1. 22 5月, 2019 3 次提交
    • Y
      Fix examples of fluid.layers.sums and fluid.layers.DynamicRNN (#17308) · cf5d271c
      Yiqun Liu 提交于
      * Fix examples of fluid.layers.sums.
      test=document_preview
      
      * Correct the example of DynamicRNN and its functions.
      test=develop
      
      * Add 'import paddle.fluid as fluid' to examples.
      test=develop
      
      * Update API.spec.
      test=develop
      
      * Add space lines.
      test=develop
      
      * Update the API.spec.
      test=develop
      cf5d271c
    • G
      Enable the convolution/relu6(bounded_relu) fusion for FP32 on Intel platform. (#17130) · 2281ebf0
      guomingz 提交于
      * Relu6 is the bottleneck op for Mobilenet-v2. As the mkldnn supports the conv/relu6 fusion, we implement it fusion via cpass way. Due to the int8 enabling for this fusion will be supported in MKLDNN v0.20, so this PR is focused on the fp32 optimization.
      
      Below table shows the benchmark(FPS) which measured on skx-8180(28 cores)
      Batch size | with fusion | without fusion
      -- | -- | --
      1 | 214.7 | 53.4
      50 | 1219.727 | 137.280
      
      test=develop
      
      * Fix the format issue
      
      test=develop
      
      * Add the missing nolint comments.
      
      test=develop
      
      * Fix the typos.
      
      test=develop
      
      * Register the conv_brelu_mkldnn_fuse_pass for the MKLDNN engine.
      
      test=develop
      
      * Adjust the indentation.
      
      test=develop
      
      * Add the test_conv_brelu_mkldnn_fuse_pass case.
      
      test=develop
      
      * Slightly update the code per Baidu comments.
      Let the parameter definition embedded into the code.
      That's will make the code easy to understand.
      
      test=develop
      2281ebf0
    • Z
      Adding AddQuantDequantPass for TensorRT int8 (#17529) · 3398f996
      Zhen Wang 提交于
      * add quant_dequant_pass, test=develop
      
      * Add quant_dequant before some ops, such as the elementwise_add op. This is required by TensorRT. test=develop
      3398f996
  2. 21 5月, 2019 10 次提交
  3. 20 5月, 2019 9 次提交
  4. 19 5月, 2019 2 次提交
  5. 18 5月, 2019 3 次提交
  6. 17 5月, 2019 7 次提交
  7. 16 5月, 2019 6 次提交