David Radianu

When using my own images to train for object identification with tensorflow. I have followed all instructions given by: https://github.com/EdjeElectronics/TensorFlow-Object-Detection-API-Tutorial-Train-Multiple-Objects-Windows-10 As im using the command: "python generate_tfrecord.py --csv_imput=images\train_labels.csv --image_dir=images\train --output_path=train.record"...

Hello i have trained the model with 3 classes. The data.py classes looks like: ` BackGround = [0, 0, 0] road = [2, 2, 2] # COLOR_DICT = np.array([BackGround, road])...

Input size of images 1024

1

Hello, im using the input size of 1024 x 1024 instead of 512 and i get the following error: ValueError: Error when checking input: expected input_1 to have shape (1024,...