search

kailigo / cvcZSL

PyTorch Implementation for ICCV19 paper "Rethinking Zero-Shot Learning: A Conditional Visual Classification Perspective"
33 stars 6 forks source link

Question about the weight_gen_model_name #4

Open NanAlbert opened 4 years ago

NanAlbert commented 4 years ago

Sorry to disturb you. I have read your paper, an interesting work, and tried to implement your code, but I have some problems.

  1. What is weight_gen_model_name? Does it contain the parameters of the pre-training model? If the answer is yes, is it pre-trained on ImageNet. If not, can you provide some details? If I train the model on other datasets, e.g. CUB, it seems I don't have './models/CUB1/weight_gen_model.pt', where can I get the file?
  2. Are the parameters trained on different data sets consistent? python trans_train.py --dataset AWA1 --ways 16 --shot 1 --lr 1e-4 --opt_decay 1e-5 --step_size 200 --loss_q 5e-1 --trans_model_name trans_s1w16_lr4_opt5_ss200_q5e1 --log_file trans_s1w16_lr4_opt5_ss200_q5e1

Looking forward to your reply.

NanAlbert commented 4 years ago

Sorry to disturb you. I have read your paper, an interesting work, and tried to implement your code, but I have some problems.

  1. What is weight_gen_model_name? Does it contain the parameters of the pre-training model? If the answer is yes, is it pre-trained on ImageNet. If not, can you provide some details? If I train the model on other datasets, e.g. CUB, it seems I don't have './models/CUB1/weight_gen_model.pt', where can I get the file?
  2. Are the parameters trained on different data sets consistent? python trans_train.py --dataset AWA1 --ways 16 --shot 1 --lr 1e-4 --opt_decay 1e-5 --step_size 200 --loss_q 5e-1 --trans_model_name trans_s1w16_lr4_opt5_ss200_q5e1 --log_file trans_s1w16_lr4_opt5_ss200_q5e1

Looking forward to your reply.