pretrained-models.pytorch
pretrained-models.pytorch copied to clipboard
Cadene
Pretrained ConvNets for pytorch: NASNet, ResNeXt, ResNet, InceptionV4, InceptionResnetV2, Xception, DPN, etc.
Best practices to import with "*", also fixes my use case of automatically generate lookup dictionary by having the names of the models being exported: ``` from pretrainedmodels.models import __all__...
hi can anyone help me solve this problem: `Traceback (most recent call last): File "", line 1, in runfile('C:/Users/Windows10/Downloads/pretrained-models.pytorch-master/examples/voc2007_extract.py', wdir='C:/Users/Windows10/Downloads/pretrained-models.pytorch-master/examples') File "C:\Users\Windows10\Anaconda3\envs\New\lib\site-packages\spyder_kernels\customize\spydercustomize.py", line 827, in runfile execfile(filename, namespace) File "C:\Users\Windows10\Anaconda3\envs\New\lib\site-packages\spyder_kernels\customize\spydercustomize.py",...
`model = se_resnext101_32x4d(pretrained='se_resnext101_32x4d-3b2fe3d8.pth')` KeyError: 'se_resnext101_32x4d-3b2fe3d8.pth' I don't kown how to use it, who can help me
Code and pretrained up to B3 https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet
hello, I am trying to train resnet50 based on pytorch, however, I only got 57% top1 validation acuracy on imagenet, which is far from SOTA. I tried to do inference...
Hi @Cadene Thanks for your great works for providing imagenet pre-trained models. I was wondering if HRNet is on your mind? https://github.com/HRNet/HRNet-Image-Classification Best, Ke
Hi Cadene Thanks for your splendid works for creating so useful pretrained pytorch models. I was wondering if VGGFace2 is on your mind? BR Abhik
adaptiveAvgPoolWidth should be an int and not a tensor put .item() in line 302 of pretrainedmodels/models/inceptionv4.py the following ``` adaptiveAvgPoolWidth = features.shape[2].item()
I tried to install this package from repo but got EOF error from runing python setup.py install Could you help me to figure it out? ERROR: Traceback (most recent call...
This fixes se_resnext models where `math.floor` is used to compute layer width. In Python 3 this outputs an integer, but in 2.7 this outputs a float. This fix makes sure...
