search

he-y / soft-filter-pruning

Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks
https://arxiv.org/abs/1808.06866
374 stars 74 forks source link

how to obtain the pruned small model(inceptionv3)? #11

Closed raninbowlalala closed 5 years ago

raninbowlalala commented 5 years ago

Hello, I use your method in InceptionV3, which I download from https://download.pytorch.org/models/inception_v3_google-1a9a5a14.pth. After 100 epoch train, I got the best.inception_v3.pth.tar. Then I want to obtain the samll modle. I saw the issue , but I still don't know how to obtain. Can you help me? Thank you!

he-y commented 5 years ago

Please refer to the released pruned model and instruction for the model. You can find the construction of pruned model here.

he-y commented 5 years ago

Hi, we have released the conversion code to delete zeros and obtain small model, which might help you.

Please refer to the conversion code here. The corresponding explanation is here.

raninbowlalala commented 5 years ago

I will try your code, thank you!

zhanghongruiupup commented 4 years ago

请参阅发布修剪的模型和指令的模式。 您可以在此处找到修剪模型的构造。

请参阅发布修剪的模型和指令的模式。 您可以在此处找到修剪模型的构造。

hi,resnet50_small error,Lack of index and bn_value info:
model = ResNet_small(Bottleneck, [3, 4, 6, 3], **kwargs) TypeError: init() missing 2 required positional arguments: 'index' and 'bn_value'