ForawardStar

How to finetune on the MSRVTT

1

Hello, wonderful project!. Here I wonder how to finetune the pre-trained models on downstream video-text retrieval datasets like MSR-VTT, LSMDC, and MSVD? I notice that the script for zero-shot retrieval...

Hi, I like this work very much and I think it is really cool. But when I tried to use an image in the target domain to decide the attribute...

seeking for pre-trained model for shoes and handbags to edges

1

Hi, thank you for releasing the code. I want to to translate shoes and handbags to edges but find that the training time is too long, can you release the...

AttributeError: 'Namespace' object has no attribute 'train_datasets'

2

When I launched the 2nd stage training using : ``` horovodrun -np 4 python pretrain_vcr.py --config config/pretrain-vcr-base-4gpu.json \ --output_dir $PRETRAIN_VCR_EXP ``` An error occured, which is: ``` Traceback (most recent...

Releasing the pretrained models

3

Hi, a very great project. However, when I click the link of pretrained models, I found there are many saliency detection results, instead of the pretrained models, no matter baiduyun...

If I already output the saliency detection mapts, all I want to do is to evaulate my results by F-measure. Can I just use the matlab code and the .tex...

Cannot reproduce the reported F-score

9

Can anyone successfully reproduce the results reported in this paper？My python environment is python 3.6, and train the model using the augmented dataset downloaded from http://vcl.ucsd.edu/hed/HED-BSDS.tar. But the visual results...

multi-scale input

2

How to get the multi-scale input?

.lst文件

1

请问如何生成数据集的.lst文件？

Hi, wonderful project! Here I have a question the visualization. The command for visualizing the detections from the pretrained models in your README.md is: `python tools/demo/demo_image.py --config_file sgg_configs/vgattr/vinvl_x152c4.yaml --img_file ../maskrcnn-benchmark-1/datasets1/imgs/woman_fish.jpg...