Lanxiao Wang

question about restore model

3

when i restore the rgb_imagenet model, the layer name maybe wrong, I change into ### for variable in tf.global_variables(): rgb_variable_map['RGB/'+variable.name.replace(':0', '')] = variable ### then the name is right; but...

Hi, thanks for your great work! We tried to modify the code to use 4 GPUs (2080T) for training, and found that the time did not shorten much. Have you...

Thank you very much for making the code open source I can find 4 configs about xlan and transformer in the experiment folder Can you provide the basic model(updown) of...

Is it possible to set different parameter sets and different learning rates for the optimizer？ Such as : backbone_params = list(map(id,model.backbone.parameters())) base_params = filter(lambda x:id(x) not in backbone_params ),model.parameters()) optimizer...

Hi, these days I find that the Googel drive about models of image captioning are lost. Could you check the link about it?

socket.gaierror: [Errno -5] No address associated with hostname

1

Thanks for your help. I meet some strange errors as below. The log file is: 2022-10-08 19:57:58,183 WARNING worker.py:1189 -- The agent on node amax failed with the following error:...

Score about Online test

2

Hi, thanks for your work~ I have a question about your score of onlien test for MSCOCO. The score is for single model? or an Ensemble model? If for ensemble,...

Question about Results

1

Thanks for your work and code. It is a pretty good paper. Could you share the best model of text-only image captioning on MSCOCO or the generated results json for...