deepin-ocr/3rdparty/ncnn/benchmark/alexnet.param
wangzhengyang 718c41634f feat: 切换后端至PaddleOCR-NCNN,切换工程为CMake
1.项目后端整体迁移至PaddleOCR-NCNN算法,已通过基本的兼容性测试
2.工程改为使用CMake组织,后续为了更好地兼容第三方库,不再提供QMake工程
3.重整权利声明文件,重整代码工程,确保最小化侵权风险

Log: 切换后端至PaddleOCR-NCNN,切换工程为CMake
Change-Id: I4d5d2c5d37505a4a24b389b1a4c5d12f17bfa38c
2022-05-10 10:22:11 +08:00

18 lines
1.6 KiB
Plaintext

7767517
15 15
Input data 0 1 data -23330=4,3,227,227,3 0=227 1=227 2=3
Convolution conv1 1 1 data conv1_relu1 -23330=4,3,55,55,96 0=96 1=11 3=4 5=1 6=34848 9=1
LRN norm1 1 1 conv1_relu1 norm1 -23330=4,3,55,55,96 2=1.000000e-04
Pooling pool1 1 1 norm1 pool1 -23330=4,3,27,27,96 1=3 2=2
ConvolutionDepthWise conv2 1 1 pool1 conv2_relu2 -23330=4,3,27,27,256 0=256 1=5 4=2 5=1 6=307200 7=2 9=1
LRN norm2 1 1 conv2_relu2 norm2 -23330=4,3,27,27,256 2=1.000000e-04
Pooling pool2 1 1 norm2 pool2 -23330=4,3,13,13,256 1=3 2=2
Convolution conv3 1 1 pool2 conv3_relu3 -23330=4,3,13,13,384 0=384 1=3 4=1 5=1 6=884736 9=1
ConvolutionDepthWise conv4 1 1 conv3_relu3 conv4_relu4 -23330=4,3,13,13,384 0=384 1=3 4=1 5=1 6=663552 7=2 9=1
ConvolutionDepthWise conv5 1 1 conv4_relu4 conv5_relu5 -23330=4,3,13,13,256 0=256 1=3 4=1 5=1 6=442368 7=2 9=1
Pooling pool5 1 1 conv5_relu5 pool5 -23330=4,3,6,6,256 1=3 2=2
InnerProduct fc6 1 1 pool5 fc6_drop6 -23330=4,1,4096,1,1 0=4096 1=1 2=37748736 9=1
InnerProduct fc7 1 1 fc6_drop6 fc7_drop7 -23330=4,1,4096,1,1 0=4096 1=1 2=16777216 9=1
InnerProduct fc8 1 1 fc7_drop7 fc8 -23330=4,1,1000,1,1 0=1000 1=1 2=4096000
Softmax prob 1 1 fc8 output -23330=4,1,1000,1,1