Open tomruarol opened 5 years ago
Seems you put a wrong number for the path. “00010->00100”
This type of error happens if you are using wrong path for input_path key. Check file path mentioned in config file for input_path is present on disk, you will not get exact file but you should see file with something this name: coco_val.record-00000-of-00010 OR coco_val.record-00099-of-00010
(coco_val.record-?????-of-00010 question mark represents 5 digit number of record file)
@tomruarol
Is this still an issue?.Please, close this thread if your issue was resolved.Thanks!
Yes, it's still an issue.
I am trying to train a whole model based on the COCO dataset using this scripts provided but reducing the number of classes to only 6.
I run the
download_and_preprocess_coco.sh
script which downloads the dataset and calls thecreate_coco_tf_record.py
script which creates the TFRecords from the dataset previously downloaded. After that steps (successfully achieved) I try to run theretrain_detection_model.sh
as it is described in the tutorial, but modifying the labels .pdtxt file in order to take into account only 6 clases and modifying thepipeline.config
file in order to achieve the same (with a v2 net and training the whole model option).The first error that came out was:
RuntimeError: Did not find any input files matching the glob pattern [u'/tensorflow/models/research/tmp/mscoco/coco_train.record-00001-of-00010']
When I do have a file under:
/tensorflow/models/research/tmp/mscoco/
which contains files of the following format:Being the first set of 5 numbers after the record part numbers that go from 00000 to 00099.
So I do have those files that the error reports I do not have, and I have the PATH specified in the pipeline.config file.
I managed to move on a bit by skipping the use of the
glob
library in thedataset_builder.py
script under the routeresearch/object_detection/builders/
. It is not working as it should, so by just removing the use of it the script runs a bit ahead, but it still throws and error:I have not figured out how to move on from here.
I paste my
pipeline.config
file: