Henric Andrew

no attribute 'resize_bilinear'

1

I updated to tensorflow==2.1.0 and tensorflow-gpu==2.10. When running the training script I get the following error: AttributeError: module 'tensorflow_core._api.v2.image' has no attribute 'resize_bilinear' And it references the following function in...

I get the issue above when trying to train on a dataset of images that I have created myself. When I insted use the SVHN dataset, it works fine. Could...

Feature extraction not working

3

I get the following error when trying to run feature extraction. What is wrong?  Gtk-Message: 11:20:28.785: GtkDialog mapped without a transient parent. This is discouraged. Gtk-Message: 11:20:51.173: GtkDialog mapped...

Feature extraction not working

1

I get the following error when trying to run feature extraction. What is wrong? 

Add constraint to get absolute scale reconstruction

3

In structure-from-motion with a single camera the scene can be only recovered up to a scale. However if you have more information such as baseline of the camera motion or...

Strange looking sift features

6

I am using sift feature detection on images of chessbord with charuco patterns, and except for that a completely black background. Sift should not find any features where there is...

I was trying out the code by running the evaluation script with the following command: python3 eval.py --gpu_list=0 --test_data_path=example_images/ --model_path=tmp/icdar2015_east_resnet50/EAST_IC15+13_model.h5 --output_dir=tmp/icdar2015_east_resnet50/eval/ The images used are the ones provided by Kurapan...

CustomTensorboard and ValidationEvaluator callbacks

1

In the CustomTensorboard class you set log_dir=FLAGS.checkpoint_path + '/train' In the ValidationEvaluator class you set validation_log_dir=FLAGS.checkpoint_path + '/val' Can you explain how those tensorboard objects are supposed to differ? Because...

Ho do I interpret the output? What is "loss", "pred_score_map_loss" and "pred_geo_map_loss"? What does it mean that "pred_score_map_loss==0.01 and pred_geo_map==0 Should it be like that on the first epochs? 

Starting the training I get the EOFError shown below. What am I doing wrong? (keras2) johan@johan-VirtualBox:~/Documents/school_projects/temp/EAST-master$ python3 train.py --gpu_list=1 --input_size=512 --batch_size=12 --nb_workers=6 --training_data_path=/home/johan/Documents/school_projects/temp/train_data40 --validation_data_path=/home/johan/Documents/school_projects/temp/train_data40 --checkpoint_path=/home/johan/Documents/school_projects/temp/EAST-master/temp --max_epochs=3 /home/johan/virtualenvs/keras2/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:471: FutureWarning: Passing (type,...