寫在前面

官方手冊(cè)上和量化相關(guān)的內(nèi)容：

quantizing a model: https://developer.qualcomm.com/sites/default/files/docs/snpe/model_conversion.html

工具snpe-dlc-quantize：https://developer.qualcomm.com/sites/default/files/docs/snpe/tools.html#tools_snpe-dlc-quantize

何時(shí)使用量化：
https://developer.qualcomm.com/sites/default/files/docs/snpe/quantized_models.html

量化過程

工具位置
在$SNPE_ROOT/bin/x86_64-linux-clang下

命令行下輸入命令進(jìn)行轉(zhuǎn)換./snpe-dlc-quantize --input_dlc inception_v3.dlc --input_list /home/node2/snpe/inception_demo/data/cropped/raw_list.txt snpe-dlc-quantize命令參數(shù)簡(jiǎn)要解析：[-h，——help]顯示幫助信息。 [——version]顯示版本信息。 [——input_dlc]包含定點(diǎn)編碼模型的dlc容器的路徑應(yīng)該生成元數(shù)據(jù)。這個(gè)參數(shù)是必需的。 [——input_list]指定試驗(yàn)輸入的文件的路徑。這個(gè)文件應(yīng)該是純文本文件，每行包含一個(gè)或多個(gè)絕對(duì)文件路徑。這些檔案將被用作試驗(yàn)設(shè)置。每個(gè)路徑都指向一個(gè)包含一個(gè)試驗(yàn)輸入的二進(jìn)制文件“原始”格式，無需任何進(jìn)一步修改即可被SNPE使用。這與向snpe-net運(yùn)行的應(yīng)用程序提供輸入的方式類似。 [——output_dlc = < val >]應(yīng)該寫入包含元數(shù)據(jù)的量化模型容器的路徑。如果省略此參數(shù)，量化模型將寫入_quantized.dlc。

出現(xiàn)報(bào)錯(cuò)./snpe-dlc-quantize: error while loading shared libraries: libomp.so: cannot open shared object file: No such file or directory 查找libomp.so的位置：ind / -name libomp.so 2>/dev/null
將得到的位置加入環(huán)境變量：
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/home/node2/snpe/snpe-1.40.0.2130/lib/x86_64-linux-clang

重復(fù)2中的命令，量化轉(zhuǎn)換成功[INFO] InitializeStderr: DebugLog initialized. [INFO] Writing intermediate model [WARNING] NetworkTopology::populateNetworkDesc network desc inputs is empty. Does this network have data/input layer? [INFO] Setting activation for layer: input:0 and buffer: input:0 [INFO] bw: 8, min: -1.000000, max: 0.992188, delta: 0.007812, offset: -128.000000 [INFO] Setting activation for layer: InceptionV3/InceptionV3/Conv2d_1a_3x3/convolution and buffer: InceptionV3/InceptionV3/Conv2d_1a_3x3/BatchNorm/batchnorm/add_1:0 [INFO] bw: 8, min: -10.426631, max: 10.674884, delta: 0.082751, offset: -126.000000 [INFO] Setting activation for layer: InceptionV3/InceptionV3/Conv2d_1a_3x3/Relu and buffer: InceptionV3/InceptionV3/Conv2d_1a_3x3/Relu:0 [INFO] bw: 8, min: 0.000000, max: 10.647199, delta: 0.041754, offset: 0.000000 [INFO] Setting activation for layer: InceptionV3/InceptionV3/Conv2d_2a_3x3/convolution and buffer: InceptionV3/InceptionV3/Conv2d_2a_3x3/BatchNorm/batchnorm/add_1:0 [INFO] bw: 8, min: -8.310483, max: 8.508352, delta: 0.065956, offset: -126.000000 [INFO] Setting activation for layer: InceptionV3/InceptionV3/Conv2d_2a_3x3/Relu and buffer: InceptionV3/InceptionV3/Conv2d_2a_3x3/Relu:0 [INFO] bw: 8, min: 0.000000, max: 8.484724, delta: 0.033273, offset: 0.000000 [INFO] Setting activation for layer: InceptionV3/InceptionV3/Conv2d_2b_3x3/convolution and buffer: InceptionV3/InceptionV3/Conv2d_2b_3x3/BatchNorm/batchnorm/add_1:0 [INFO] bw: 8, min: -9.289681, max: 10.616778, delta: 0.078065, offset: -119.000000 [INFO] Setting activation for layer: InceptionV3/InceptionV3/Conv2d_2b_3x3/Relu and buffer: InceptionV3/InceptionV3/Conv2d_2b_3x3/Relu:0 [INFO] bw: 8, min: 0.000000, max: 10.628510, delta: 0.041680, offset: 0.000000 [INFO] Setting activation for layer: InceptionV3/InceptionV3/MaxPool_3a_3x3/MaxPool and buffer: InceptionV3/InceptionV3/MaxPool_3a_3x3/MaxPool:0 [INFO] bw: 8, min: 0.000000, max: 10.628510, delta: 0.041680, offset: 0.000000 [INFO] Setting activation for layer: InceptionV3/InceptionV3/Conv2d_3b_1x1/convolution and buffer: InceptionV3/InceptionV3/Conv2d_3b_1x1/BatchNorm/batchnorm/add_1:0 [INFO] bw: 8, min: -6.303848, max: 11.557054, delta: 0.070043, offset: -90.000000

總結(jié)

以上是生活随笔為你收集整理的SNPE教程2-量化的全部?jī)?nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯(cuò)，歡迎將生活随笔推薦給好友。