cascade-rcnn

cascade-rcnn copied to clipboard

make all -j 16 error happens. CXX/LD -o .build_release/tools/extract_features.bin CXX/LD -o .build_release/tools/test_net.bin CXX/LD -o .build_release/tools/net_speed_benchmark.bin CXX/LD -o .build_release/tools/convert_imageset.bin CXX/LD -o .build_release/tools/device_query.bin CXX/LD -o .build_release/tools/compute_image_mean.bin .build_release/tools/caffe.o: In function `time()': caffe.cpp:(.text+0x5cfd): undefined...

job2003

服务器V100, 16G, 8个卡 查询GPU算力不匹配，修改Makefile.config CUDA_ARCH := -gencode arch=compute_50,code=sm_50 \ -gencode arch=compute_52,code=sm_52 \ -gencode arch=compute_60,code=sm_60 \ -gencode arch=compute_61,code=sm_61 \ -gencode arch=compute_61,code=compute_61 依然会报这个错误

nobody-cheng

how to train it on my own dataset

48

hi! I want to train cascade-rcnn on my own dataset (three classes). I don't know how to modify the files(eg. examples/voc/). Can you give me some instructions? Thank you!

derek-zr

@zhaoweicai detectiondatalayer is unkown layer ,我编译的时候看到它编译detection_data_layer.cpp,当我在layer_factory.cpp加入INSTANTIATE_CLASS(DetectionDataLayer); REGISTER_LAYER_CLASS(DetectionData);,编译的时候再次报错CXX/LD -o .build_release/tools/upgrade_net_proto_text.bin .build_release/lib/libcaffe.so: undefined reference to `caffe::DetectionDataLayer<double>::ShuffleMixAspectGroupList()' .build_release/lib/libcaffe.so: undefined reference to `caffe::DetectionDataLayer<float>::ShuffleList()' .build_release/lib/libcaffe.so: undefined reference to `caffe::DetectionDataLayer<double>::~DetectionDataLayer()' .build_release/lib/libcaffe.so: undefined reference to `caffe::DetectionDataLayer<double>::PrefetchRand()'请问是什么原因呢?是opencv的版本吗??

2

zhangshuaitao

python evaluation code

3

I write a python code to evaluate the pretrained model: ``` import argparse import cv2 import numpy as np import sys import os import math import time from PIL import...

mingminzhen

Could you provide a Dockerfile? Does anyone have a Dockerfile?

francesco-p

cascade rcnn真的增加了正样本的数量吗

1

我将rpn阶段下采样得到的512个proposal中的正负样本数量打印出来，发现大多数情况下这512个proposal中也只有几个是正样本，似乎并没有增加正样本的数量呀

hust-kevin

Check failed: status == CUDNN_STATUS_SUCCESS (8 vs. 0) CUDNN_STATUS_EXECUTION_FAILED

4

F1126 12:19:18.211333 23387 cudnn_conv_layer.cu:28] Check failed: status == CUDNN_STATUS_SUCCESS (8 vs. 0) CUDNN_STATUS_EXECUTION_FAILED *** Check failure stack trace: *** @ 0x7fa7b34190cd google::LogMessage::Fail() @ 0x7fa7b341af33 google::LogMessage::SendToLog() @ 0x7fa7b3418c28 google::LogMessage::Flush() @ 0x7fa7b341b999...

neophack

When I run run_cascadercnn_voc.m, I got: Error using containers.Map/subsref The specified key is not present in this container. Error in caffe.Net/blobs (line 82) blob = self.blob_vec(self.name2blob_index(blob_name)); Error in run_cascadercnn_voc (line...

lclin666

some problems when training on my own dataset

1

niezhongliang