We have a simple socket services written in python that loads keras model and YoloV5 model into memory, and prediction is run on images when socket receives messages.
The problem is every time a prediction is run on either Keras or Yolo5, the python process's memory consumption grows, and after thousands of predictions the python process will run out of memory.
We need you to fix the memory leak, please note the following:
1. [login to view URL]() did't help.
2. We can't reload the model before each prediction, it takes too long. The model must be preloaded into memory for instant inference.
3. We are doing inferences in CPU only
4. You should test the code with large number of different images.
5. If the memory leak cannot be resolve, we will accept solutions that converts keras/yolov5 models to another framework that doesn't leak.
See attached for example of memory leaking code.
Hello
I faced another case. It is not actually a memory leak, it is a lazy Python memory manager.
In your case you need 3 "stupid" rows of code added. If you were calssic developers trained on C/Pascal, you would notice the problem at once.
Java/Python users do not pay attention to such things.
The only problem for us - no help until my proposal will be accepted and milestone created.
After that you will get a solution immediately.
Regards
$50 USD në 1 ditë
5,0 (15 përshtypje)
5,4
5,4
4 freelancers are bidding on average $141 USD for this job
Hello, thanks for your job posting!
I'm a ML and Computer Vision expert with over 10 years of experience. I just checked your python script and found the right way. I have good experience with optimize the python script with low memory and high performance. Please ping me and discuss in detail.
Thanks.