TensorFlow-Object-Detection-API-Tutorial-Train-Multiple-Objects-Windows-10

TensorFlow-Object-Detection-API-Tutorial-Train-Multiple-Objects-Windows-10 copied to clipboard

Accuracy For Detection (Issues)

24

I ran the RCNN for around 3 hours and got up to 50K steps but when I tested the images I got weird accuracy when running random images. What could...

mronda

Training with model_main.py

32

This is not an issue, more of a how-to on using model_main.py. Edje, if you are reading this, I wanted to tell you and anyone reading how to train using...

JulianOrteil

Could not find 'cudart64_100.dll' during Import tensorflow - CUDA 10.1 Incompatible with Tensorflow

3

> ImportError: Could not find 'cudart64_100.dll'. TensorFlow requires that this DLL be installed in a directory that is named in your %PATH% environment variable. Download and install CUDA 10.0 from...

Stigmaru

Part 4:python generate_tfRecord.py --csv_input=images\ train_allags.csv --image_dir=images\train --output_path=train

1

When I run Python generate_tfRecord.py --csv_input=images\ train_allags.csv --image_dir=images\train --output_path=train. Record: File "D:\Anaconda3\envs\tensorflow1\lib\site-packages\pyparsing\__init__.py", line 130, in __version__ = __version_info__.__version__ AttributeError: 'version_info' object has no attribute '__version__' How should be solved excuse...

RyanShun-511

raise ValueError('You must supply the path to save to with --output_file') ValueError: You must supply the path to save to with --output_file

1

I'm training tensorflow 1 object detection using mobilenet when I use this command: python export_inference_graph.py --input_type image_tensor --pipeline_config_path training\mobilenet.config --trained_checkpoint_prefix training\model.ckpt-100000 --output_directory trained-inference-graphs `Traceback (most recent call last): File "export_inference_graph.py",...

r2ba7

Error while training custom model with ssd_inception_v2_coco

7

(tensorflow_cpu)C:\Users\AB\Tensorflow\workplace\training_demo>python train.py --logtostderr --train_dir=training/ --pipeline_config_path=training/ssd_inception_v2_coco.config WARNING:tensorflow:From C:\Users\AB\Anaconda3\envs\tensorflow_cpu\lib\site-packages\tensorflow\python\platform\app.py:125: main (from __main__) is deprecated and will be removed in a future version. Instructions for updating: Use object_detection/model_main.py. WARNING:tensorflow:From C:\Users\AB\Anaconda3\envs\tensorflow_cpu\lib\site-packages\object_detection\legacy\trainer.py:266: create_global_step (from tensorflow.contrib.framework.python.ops.variables)...

shABanty

Issue in generating tfrecord

6

RutvikBabar

error First step cannot be zero when running train.py

20

i tried to use the same images (card) provided, i just delete all the processed file (csv,dll) and follow all the step. And when i tried to issue python train.py...

blockhunts

crop deteted objects from imagei and display it

24

I want to store the detected objects from the image into separate folder. I have made changes in visualization_utils.py to crop the image section using normalized points but it is...

ocularnets

Error while running the training command. Saying 'FasterRcnn' object has no attribute 'first_stage_only'

4

Traceback (most recent call last): File "train.py", line 163, in tf.app.run() File "C:\Users\haiL\Anaconda2\envs\tf15\lib\site-packages\tensorflow\python\platform\app.py", line 125, in run _sys.exit(main(argv)) File "train.py", line 159, in main worker_job_name, is_chief, FLAGS.train_dir) File "C:\tensorflow1\models\research\object_detection\trainer.py", line...

hail2m15