Pelin Su KARABACAK comments

Results 10 comments of


                                            Pelin Su KARABACAK

Error when executing: python train.py --logtostderr --train_dir=training/ --pipeline_config_path=training/faster_rcnn_inception_v2_pets.config

Helloo i have similar errors while running model_main_tf2.py. " _python model_main_tf2.py --alsologtostderr --model_dir=training/ --pipeline_config_path=training/faster_rcnn_inception_v2_pets.config_ " Did you find a solution ? I dont have any custom steps i did everything...

generate_tfrecord.py

> Hi, > > I tried your code and I was getting this error message: > > ``` > 2020-08-17 18:41:08.312730: W tensorflow/stream_executor/platform/default/dso_loader.cc:59] Could not load dynamic library 'cudart64_101.dll'; dlerror:...

ValueError: train_pb2.load_all_detection_checkpoint_vars unsupported in TF2

hello i have the same problem did you find any solution for this ?

Updated training/faster_rcnn_inception_v2_pets.config

Helloo i have errors while running model_main_tf2.py. " _python model_main_tf2.py --alsologtostderr --model_dir=training/ --pipeline_config_path=training/faster_rcnn_inception_v2_pets.config_ " I dont have any custom steps i did everything from [here](https://github.com/EdjeElectronics/TensorFlow-Object-Detection-API-Tutorial-Train-Multiple-Objects-Windows-10) But my tensorflow version is...

Error when executing: python train.py --logtostderr --train_dir=training/ --pipeline_config_path=training/faster_rcnn_inception_v2_pets.config

cannot import name 'fpn_pb2' from 'object_detection.protos' in Tensorflow 2.x

I have same problem did you find a solution it ? :/

During training checkpoints are being saved, also the last version of the trained model, which might not be the best model. So there should be an option to save the best model as well.

> > I would like to help, could you please provide colab copy of the code. As I am not able to find the training code. > > Thanks for...

During training checkpoints are being saved, also the last version of the trained model, which might not be the best model. So there should be an option to save the best model as well.

> @PelinSuK Chances are you trying to run a TF 1 model on the TF 2 version. Try to run a tf2 model you can get from [tf2 model zoo](https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/tf2_detection_zoo.md)...

During training checkpoints are being saved, also the last version of the trained model, which might not be the best model. So there should be an option to save the best model as well.

> > > @PelinSuK Chances are you trying to run a TF 1 model on the TF 2 version. Try to run a tf2 model you can get from [tf2...

During training checkpoints are being saved, also the last version of the trained model, which might not be the best model. So there should be an option to save the best model as well.

> I have a quick fix for this. It might not be ideal but it works! In the model_lib_v2.py script, add these few lines of code, > > ``` >...