Hi,
I am facing some difficulties while trying to train Retinanet with my own Dataset.
Here the snapshot describing the error encountered:
In the training specification txt file, I changed the size of input image such that it corresponds to my data (640x352).
I would be pleased if someone could help me to fix this.
There should be some issues from your tfrecords.
Please share the full log and spec when you run tlt-dataset-convert.
The specification file retinanet_tfrecords_kitti_trainval.txt:
root_directory_path: "/workspace/tlt-experiments/data/training"
image_dir_name: "image_2"
label_dir_name: "label_2"
image_extension: ".jpg"
partition_mode: "random"
num_partitions: 2
val_split: 14
num_shards: 10
}
image_directory_path: "/workspace/tlt-experiments/data/training"
And the log of the cmd tlt-dataset-convert:
Your val image is too little, only 6.
Please refer to Training detectnet_v2 Issue
- val_images >= num_shards
- train_images >= num_shards
Thanks a lot, that just works!