Errors during testing

[BIGDSJ]

Hello, thanks for your excellent work, I want to use this network to implement image conversion, both types of images are normal color images, during the training process I only modified the values of --batchSize and --loadSize in base_options.py, the training was completed smoothly, but during testing I tried to use some images from the training set to test the model but it keeps reporting errors: File "test.py", line 59, in
generated = model.inference(data['label'], data['inst'], data['image'])
File "/root/autodl-tmp/pix2pixHD-master/models/pix2pixHD_model.py", line 198, inference
input_label, inst_map, real_image, _ = self.encode_input(Variable(label), Variable(inst), image, infer=True)
File "/root/autodl-tmp/pix2pixHD-master/models/pix2pixHD_model.py", line 119, in encode_input
input_label = input_label.scatter_(1, label_map.data.long().cuda(), 1.0)
RuntimeError: CUDA error: device-side assert triggered
What should I do? I look forward to your answer. Thank you very much.