search

theAIGuysCode / Object-Detection-API

Yolov3 Object Detection implemented as APIs, using TensorFlow and Flask
Apache License 2.0
339 stars 179 forks source link

error when i run "app.py" cuda error. I'm in a hurryyyy!!!!!!!!!!!!!!! #11

Open uuuuujin63 opened 4 years ago

uuuuujin63 commented 4 years ago

Hi. I'm trying object-detection-API. I run all code. finally I run app.py but error occurred.

failed to allocate 120.19M (126025728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2020-06-14 01:30:23.044898: F tensorflow/stream_executor/cuda/cuda_driver.cc:175] Check failed: err == cudaSuccess || err == cudaErrorInvalidValue Unexpected CUDA error: out of memory

It is result when i run nvidia-smi

+-----------------------------------------------------------------------------+ | NVIDIA-SMI 384.130 Driver Version: 384.130 | |-------------------------------+----------------------+----------------------+ | GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC | | Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. | |===============================+======================+======================| | 0 GeForce 840M Off | 00000000:0A:00.0 Off | N/A | | N/A 39C P5 N/A / N/A | 249MiB / 2002MiB | 0% Default | +-------------------------------+----------------------+----------------------+

+-----------------------------------------------------------------------------+ | Processes: GPU Memory | | GPU PID Type Process name Usage | |=============================================================================| | 0 1065 G /usr/lib/xorg/Xorg 119MiB | | 0 1822 G compiz 79MiB | | 0 2280 G /opt/teamviewer/tv_bin/TeamViewer 9MiB | | 0 4531 G ...AAAAAAAAAAAACAAAAAAAAAA= --shared-files 39MiB | +-----------------------------------------------------------------------------+

I should fix it by Monday. plz help me plz pleaseeeeee...... Thanks