biyuehuang

Hi, I use example/classification/classification.ipynb by inceptionV3 model on Jetson AGX Xavier. I modify it to print inference time by "import datetime" as following: ``` ...... tf.import_graph_def(trt_graph, name='') tf_input = tf_sess.graph.get_tensor_by_name(input_names[0]...

Do you know how to use this project mtcnn_facenet_cpp_tensorRT with multi-stream video input, i.e. by deepstreamSDK

./build_and_install.sh sucessfully but vainfo exist error

4

SVET sample application building has completed! But $ vainfo libva info: VA-API version 1.9.0 libva info: User environment variable requested driver 'iHD' libva info: Trying to open /usr/lib/x86_64-linux-gnu/dri/iHD_drv_video.so libva info:...

Can modin support pandas on Intel Arc DGPU?

2

OS: Ubuntu22.04 hardware: ADl 12700 + Arc A770

[TTS]Windows10 CPU fastspeech2_mix_onnx_0.2.0遇到am_sess.run(None, input_feed=am_input_feed)时不报错，直接结束运行代码

1

环境：windows10 CPU Core i7 ``` conda create -n audio python=3.9 libuv conda activate audio pip install paddlepaddle -i https://mirror.baidu.com/pypi/simple pip install pytest-runner paddlespeech==1.4.1 或者 paddlespeech==1.4.0 pip install langid==1.1.6 zhconv==1.4.3 transformers==4.31.0...

yolov5_demo_OV2021.3.py Error by openvino2022.1

1

mo --input_model yolov5s.onnx --data_type FP16 --reverse_input_channels --output Conv_238,Conv_218,Conv_198 --batch 1 python yolov5_demo_OV2021.3.py -i people.png -m yolov5s.xml [ INFO ] Creating Inference Engine... [ INFO ] Loading network: yolov5s.xml [ INFO...

vllm can‘t use oneCCL on host

3

Ubuntu22.04,kernel 5.15.0 with 4 * Arc A770 on Xeon(R) w9-3495X $ clinfo Driver Version 24.22.29735.27 script ``` source /opt/intel/oneapi/2024.0/oneapi-vars.sh --force source /opt/intel/1ccl-wks/setvars.sh --force # use oneCCL export MODEL="/opt/Meta-Llama-3-8B-Instruct" export CCL_WORKER_COUNT=2...

vllm在A770运行过程中，卡住了

1

A770，Ubuntu系统 ``` for n in $(seq 16 16); do echo "Model= $MODEL RATE= 0.7 N= $n..." python3 benchmark_vllm_throughput.py \ --backend vllm \ --model $MODEL \ --num-prompts 100 \ --trust-remote-code \...