musco-pytorch
musco-pytorch copied to clipboard
musco-ai
MUSCO: MUlti-Stage COmpression of neural networks
Like I already mentioned in [Issue 13](https://github.com/musco-ai/musco-pytorch/issues/13#issuecomment-812170929), the demo code seems to crash with an error. ``` from torchvision.models import resnet50 from flopco import FlopCo from musco.pytorch import CompressorVBMF, CompressorPR,...
I've tried to compress my resnet18 and failed. SVDDecomposedConvLayer has no min_rank field. I'm getting exception. ``` Anaconda3\envs\musco\lib\site-packages\musco\pytorch\compressor\decompositions\svd_layer.py in __init__(self, layer, layer_name, rank_selection, rank, pretrained, vbmf_weaken_factor, param_reduction_rate) 157 158 if...
In standardize_model was added new feature: some attributes wasn't copy from CustomLayer to nn.Sequntial. Now it fixed CP3DecomposedLayerConv1D was created in the same way as previous similar layers, but also...
Hi, could ResNet-18 on ILSVRC-12 validation dataset in 6.2 of your paper be released, which experience only 0.47 percent top-1 accuracy drop while achieving 2.42 flops reduction.
Hi author! Thx for ur sharing! I was just trying your iterative compression algorithms using vbmf for compressing the faster rcnn model (exactly the same code mentioned in your paper),...
Hi, users are unable to run **_musco-pytorch_** due to dependency conflict with _**numpy**_ package. As shown in the following full dependency graph of **_musco-pytorch_**, **_musco-pytorch_** requires **_numpy *_**，while **_scikit-tensor-py3_** requires...
when I run the compressed VGG16 model, the runtime is even longer than VGG16 before compressed. how to run the compressed models getting the same results (Table 5) in the...
Relying on copy.deepcopy to copy the model in: - compression_conf_fc.ipynb - compress.py Does not work for Faster R-CNN models which use mixed serialization & non-script modules. This results in the...
