dmarnerides / Pydlt
Licence: bsd-3-clause-clear
PyTorch based Deep Learning Toolbox
Stars: ✭ 208
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Pydlt
Sal eval toolbox
evaluation toolbox for salient object detection
Stars: ✭ 105 (-49.52%)
Mutual labels: toolbox
D Tools
d-tools is a toolbox for developers.Formatter, Base64, Regex test,Host manager and so on.
Stars: ✭ 131 (-37.02%)
Mutual labels: toolbox
Kitematic
Visual Docker Container Management on Mac & Windows
Stars: ✭ 12,252 (+5790.38%)
Mutual labels: toolbox
Meta Blocks
A modular toolbox for meta-learning research with a focus on speed and reproducibility.
Stars: ✭ 110 (-47.12%)
Mutual labels: toolbox
Blender Toolbox Qt
Attempt to recreate a blender like toolbox in Qt
Stars: ✭ 98 (-52.88%)
Mutual labels: toolbox
Pixelssl
A PyTorch-based Semi-Supervised Learning (SSL) Codebase for Pixel-wise (Pixel) Vision Tasks
Stars: ✭ 130 (-37.5%)
Mutual labels: toolbox
Yakutils
🐃 Yet another toolbox of Python 3 helper functions.
Stars: ✭ 111 (-46.63%)
Mutual labels: toolbox
Auquan Toolbox Python
Backtesting toolbox for trading strategies - DEPRECATED
Stars: ✭ 108 (-48.08%)
Mutual labels: toolbox
Deeplabcut
Official implementation of DeepLabCut: Markerless pose estimation of user-defined features with deep learning for all animals incl. humans
Stars: ✭ 2,550 (+1125.96%)
Mutual labels: toolbox
Laser Camera Calibration Toolbox
A Laser-Camera Calibration Toolbox extending from that at http://www.cs.cmu.edu/~ranjith/lcct.html
Stars: ✭ 99 (-52.4%)
Mutual labels: toolbox
Ui Stack
🔍 A Chrome extension that lets you inspect a website's framework and libraries
Stars: ✭ 178 (-14.42%)
Mutual labels: toolbox
Low Rank Bilinear Pooling
Fine-grained classification via second order statistics in a compact end-to-end trainable model
Stars: ✭ 145 (-30.29%)
Mutual labels: toolbox
PyTorch Deep Learning Toolbox
PyDLT is a set of tools aimed to make experimenting with PyTorch easier (than it already is).
Features
- Trainers (currently supporting Vanilla, VanillaGAN, WGAN-GP, BEGAN, FisherGAN)
trainer = dlt.train.VanillaGANTrainer(generator, discriminator, g_optim, d_optim)
for batch, (prediction, losses) in trainer(data_loader):
# Training happens in the iterator and relevant results are returned for each step
- Built in configurable parser with arguments.
opt = dlt.config.parse() # Has built in options (can add extra)
print('Some Settings: ', opt.experiment_name, opt.batch_size, opt.lr)
- Configuration files support and parser compatible functions.
$ python main.py @settings.cfg
Some Settings: config_test 32 0.0001
- HDR imaging support (.hdr, .exr, and .pfm formats)
img = dlt.hdr.imread('test.pfm')
dlt.hdr.imwrite('test.exr', img)
- Checkpointing of (torch serializable) objects; Network state dicts supported.
data_chkp = Checkpointer('data')
data_chkp.save(np.array([1,2,3]))
a = data_chkp.load()
- Image operations and easy conversions between multiple library views (torch, cv, plt)
img = cv2.imread('image.jpg') # Height x Width x Channels - BGR
dlt.viz.imshow(img, view='cv') # Height x Width x Channels - RGB
tensor_with_torch_view = cv2torch(img) # Channels x Height x Width - RGB
- Easy visualization (and make_grid supporting Arrays, Tensors, Variables and lists)
for batch, (prediction, loss) in trainer(loader):
grid = dlt.util.make_grid([ batch[0], batch[1], prediction], size(3, opt.batch_size))
dlt.viz.imshow(grid, pause=0.01, title='Training Progress')
- Parameter and input/outputs/gradients layer visualization.
net = nn.Sequential(nn.Linear(10, 10))
dlt.viz.modules.forward_hook(net, [nn.Linear], tag='layer_outputs', histogram=False)
net(Variable(torch.Tensor(3,10)))
- CSV Logger.
log = dlt.util.Logger('losses', ['train_loss', 'val_loss'])
log({'train_loss': 10, 'val_loss':20})
- Command line tool for easy plotting of CSV files (with live updating).
$ dlt-plot --file losses.csv train_loss val_loss --refresh 5 --loglog True --tail 100
- A minimal Progress bar (with global on/off switch).
from dlt.util import barit
barit.silent = False # Default is False
for batch in barit(loader, start='Loading'):
pass
Installation
Make sure you have PyTorch installed. OpenCV is also required:
conda install -c menpo opencv
conda install (recommended):
conda install -c demetris pydlt
From source:
git clone https://github.com/dmarnerides/pydlt.git
cd pydlt
python setup.py install
About
I created this toolbox while learning Python and PyTorch, after working with (Lua) Torch, to help speed up experiment prototyping.
If you notice something is wrong or missing please do a pull request or open up an issue.
Contact
Demetris Marnerides: [email protected]
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].