search

amr4i / EmotionDetection

An emotion extraction system for images, that extracts emotion which will be felt by the user of viewing the image, representing them in a 2-Dimensional space that represents Arousal and Valence.
32 stars 13 forks source link

apply for help #3

Open libo327 opened 5 years ago

libo327 commented 5 years ago
  1. I don't find resnet34-places365.pth and resnet50-places365.pth in http://sceneparsing.csail.mit.edu/model/pretrained_resnet . 2.I download decoder_epoch_20.pth and decoder_epoch_20-2.pth in http://sceneparsing.csail.mit.edu/model/pytorch/baseline-resnet50_dilated8-ppm_bilinear_deepsup/ and I make parser.add_argument('--weights_encoder', default='encoder_epoch_20.pth') parser.add_argument('--weights_decoder', default='decoder_epoch_20-2.pth') is that right? thank you for your help
libo327 commented 5 years ago

Can I use CPU to run the resnet in your semantic_features?just test, not train