search

MILVLG / bottom-up-attention.pytorch

A PyTorch reimplementation of bottom-up-attention models
Apache License 2.0
294 stars 76 forks source link

Extract features gets stuck #94

Closed preetom-saha-arko closed 1 year ago

preetom-saha-arko commented 2 years ago

I used a folder containing only 1 image for extracting features (roi_feats). 40 minutes passed and yet the command seemed nowhere near completion. Nothing pops up after "Number of images on split0:1" is printed. Is there any minimum or maximum limit on the number of images for feature extraction? I am using an 8th gen Intel Core i7 laptop having a GTX 1070 Max-Q GPU. I executed the following command: python3 extract_features.py --mode caffe --num-cpus 0 --gpus 1 --extract-mode roi_feats --min-max-boxes '10,100' --config-file configs/caffe/test-caffe-r101.yaml --image-dir "/home/arko/Documents/images" --out-dir "/home/arko/Documents/outputs" --fastmode

preetom-saha-arko commented 1 year ago

Issue resolved after removing --fastmode

Abhayy-Kumar commented 6 months ago

Issue resolved after removing --fastmode

can you please tell where did you execute all the commands? also did you use windows or Linux?