pretrained-models.pytorch
pretrained-models.pytorch copied to clipboard
Cadene
Pretrained ConvNets for pytorch: NASNet, ResNeXt, ResNet, InceptionV4, InceptionResnetV2, Xception, DPN, etc.
Please,how to train the Nasnet on my own datasets?
Hi. May I ask for SENet154 model in repo, the input needs to be normalized both by: 1- First dividing by 255 (having a range between 0-1) 2- Normalizing by...
(1)when i run the architecture squeezenet1_0 and squeezenet1_1 ,I met the problem above. (2)then I print the shape of output and target as below: output.shape torch.Size([20, 1000, 1, 1]) target.shape...
When using the non-pretrained version ``` model = pretrainedmodels.inceptionv4( num_classes=1000 , pretrained=False ) ``` Something like does this does not initialise variables like input_range and others. I would like to...
Hello, we tried to reproduce the ResNet50 inference, but only got 73+% top1, it is still far from SOTA(75%) and your data(76%). Any comments here? Details: torch (1.1.0a0+a3933b8) torchvision (0.2.2.post3)...
* Deprecation warnings are raised due to invalid escape sequences. This can be fixed by using raw strings or escaping the literals. pyupgrade also helps in automatic conversion : https://github.com/asottile/pyupgrade/...
Just need to have hubconf according to torch.hub documentation. Now we can do `torch.hub.list('Cadene/pretrained-models.pytorch')`
Guys from Amazon released new model: ResNeSt. Code is here: https://github.com/zhanghang1989/ResNeSt If you think it'll be useful, I can port code and pertained models from this repo to this repo's...
Regarding: pretrainedmodels/models/xception.py Normalizing an image as below will result in a range -1..1 (not 0..1 as specified). Please can you confirm if the input range should be -1..1 or 0..1?...
