dsuthar-nvidia

@nerox8664 The onnx-tensorflow has a resize layer implementation at https://github.com/onnx/onnx-tensorflow/blob/master/onnx_tf/handlers/backend/resize.py Can you use this and add it to onnx2keras?

@alanchiao any insights on when will this be fixed?

@alanchiao Is this a major change? From the stack trace it looked more like a minor bug where some piece of code is not properly respecting the dtype.

@mizhitian-xiaomi Generally CV-CUDA recommends that you use GPU accelerated data decoding libraries like [nvimagecodec](https://docs.nvidia.com/cuda/nvimagecodec/) or [pynvvideocodec](https://developer.nvidia.com/pynvvideocodec). CV-CUDA [samples](https://github.com/CVCUDA/CV-CUDA/tree/main/samples) cover a broad range of pipelines that reads videos and images and...

@amahendrakar That was my point. Did you read my post above? Mean IOU, implemented as a metric, is pretty much unusable without a threshold. You can try replacing 1 values...

@pavithrasv any idea on when will this be addressed? Seems like a minor change on API side but it carries big impact on usability.

Need threshold to stay consistent with the rest of the API. See TruePositives, FalsePositives etc implementations https://www.tensorflow.org/api_docs/python/tf/keras/metrics/TruePositives?hl=TR

First, at-least the docs of TruePositives and MeanIoU refer `y_pred` as `y_pred | The predicted values.` Second, on the docs it says IOU is defined as follows: `IOU = true_positive...

@lazylazypig @kywish Does something like the following work for you? ``` #include #include #include #include #include #include #include #include // Utility function to check CUDA errors #define CHECK_CUDA_ERROR(call) \ do...

@hongsamvo We have tested the samples with TensorRT image 24.01-py3 as mentioned in the samples [readme](https://github.com/CVCUDA/CV-CUDA/blob/main/samples/README.md). Generally CUDA initialization errors have common causes like: - Driver Issues: The installed NVIDIA...