pretrained-models.pytorch

pretrained-models.pytorch copied to clipboard

Adaptive pooling for senet

2

Needed to add this line to make it work on other resolution images.

erikgaas

resnet v2 pretrained models

1

Hi, would you release the resnet v2 pretrained models?

Ariel-JUAN

BNInception architecture

5

Seems like there is a mistake in BNInception architecture after the 29th Oct commit. I try to use its convolutional part as a pretrained model for transfer learning and get...

hokmund

Hallo everyone, I'm trying use VGGM.py extract video features. I have done with only one frame (1,3,224,224:1 frame, 3 channels, each frames 224*224 ) feature extraction, now I want try...

wentaoxandry

RuntimeError: invalid hash value

3

invalid hash value (expected "520b38e4", got "238c6f4e0b78e304085bb52cdbe98bf52e66b778eeb19fc2318a88c55b1bcf67") The code is model_name = 'inceptionresnetv2' model = pretrainedmodels.__dict__[model_name](num_classes=1000, pretrained='imagenet')

FindTheAnswer

InceptionV4 raises Exception

1

I would like to try `InceptionV4` on small dataset. It is `CIFAR-10`. I instantiate the model and train by myself. And the `Exception` raises ```python model = InceptionV4() for epoch...

elcolie

Error: 'DenseNet' object has no attribute 'logits'

2

I used the pretrainedmodels.densent121 to trian my own dataset, but when I load the model I trianed, I get the error: 'DenseNet' object has no attribute 'logits', I wnant to...

iWangLin

wrong with senet???

2

Hello, I have tried to load the senet ,and use the pretrained one ....but the error as below  I don't know what's wrong here.

sxzy

Use the pretrained model Resnet34 cannot get the mentioned result?

1

I used the pretrained model resnet34 (download from https://download.pytorch.org/models/resnet34-333f7ec4.pth ) . Using imagenet_eval.py testing on Imagenet only get Acc@1 72.342 Acc@5 90.844 not the mentioned 73.554 91.456 . Why?

iie-gao

Add model size info in Evaluation on imagenet.

1

Can you add model size info in **Evaluation on imagenet** sheet ? Thank you.

finlay-liu