search

nexusapoorvacus / DeepVariationStructuredRL

A PyTorch implementation of the "Deep Variation-structured Reinforcement Learning for Visual Relationship and Attribute Detection" paper by Liang et. al.
63 stars 12 forks source link

setup.sh expects a non-existent directory #5

Open StrangeTcy opened 5 years ago

StrangeTcy commented 5 years ago

After being run in project root directory, setup.sh fails with

Traceback (most recent call last): File "create_data_samples.py", line 69, in data = create_data_sample_file() File "create_data_samples.py", line 18, in create_data_sample_file for im_name in os.listdir(IMAGE_DIR)[:NUM_IMAGES_TRAIN + NUM_IMAGES_VALIDATION + NUM_IMAGES_TEST]: FileNotFoundError: [Errno 2] No such file or directory: '/data/apoorvad/VG_Scene_Graph/VG_100K/'

This is a directory never mentioned in the README, so it wasn't created when following the instructions.

13732858501 commented 5 years ago

I have encountered the same problem, have you solved it?

nexusapoorvacus commented 5 years ago

Sorry about that, just fixed the path. The correct path is data/VG_100K. You should download the Visual Genome image data as specified in the README directions in data/VG_100K

13732858501 commented 5 years ago

Thank you .But I got another error, evaluation function is not defined when I typed the python main.py --test command.