-
-deleted-
-
### Describe the bug
Simply `import anomalib.models` will display the following warning: `OpenVINO is not installed. Please install OpenVINO to use OpenVINOInferencer.`
### Dataset
N/A
### Model…
-
### Issue Description
Vram usage during the VAE step is inconsistent and will spike to >12 gb for an sdxl model. This is atypical for my usage, where an SDXL model will stay at 10gb or less during t…
-
HI, I have no clues why the NeuralNetwork node's output tensor comes with almost all zero with using openvino pretrained model ssdlite_mobilenet_v2 and my pytorch custom model. Before converting to t…
-
when I run vLLM model like Qwen2-VL-2B with ARC770 on MTL platform, will report error message as below:
RuntimeError: Current platform can NOT allocate memory block with size larger than 4GB! Tried t…
-
# Design proposal
## Introduction
OpenVINO provides API for specifying input/output nn model characteristics such as: `Precision`, `Layout`, particularly for `input` it's also possible to specify if…
-
The current model is restricted to 512x512 pixels. Can you please give a tutorial to customize openvino models with the resolutions of choice? For example, 768x512 pixels?
-
Hello,
When implementing this interesting application, I get the follwoing runtime error:
RuntimeError: Layer data_mul_2528825292/copy_const not found in network.
Details are given below.
…
-
经测试，onnxruntime版本为1.10使用cpu版本在linux平台推理单张图像时间为0.8s，而使用gpu推理后，时间达到了2.8s，gpu效率比cpu还低几倍，博主可以解释下吗，谢谢
-
Hello, can you please share the steps and command line you used to convert the original model to OpenVINO IRs. Need this to help optimize these models further.