-
Dear authors,
I'd like to test your model on my custom 3D reconstructed pointclouds + rgb map.
In order to directly use the [checkpoints](https://huggingface.co/CH3COOK/Vote2Cap-DETR-weights/tree/…
-
The [tutorial](http://caffe.berkeleyvision.org/gathered/examples/feature_extraction.html) says 'The features are stored to LevelDB'. But it actually stores them in lmdb.
And the tutorial says 'the fe…
-
I want to out put the features extracted by pre-trained CNN.
But I only can apply the pre-trained CNN on new data with model.load and get the prediction with model.predict.
How can I output the i…
-
Hi, I've downloaded the pretained features for train/val using the provided links (36 - 100 features per image), however, there are four tsv files in it, namely,
1) karpathy_train_resnet101_faster_…
-
Good evening, I am a graduate student of Level 21 and also interested in cross-modal retrieval. I would like to ask you which three terms V you used respectively when extracting the text features of t…
-
Only being able to get the output of extract_features saved into a single file is limiting. The other commands supported by this repository already have a --output-dir argument: this command should as…
-
After manually fixing the other issues:
* The script finds the models, videos, and makes it all the the way to the progress bar
after the first progress bar shows, there is repeated output of th…
-
I found in task asr, pitch feature in kaldi is much more popular. It compute fbank feature and pitch feature and I want to extract this pitch feature in python, can you give some useful ways to do th…
-
Thanks for your great job
I wander how to test my own data
-
Hello Author, thanks for your great work. I have some questions about CLIP features. How to extract feature with every 16 frames?
I select one frame in every 16 frames and extract it feature, but th…