Till Beemelmanns

 I use a recorded bag file and experienced an instable behavior of the calibration method. Using the identical bag file and identical parameters the method delivers varying...

I am wondern if it is possible to print and cut the ArUco markers directly on the black border so that b1 and b2 are zero. Or is a white...

```Python import chocolate as choco def get_op_space(i): return { "{}_posterize".format(i) : {"{}_l_posterize".format(i): choco.quantized_uniform(0, 11, 1), "{}_p_posterize".format(i): choco.quantized_uniform(0, 1, 0.1)}, "{}_solarize".format(i) : {"{}_l_solarize".format(i): choco.quantized_uniform(0, 11, 1), "{}_p_solarize".format(i): choco.quantized_uniform(0, 1, 0.1)}, "{}_adjust_brightness".format(i):...

stereo_image_proc Output-Timing is async

3

I am using stereo image proc to convert the raw output of a stereo camera. Both cameras use a Bayer 8 Bit encoding. As shown in the image, the raw...

I was testing the UNet model along with a mobilenetv2 and saw that there are a lot non-trainable params, which I could not explain. I quick lookup in the model...

Hi, I am recording the imagezero topic with ``` rosbag record /sensors/camera/left/image_color/imagezero ``` After that, I play the recorded bagfile with `rosbag play`. Using ```xml ``` for decompressing the images...

I am currently doing some experiments with the Waymo 3D Object Detector **Centernet** and found out that there is a bug in the [CenterNetBoxLoss](https://github.com/keras-team/keras-cv/blob/7136ceb3c05335c90670651cc4f5a2ebc1a645ac/keras_cv/src/losses/centernet_box_loss.py#L37) function. I trained the model for...

Use jit_compile=False for CenterNet to avoid XLA compilation during training

1

I am running into problems when using `keras-cv/examples/training/object_detection_3d/waymo/train_pillars.py` with Keras 3. Some of the layers constantly recompile XLA (probably the voxelization layer) causing very long step time and OOM crash....

Hello, what is the difference to the original code ? Why is this repository well suited for high resolution images? Which resolution of GTA and Cityscapes can you recommend for...

Using keras.models.load_model leads to TypeError

2

```python from keras.models import load_model from recurrentshop.engine import RecurrentContainer from seq2seq.cells import LSTMDecoderCell def mean_squared_displacement(y_true, y_pred): return K.mean(K.sum(K.square(y_true - y_pred), axis=-1)) model = Seq2Seq(input_dim=2, input_length=8, output_dim=2, output_length=12, hidden_dim=128, dropout=0.0, peek=False,...