Detectron.pytorch

Detectron.pytorch copied to clipboard

When I run the inference command,the error is: `UnicodeDecodeError: 'ascii' codec can't decode byte 0xf5 in position 1: ordinal not in range(128)` How to solve this problem? btw,I followed the...

Yinhance

_pickle.UnpicklingError: invalid load key, '\x0a'.

2

I followed your guidance and met the problem below when I run the code : "python /home/liujianguo/jiguo/mask-rcnn.pytorch/tools/train_net_step.py --dataset coco2017 --cfg /home/liujianguo/jiguo/mask-rcnn.pytorch/configs/baselines/e2e_mask_rcnn_R-50-C4_1x.yaml --bs 2 --iter_size 1" Traceback (most recent call last):...

guoguotingzhu

undefined symbol: __cudaRegisterFatBinaryEnd

1

I am getting the following error and I don't understand how to get rid of it coz my cuda version and symlinks are correct. ImportError: /home/anam/Codes/mask-rcnn.pytorch/lib/model/roi_pooling/_ext/roi_pooling/_roi_pooling.so: undefined symbol: __cudaRegisterFatBinaryEnd Command...

ZahraAnam

WRONG: cd lib sh make.sh

19

I build this repo as your guide, but when I run cd lib & sh make.sh, I got the following error: /opt/conda/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/THC/THCGeneral.h:12:18: fatal error: cuda.h: No such file or directory...

Ai-is-light

## PLEASE FOLLOW THESE INSTRUCTIONS BEFORE POSTING 1. **Read the README.md thoroughly ! README.md is not a decoration.** 2. Please search existing *open and closed* issues in case your issue...

henbucuoshanghai

AssertionError: Range subprocess failed (exit code: 1)

3

The command that I ran python tools/test_net.py --dataset coco2017 --cfg configs/panet/e2e_panet_R-50-FPN_2x_mask.yaml --multi-gpu-testing --load_ckpt /home1/chelixuan/PANet_old/Outputs/e2e_panet_R-50-FPN_2x_mask/Oct31-19-45-45_2x1080Ti-36_step/ckpt/model_step17999 ------------------------------------------------------------------------------------------------------------------------------------------- problem: loading annotations into memory... Done (t=0.35s) creating index... index created! INFO test_engine.py: 330: loading...

chelixuan

Hi, it can work when I run test_net.py with one gpu . But it is too slow, so I run with command "--multi-gpu-testing" .By the way, I have 4 GPUS....

azhuantou

AttributeError: 'module' object has no attribute 'getLogger'

11

Hi, when I run the benchmark ``` python tools/train_net_step.py \ --dataset coco2017 --cfg configs/e2e_faster_rcnn_R-50-FPN_1x.yaml \ --bs 8 --iter_size 2 --use_tfboard ``` , I got the error: ``` Traceback (most recent...

JudyYe

Accounting for varying object size in images of constant size

1

This issue is somewhat related to #86. I understand that `TRAIN.SCALES` parameter allows us to show the scaled version of the image to the model. My question is will this...

ashnair1

Compile the CUDA code on Win10/Win7

3

Has anyone successfully complied the CUDA code on Windows? I do not know how to compile it on Windows.

wuyi1983