold MASK_THRESHOLD] [--scale SCALE]

Predict masks from input images

optional arguments:
  -h, --help            show this help message and exit
  --model FILE, -m FILE
                        Specify the file in which the model is stored
  --input INPUT [INPUT ...], -i INPUT [INPUT ...]
                        Filenames of input images
  --output INPUT [INPUT ...], -o INPUT [INPUT ...]
                        Filenames of output images
  --viz, -v             Visualize the images as they are processed
  --no-save, -n         Do not save the output masks
  --mask-threshold MASK_THRESHOLD, -t MASK_THRESHOLD
                        Minimum probability value to consider a mask pixel white
  --scale SCALE, -s SCALE
                        Scale factor for the input images
```
You can specify which model file to use with `--model MODEL.pth`.

## Weights & Biases

The training progress can be visualized in real-time using [Weights & Biases](https://wandb.ai/).  Loss curves, validation curves, weights and gradient histograms, as well as predicted masks are logged to the platform.

When launching a training, a link will be printed in the console. Click on it to go to your dashboard. If you have an existing W&B account, you can link it
 by setting the `WANDB_API_KEY` environment variable.

---

Original U-Net paper by Olaf Ronneberger, Philipp Fischer, Thomas Brox:

[U-Net: Convolutional Networks for Biomedical Image Segmentation](https://arxiv.org/abs/1505.04597)

![network architecture](https://i.imgur.com/jeDVpqF.png)

Owner

GitHub Events