caffe_ocr_for_linux

caffe_ocr_for_linux copied to clipboard

DenseBlock编译错误

4

In file included from src/caffe/layers/DenseBlock_layer.cpp:19:0: ./include/caffe/layers/DenseBlock_layer.hpp:147:3: error: ‘cudnnTensorDescriptor_t’ does not name a type cudnnTensorDescriptor_t * quadG_tensorDesc; ^ ./include/caffe/layers/DenseBlock_layer.hpp:148:3: error: ‘cudnnTensorDescriptor_t’ does not name a type cudnnTensorDescriptor_t * quadG_paramDesc; ^ ./include/caffe/layers/DenseBlock_layer.hpp:149:3:...

Lesley96-11

Makefile:601: recipe for target '.build_release/cuda/src/caffe/layers/DenseBlock_layer.o' failed

3

I ran into the following error: NVCC src/caffe/layers/cudnn_sigmoid_layer.cu /usr/local/include/boost/core/noncopyable.hpp(42): error: defaulted default constructor cannot be constexpr because the corresponding implicitly declared default constructor would not be constexpr 1 error detected...

ReallySpicyChicken

编译和测试没问题，但在训练模型时出现warp_ctc_loss_layer.cu:118] Check failed: status == CTC_STATUS_SUCCESS (3 vs. 0)

2

你好，编译通过了，测试也没有问题，但是在训练模型时出现warp_ctc_loss_layer.cu:118] Check failed: status == CTC_STATUS_SUCCESS (3 vs. 0) CTC Error: execution failed 怎么解决呢？谢谢

Echo-byte

lt573152873

预测时，置信度，怎么得到

shaoshuaiche

shaoshuaiche

关于测试脚本

15

我用来训练7位的英文字母，训练的时候准确率达到99.9%以上，但是我就用训练集进行测试，结果只有不到3%完全正确，测出来的结果是6位甚至5位，是测试脚本的问题么？

AllenDuane

这个操作没有啊

HouBiaoLiu

我在进行ocr_test测试时，使用第0块显卡；现在我想通过命令行参数传递使用哪块选卡，于是做了如下修改 bool Classifier::Init(const string& model_path, int gpu_id) { const string trained_file = model_path + "/model.caffemodel"; const string model_file = model_path + "/deploy.prototxt"; string mean_file = model_path + "/mean.binaryproto"; const string...

HouBiaoLiu

将fc1x层的节点数由5990变为36（因为我只识别数字和大写英文字母），无法训练，loss=nan

12

HouBiaoLiu