Extracting output image from pickle - Coco model inference

[benkmoore]

How do I produce images from the pickle file produced when I run;

python2.7 test_net.py --cfg e2e_mask_rcnn_R-101-FPN_2x.yaml TEST. WEIGHTS https://dl.fbaipublicfiles.com/detectron/35861858/12_2017_baselines/e2e_mask_rcnn_R-101-FPN_2x.yaml.02_32_51.SgT4y1cO/output/train/coco_2014_train:coco_2014_valminusminival/generalized_rcnn/model_final.pkl NUM_GPUS 1

I cant interpret the chunk of data produced

Detailed steps to reproduce

`import pickle

pkl_file = open('detection_range_1_5.pkl',encoding='iso-8859-1') images = pickle.load(pkl_file) print(images) pkl_file.close()`

System information

• Operating system: Ubuntu 16.04
• Compiler version: [GCC 5.4.0 20160609]
• CUDA version: 10.1
• NVIDIA driver version: 418.67
• GPU models (for all devices if they are not all the same):
• PYTHONPATH environment variable: not set (empty string)
• python --version output: 2.7

Any help would be great, thanks

[benkmoore]

Solved: Used your visualize_results.py file

Example

python2.7 visualize_results.py --detections detection_range_0_10.pkl --first 5