pytorch-faster-rcnn

pytorch-faster-rcnn copied to clipboard

Just Train Network for Person Detection

1

Dear @ruotianluo, Thank you for your work. I have a general question. In the **VOC** and **COCO** datasets there are some classes (_e.g._, 20 or 80 classes (person, car, horse,...

ahkarami

Training loss has been oscillating and does not converge.

2

My training loss has been oscillating and does not converge. All parameters are default. My training command is : ./experiments/scripts/train_faster_rcnn_notime.sh 1 pascal_voc vgg16

yuanyao366

CUDA 9.0

2

Hi, is it possible use this project having CUDA 9.0? Because I've just tried but I have this error when I run: `./experiments/scripts/train_faster_rcnn.sh 0 pascal_voc vgg16` and maybe it's a...

capuzz

ImportError: dlopen: cannot load any more object with static TLS

3

Traceback (most recent call last): File "/home/yang/pytorch-faster-rcnn/tools/convert_from_tensorflow_vgg.py", line 2, in import torch File "/usr/local/lib/python2.7/dist-packages/torch/__init__.py", line 53, in from torch._C import * ImportError: dlopen: cannot load any more object with static...

yhz5256

MY computer just freezes and then restarts by itself when i use this to train on my dataset.

7

MY computer just freezes and then restarts by itself when i use this to train on my dataset. Can anyone guess how this could occur. I compilde all the files...

manoja328

An error happened when running build.py of roi pooling

4

Eecuse me if anyone get this problem like this,can you tell me how to solve this problem please. x86_64-linux-gnu-gcc -pthread -DNDEBUG -g -fwrapv -O2 -Wall -Wstrict-prototypes -fno-strict-aliasing -Wdate-time -D_FORTIFY_SOURCE=2 -g...

lianshushu

Test Without GPU

1

Hi, I downloaded and run the code on nVidia Tesla P100. I set the -arch flag to sm_60 and successfully trained and tested the model with GPUS on COCO 2014...

mahiratmis

Error occur during training , Command terminated by signal 15

1

 This occur when I run ./experiments/scripts/train_faster_rcnn.sh 1 coco res101 With env TITAN X (Pascal) , Ubuntu 16.04.1

aliceyayunji

libprotobuf error causes crash in the middle of training

4

I'm running into a strange error. During training (after several thousand iterations), my training script crashes with the error ```bash libprotobuf FATAL google/protobuf/wire_format.cc:830] CHECK failed: (output->ByteCount()) == (expected_endpoint): : Protocol...

Feynman27

add ENV variable to flag build with CUDA (instead of only "torch.cuda…

2

I want to run the build scripts from within a docker container. I use nvidia-docker but the nvidia devices are not available during build by design. All the cuda libraries...

brandonfranzke