bonnetal

bonnetal copied to clipboard

Hi, I have tested the mapillary_mobilenetsv2_aspp_res_512_os8_34 model on my video but the result in python is better than C++. I used Pytorch on both of them.  

sctrueew

FPS

1

Hello, I'm using PyTorch GPU and "MobilenetsV2 ASPP Res - 512px" model with Python and C++ but I get ~94ms on my PC. Is it ok or not? OS: Win...

sctrueew

Inference uses too much GPU memory

3

Hi, I have trained a model on my own data, and now trying to run inference. When running `infer_img.py` on one image (640x480) I see my GPU (GeForce GTX 1080)...

ivannson

terminate called after throwing an instance of 'c10::Error'

2

Hi, I am trying to run segmentation using pretrained model. I am using docker on Ubuntu 18.04 with GPU. nvidia-smi works fine (but whole gpu mem is already used for...

karolmajek

Training terminates after the first epoch due to excessive RAM usage

4

I am trying to train a semantic segmentation model from scratch using COCO dataset, and every time I try to run the training script, it is `Killed` at the validation...

ivannson

I am finding the same error but do not seem to be able to solve it. I have changes the labels and preprocessed the label file (changed labels.py and ran...

cristinanavarrorubio