pretrained-models.pytorch
pretrained-models.pytorch copied to clipboard
Cadene
Pretrained ConvNets for pytorch: NASNet, ResNeXt, ResNet, InceptionV4, InceptionResnetV2, Xception, DPN, etc.
As I know, the pytorch supply the torch.nn.LocalResponseNorm, why you write it by yourself?
SqueezeNext: Hardware-Aware Neural Network Design Could you please suport the SqueezeNet？
Dear @Cadene, Do you have any plan to re-implement or convert the **[Shake-shake regularization Net](https://github.com/xgastaldi/shake-shake)** into PyTorch and your nice repository? To the best of my knowledge, it has the...
Would be possible to have the 3d cnn pretrained model? Thanks
https://github.com/Cadene/pretrained-models.pytorch/blob/8aae3d8f1135b6b13fed79c1d431e3449fdbf6e0/pretrainedmodels/models/fbresnet.py#L152 In fbresnet.py,the forward method contains irrelevant attributes. self.conv1_input = x.clone() in forward is not used, What is the function of this attribute?
Please add the module 'six' to your requirements, sinc you use it in 'pretrainedmodels/datasets/voc.py(6)'.
新的torchvision0.14在加载模型的时候已经弃用了pretrained, 而是使用weights, 当我在加载resnet50的时候出现的如下的警告。 ``` > model = pretrainedmodels.__dict__["resnet50"]() ...\torchvision\models\_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead. warnings.warn( ...\torchvision\models\_utils.py:223:...
could i get the pretrained image net for grayscale version? i used the RadImageNet for medical image fine tune, but the result is very poor, is there anyone experienced the...
As #197 and #206 have pointed out, there are some inconsistencies with the implementation of Inception-ResNet-v2 and [the paper](https://arxiv.org/pdf/1602.07261). @agsourav highlights that the stem seems to be that of Inception-ResNet-v1...
