Closed hs457681503 closed 4 years ago
Hi friend,
It seems you are one step ahead. Can you please guide me from where to get the right structure of data to generate captions.pickle file. I am facing issue in that. Because when I downloaded CUB dataset and used in this code, captons.pickle comes empty. I want to train and test this repository too.
Your help will be highly appreciated. Thanks
can you please mention your email id? Facing issue in registering on wechat. Thanks
On Sat, 25 Jul 2020 at 12:21, hs457681503 notifications@github.com wrote:
Hi friend,
It seems you are one step ahead. Can you please guide me from where to get the right structure of data to generate captions.pickle file. I am facing issue in that. Because when I downloaded CUB dataset and used in this code, captons.pickle comes empty. I want to train and test this repository too.
Your help will be highly appreciated. Thanks
hello,my wechat is 19845918683,
Please contact me
— You are receiving this because you commented. Reply to this email directly, view it on GitHub https://github.com/MinfengZhu/DM-GAN/issues/15#issuecomment-663822012, or unsubscribe https://github.com/notifications/unsubscribe-auth/AMQCS4V3YPUGOAIAEGI2NRTR5KBXNANCNFSM4PGO2RXQ .
When i try to train the the birds model, I encountered this problem.
Coulde you help me solve this problem?
RuntimeError: Error(s) in loading state_dict for RNN_ENCODER: size mismatch for encoder.weight: copying a param of torch.Size([1, 300]) from checkpoint, where the shape is torch.Size([5450, 300]) in current model.
Could you please provide more information (e.g., config file or command)? If you train the model from scratch, there is no checkpoint to load.
It seems you are one step ahead. Can you please guide me from where to get the right structure of data to generate captions.pickle file. I am facing issue in that. Because when I downloaded CUB dataset and used in this code, captons.pickle comes empty. I want to train and test this repository too.
Have you downloaded the metadata for CUB dataset?
python google_drive.py 1O_LtUP9sch09QH3s_EBAgLEctBQ5JBSJ ./data/bird.zip
The size of captons.pickle file is 6.2M.
Please see #1 for data directory structures.
Thanks. I have one more question.
I am using example_filename.txt and generating images using main.py. But I am achieving IS 2.92 only. Can you please guide me why I am not getting the same mentioned IS score as you have mentioned in your paper. For FID, I am getting 65.48. Please guide me.
Thanks
Thanks. I have one more question.
I am using example_filename.txt and generating images using main.py. But I am achieving IS 2.92 only. Can you please guide me why I am not getting the same mentioned IS score as you have mentioned in your paper. For FID, I am getting 65.48. Please guide me.
Thanks
Please generate images using the following command. You should generate images using text descriptions from the whole valid dataset.
python main.py --cfg cfg/eval_bird.yml --gpu 0
I am using this command already but with example_filename.txt. Where are the text descriptions for the validation set? Please help.
Thanks
Please do not use example_filename.txt. All captions are stored in captions.pickle. Please read dataset.py for more details.
This command will generate images for the validation set.
python main.py --cfg cfg/eval_bird.yml --gpu 0
When i try to train the the birds model, I encountered this problem.
Coulde you help me solve this problem?
RuntimeError: Error(s) in loading state_dict for RNN_ENCODER: size mismatch for encoder.weight: copying a param of torch.Size([1, 300]) from checkpoint, where the shape is torch.Size([5450, 300]) in current model.