[英]Visualizing my own set of images with Tensorflow deeplab
I am trying to implement Deeplab example from Tensorflow.我正在尝试从 Tensorflow 实现Deeplab 示例。 I followed the guideline and manage to train it with Cityscapes dataset with accuracy of 0.77.我遵循了指南并设法使用 Cityscapes 数据集对其进行了训练,精度为 0.77。 I am able to use the vis code to create segmented images with the images of the Cityscape dataset.我能够使用 vis 代码创建带有 Cityscape 数据集图像的分割图像。
Now I want to use my set of images to be visualized, I tried replacing the files from the dataset by putting them in the folder /models/research/deeplab/datasets/cityscapes/leftImg8bit/val and rerun sh convert_cityscapes.sh
but it finishes creating tfrecord when I run现在我想使用我的一组图像进行可视化,我尝试通过将它们放在文件夹 /models/research/deeplab/datasets/cityscapes/leftImg8bit/val 中来替换数据集中的文件并rerun sh convert_cityscapes.sh
但它完成了运行时创建 tfrecord
python deeplab/vis.py
--logtostderr \
--vis_split="val" \
--model_variant="xception_65" \
--atrous_rates=6 \
--atrous_rates=12 \
--atrous_rates=18 \
--output_stride=16 \
--decoder_output_stride=4 \
--vis_crop_size=1025 \
--vis_crop_size=2049 \
--dataset="cityscapes" \
--colormap_type="cityscapes" \
--checkpoint_dir=${PATH_TO_CHECKPOINT} \
--vis_logdir=${PATH_TO_VIS_DIR} \
--dataset_dir=${PATH_TO_DATASET}
It doesnt create anything.它不会创造任何东西。
I dont need to run the training again, I just want to use my pretrained model to predict the image segmentations from my own images, but I dont know how to progress.我不需要再次运行训练,我只想使用我的预训练模型从我自己的图像中预测图像分割,但我不知道如何进行。
Did you make sure the tfrecords you created are of pattern: val-*
?你确定你创建的 tfrecords 是模式: val-*
吗? You can also create your own DatasetDescriptor so that you won't mix up with your true val set.您还可以创建自己的 DatasetDescriptor,这样您就不会与真正的 val 集混淆。
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.