seraj94ai/train-object-detection-classifier

How To Train an Object Detection Classifier for Multiple Objects Using TensorFlow (GPU) on Windows 10

train-object-detection-classifier's Issues

python: can't open file 'train.py': [Errno 2] No such file or directory WARNING: The TensorFlow contrib module will not be included in TensorFlow 2.0.

Hello,
I followed all the tutorial and at the end received below Errors.
1) First i used python train.py --logtostderr --train_dir=training/ --pipeline_config_path=training/ssd_inception_v2_coco.config
and Received below Error.
(tensorflow1) C:\tensorflow1\models\research\object_detection>python train.py --logtostderr --train_dir=training/ --pipeline_config_path=training/faster_rcnn_inception_v2_pets.config
python: can't open file 'train.py': [Errno 2] No such file or directory

2. Then I found that to use legacy and i wrote as below
   (tensorflow1) C:\tensorflow1\models\research\object_detection>python legacy/train.py --logtostderr --train_dir=training/ --pipeline_config_path=training/faster_rcnn_inception_v2_pets.config

WARNING: The TensorFlow contrib module will not be included in TensorFlow 2.0.
For more information, please see:

• https://github.com/tensorflow/community/blob/master/rfcs/20180907-contrib-sunset.md
• https://github.com/tensorflow/addons
  If you depend on functionality not listed there, please file an issue.

Traceback (most recent call last):
File "legacy/train.py", line 51, in
from object_detection.builders import model_builder
File "C:\Pyth\Anaconda3\envs\tensorflow1\lib\site-packages\object_detection-0.1-py3.7.egg\object_detection\builders\model_builder.py", line 27, in
from object_detection.builders import post_processing_builder
File "C:\Pyth\Anaconda3\envs\tensorflow1\lib\site-packages\object_detection-0.1-py3.7.egg\object_detection\builders\post_processing_builder.py", line 22, in
from object_detection.protos import post_processing_pb2
File "C:\Pyth\Anaconda3\envs\tensorflow1\lib\site-packages\object_detection-0.1-py3.7.egg\object_detection\protos\post_processing_pb2.py", line 15, in
from object_detection.protos import calibration_pb2 as object__detection_dot_protos_dot_calibration__pb2
ImportError: cannot import name 'calibration_pb2' from 'object_detection.protos' (C:\Pyth\Anaconda3\envs\tensorflow1\lib\site-packages\object_detection-0.1-py3.7.egg\object_detection\protos_init_.py)

Please help to solve this issue efficiently

Object_detection_image Error

Could you tell me about your tensorflow's version.I try all version 1.9.0 to 1.13.0,but also has error.
I get error about Failed to get convolution algorithm. This is probably because cuDNN failed to initialize,others suggest force upgrade tensorflow to v 1.9.0 but this version tensorflow couldn't run you code.

trainin run code problem :(

Hello Dear Seraj, ı have problem

(tensorflow1) C:\tensorflow1\models\research\object_detection>python train.py --logtostderr --train_dir=training/ --pipeline_config_path=training/faster_rcnn_inception_v2_pets.config
Traceback (most recent call last):
File "train.py", line 51, in
from object_detection.builders import model_builder
File "C:\Users\Alper Z\Anaconda3\envs\tensorflow1\lib\site-packages\object_detection-0.1-py3.6.egg\object_detection\builders\model_builder.py", line 30, in
from object_detection.models import faster_rcnn_inception_resnet_v2_feature_extractor as frcnn_inc_res
File "C:\Users\Alper Z\Anaconda3\envs\tensorflow1\lib\site-packages\object_detection-0.1-py3.6.egg\object_detection\models\faster_rcnn_inception_resnet_v2_feature_extractor.py", line 28, in
from nets import inception_resnet_v2
ModuleNotFoundError: No module named 'nets'

pls help me..

Im not taking accuracy

Im not taking accuracy, just error functions in tensorboard, do you know how I could take it?