search

sysu-imsl / EdgeGAN

Code for paper "SketchyCOCO: Image Generation from Freehand Scene Sketches" (CVPR 2020)
https://sysu-imsl.com/EdgeGAN/
45 stars 7 forks source link

Issue when training in single class #23

Open Michael-Ray-Sirius opened 1 year ago

Michael-Ray-Sirius commented 1 year ago

Thanks for your interesting work! But when I run the code 'python -m edgegan.train --name=edgegan --dataroot='/home/ai/EdgeGAN/data' --nomulticlasses --dataset=2 --gpu=0'

Traceback (most recent call last): File "/home/ai/anaconda3/envs/EdgeGAN/lib/python3.7/runpy.py", line 193, in _run_module_as_main "main", mod_spec) File "/home/ai/anaconda3/envs/EdgeGAN/lib/python3.7/runpy.py", line 85, in _run_code exec(code, run_globals) File "/home/ai/EdgeGAN/edgegan/train.py", line 138, in tf.app.run() File "/home/ai/anaconda3/envs/EdgeGAN/lib/python3.7/site-packages/tensorflow/python/platform/app.py", line 40, in run _run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef) File "/home/ai/anaconda3/envs/EdgeGAN/lib/python3.7/site-packages/absl/app.py", line 308, in run _run_main(main, args) File "/home/ai/anaconda3/envs/EdgeGAN/lib/python3.7/site-packages/absl/app.py", line 254, in _run_main sys.exit(main(argv)) File "/home/ai/EdgeGAN/edgegan/train.py", line 134, in main edgegan_model.train() File "/home/ai/EdgeGAN/edgegan/models/edgegan.py", line 459, in train batch_images, batch_z, batch_files = self.dataset[idx] File "/home/ai/EdgeGAN/edgegan/utils/data/dataset.py", line 69, in getitem batch_images = np.array(batch).astype(np.float32) ValueError: could not broadcast input array from shape (64,128,3) into shape (64,128)

do i need to reshape the input array to the shape (64, 128) ?