search

CSAILVision / places365

The Places365-CNNs for Scene Classification
http://places2.csail.mit.edu/
MIT License
1.92k stars 536 forks source link

error when untar the pytorch model downloaded from DenseNet161. #38

Closed frankhyj closed 7 years ago

frankhyj commented 7 years ago

Excuse me,when i download tar from website, the downloaded file can not be untar. How can i fix this problem? Thanks!

The models are downloaded from websites below.

PyTorch Places365 models: AlexNet, ResNet18, ResNet50, DenseNet161. The models are trained in Python2.7+PyTorch 0.2, when the models are being loaded in python3, you might encounter UnicodeDecodeError, see this issue. Run basic code to get the scene prediction from PlacesCNN:

hailsham commented 7 years ago

I also have the same problem, the files can not be untar.

zhoubolei commented 7 years ago

If you take some minimum effort to look at the demo script (https://github.com/CSAILVision/places365/blob/master/run_placesCNN_basic.py) you won't ask this kind of question...

hailsham commented 7 years ago

thanks~