Lottery-Ticket-Hypothesis-in-Pytorch

Lottery-Ticket-Hypothesis-in-Pytorch copied to clipboard

Bumps [numpy](https://github.com/numpy/numpy) from 1.17.2 to 1.22.0. Release notes Sourced from numpy's releases. v1.22.0 NumPy 1.22.0 Release Notes NumPy 1.22.0 is a big release featuring the work of 153 contributors spread...

dependabot[bot]

#rap_game

1

@rap_game @rap.fame @MAT'MICHAELLOZWA**  @MichaelloAngelo**

Monsamich

Can you give a hint on the expected runtime or parameter settings? I am trying to prune a VGG16 with the CIFAR10 dataset using the command below. I have started...

annahambi

Bumps [pillow](https://github.com/python-pillow/Pillow) from 6.2.0 to 9.0.1. Release notes Sourced from pillow's releases. 9.0.1 https://pillow.readthedocs.io/en/stable/releasenotes/9.0.1.html Changes In show_file, use os.remove to remove temporary images. CVE-2022-24303 #6010 [@​radarhere, @​hugovk] Restrict builtins within...

dependabot[bot]

Bumps [protobuf](https://github.com/protocolbuffers/protobuf) from 3.9.2 to 3.15.0. Release notes Sourced from protobuf's releases. Protocol Buffers v3.15.0 Protocol Compiler Optional fields for proto3 are enabled by default, and no longer require the...

dependabot[bot]

Every dataset is normalized with MNIST's mean and std dev

1

The `transform` used while loading every dataset (line 37, main.py) uses MNIST's mean and standard deviation. The correct values for normalizing CIFAR 10, etc are different.

npnbpb

Freeze pruned weights method not efficient

1

In 'main.py' line 257 - 262, the author used the following codes to freeze the pruned weights: for name, p in model.named_parameters(): if 'weight' in name: tensor = p.data.cpu().numpy() grad_tensor...

guoyuntu

I just installed the dependencies and tried to run the example `python3 main.py --prune_type=lt --arch_type=fc1 --dataset=mnist --prune_percent=10 --prune_iterations=35` and got the following error ``` Downloading http://yann.lecun.com/exdb/mnist/train-images-idx3-ubyte.gz to ../data/MNIST/raw/train-images-idx3-ubyte.gz Traceback (most...

FischerJo

Freezing Pruned weights smaller than 1e-6

3

In main.py #Freezing Pruned weights by making their gradients Zero grad_tensor = np.where(tensor < EPS, 0, grad_tensor) Does this also freeze the weights that have negative values? More than just...

yuezhixiong

The `prune_by_percentile` function defined in `main.py` uses layer-wise pruning for all models. While it is found in the original LTH paper that global pruning works better for larger convolutional models...

xhchrn