Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 1 of 1 for GetConv2DInputArgNum (0.22 sec)

  1. tensorflow/compiler/mlir/tensorflow/transforms/tpu_space_to_depth_pass.cc

    // Only the first convolution in the graph whose batch size smaller than 8
    // and its input feature size smaller than 8 can be transformed.
    std::optional<BlockArgumentInfo> GetConv2DInputArgNum(TF::Conv2DOp conv2d) {
      if (conv2d.getDataFormat() != "NHWC" || conv2d.getStrides().size() != 4) {
        return std::nullopt;
      }
      // Current supported ops between convolution input and the block arguments are
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Thu Apr 25 16:01:03 UTC 2024
    - 29.3K bytes
    - Viewed (0)
Back to top