CenterNet

CenterNet copied to clipboard

Hey, I am trying to understand this sentence from section 3.3 : ``` It first looks along a boundary to find a boundary maximum value ``` in other words "normal...

gr33n1

import top_pool error!!

5

File "train.py", line 18, in from nnet.py_factory import NetworkFactory File "/home/travail/zfkang/CenterNet/nnet/py_factory.py", line 8, in from models.py_utils.data_parallel import DataParallel File "/home/travail/zfkang/CenterNet/models/py_utils/__init__.py", line 6, in from ._cpools import TopPool, BottomPool, LeftPool, RightPool...

Kangzf1996

undefined symbol: _ZNSt15__exception_ptr13exception_ptr10_M_releaseEv

1

I get this error when I try to run `python train.py CenterNet-52` ``` Traceback (most recent call last): File "train.py", line 18, in from nnet.py_factory import NetworkFactory File "/home/prajwal/CenterNet/nnet/py_factory.py", line...

Prajwal-Gupta

Hi I tested inference of the `CenterNet HourGlass104 512x512` implementation on [Tensorflow 2 Object Detection API](https://colab.research.google.com/github/tensorflow/hub/blob/master/examples/colab/tf2_object_detection.ipynb#scrollTo=rOvvWAVTkMR7). I found `CenterNet HourGlass104 512x512` feature extractor to be useful in object detection for...

santhoshnumberone

why do you copy the data in minival2014 to train2014 and the data in minival2014 to testdev2017? for what? what's the point? thx so much

sanwei111

I was using my customized COCO dataset to train a new model I use the command "python train.py CenterNet-52" and I modified relevant configs. but I got this error. could...

Dogeeeeeee

ImportError

1

Traceback (most recent call last): File "test.py", line 14, in from nnet.py_factory import NetworkFactory File "/home/wickked/Net/CenterNet/nnet/py_factory.py", line 8, in from models.py_utils.data_parallel import DataParallel File "/home/wickked/Net/CenterNet/models/py_utils/__init__.py", line 6, in from ._cpools...

Wickked-swag

Testing this on my own dataset

20

Hey how can I integrate this in a project like how can I run it on a bunch of images and get bounding boxes and confidence score in return .

chariot1498

Compiling Corner Pooling Layers Error

1

cc1plus: warning: command line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++ src/top_pool.cpp: In function ‘std::vector top_pool_backward(at::Tensor, at::Tensor)’: src/top_pool.cpp:44:41: error: could not convert ‘at::CUDA((c10::ScalarType)6)’ from ‘at::DeprecatedTypeProperties’ to ‘c10::IntArrayRef...

ChenJiaDeYang

> ERROR:--->>>CUDA out of memory. Tried to allocate 1.02 GiB (GPU 0; 15.75 GiB total capacity; 13.79 GiB already allocated; 261.62 MiB free; 570.45 MiB cached)

ChenJiaDeYang