Eval batch size always 0

hello i’m using deepstream 5.0, and tlt

i’m trying to train my model
but evaluation fail every time

please help

Is there something wrong in above tfrecords path?

thanks for reply
unfortunately path is correct
because training is running before evaluation

Could you double check why there is double “//” ?


it’s just my trying result
because some path using single ‘/’ cause path error
is it cause error???
but it was working before evaluation

How many images of your val dataset?
If possible, please share your full log when you run tlt-dataset-convert.

i attached log file!

Thanks for helping me

According to your tfrecord log, there are only 3 classes.
b’person’: b’person’
b’car’: b’car’
b’target’: b’target’

But you set wrong target_class_mapping in the training spec.
Could you change to below and retry?
target_class_mapping {
key: “person”
value: “person”
target_class_mapping {
key: “car”
value: “car”
target_class_mapping {
key: “target”
value: “target”