vanpersie32

Results 7 comments of vanpersie32

Help the preprocess.py error!

yeah, it takes much time to preprocess all images

Do you have MIL based on resnet?

@gujiuxiang Thank you

您好，运行train_t5_copy，报prepare_inputs_for_generation()参数错误

I met the same problem

Issue with model checkpoint loading in eval_res_att_knn_test5000.lua

@dastan92 Hey, have you replicate the result in the paper?

Error while running run_inference using pretrained model

@erastogi It seems that you should add require 'cudnn' in script ./000_data_construction/001_resNet101_conv_feat/extract_resnet_feat.lua.

Resnet convnet feature extraction for each image taking too much time

I have implemented extracting feature in batch, but seems in vain. It seems that torch.save consumes much time. I don't think it a good idea to save the feature map...

Resnet convnet feature extraction for each image taking too much time

@JonghwanMun The reason why feature extraction is so slow is because you collect garbage too often. Here Here Here [here](https://github.com/JonghwanMun/TextguidedATT/blob/master/000_data_construction/001_resNet101_conv_feat/extract_resnet_feat.lua#L111)