! python3 "/content/models/research/deeplab/train.py" \
--logtostderr \
--training_number_of_steps=100000 \
--train_split="train" \
--model_variant="xception_71" \
--decoder_output_stride=4 \
--train_crop_size="513,513" \
--train_batch_size=4 \
--dataset="pascal_voc_seg" \
--save_interval_secs=300 \
--save_summaries_secs=300 \
--save_summaries_images=True \
--log_steps=100 \
--tf_initial_checkpoint="/content/deeplab/datasets/pretrained/model.ckpt" \
--train_logdir="/content/deeplab/datasets/train" \
--dataset_dir="/content/deeplab/datasets/tfrecord"
启动此命令后,出现以下错误。
ValueError: Total size of new array must be unchanged for logits/semantic/weights lh_shape: [(1, 1, 256, 19)], rh_shape: [(1, 1, 256, 21)]
我的数据集只有2个类(两个是背景类),这会导致错误吗?