- Sort Score
- Result 10 results
- Languages All
Results 1 - 10 of 10 for conv_2d (0.13 sec)
-
tensorflow/compiler/mlir/lite/stablehlo/tests/uniform-quantized-stablehlo-to-tfl.mlir
} // Confirm that the `stablehlo.convolution` is not converted to `tfl.conv_2d`. // CHECK-LABEL: convolution_upstream_srq_non_const_filter // CHECK-SAME: %[[ARG:.+]]: tensor<1x3x3x4x!quant.uniform<i8:f32, 1.000000e+00:-100>> // CHECK: stablehlo.convolution // CHECK-NOT: tfl.conv_2d // ----- // Tests that if the window padding contains values of 0, tfl.pad op is not
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue May 14 17:10:32 UTC 2024 - 106.2K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/tests/ops.mlir
func.func @testConv2D(tensor<256x32x32x3xf32>, tensor<16x3x3x3xf32>, tensor<16xf32>) -> tensor<256x32x32x16xf32> { ^bb0(%arg0: tensor<256x32x32x3xf32>, %arg1: tensor<16x3x3x3xf32>, %arg2: tensor<16xf32>): // CHECK: "tfl.conv_2d"(%arg0, %arg1, %arg2)
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Jun 06 19:09:08 UTC 2024 - 189.2K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/stablehlo/transforms/uniform_quantized_stablehlo_to_tfl_pass.cc
FindUserOfType<TFL::QuantizeOp>(op) != nullptr); } }; // Rewrites `stablehlo.convolution` into fused `tfl.conv_2d`. // If available, fuse bias and activation adjacent to `stablehlo.convolution`. // This RewritePattern rewrites both the following into `tfl.conv_2d` op: // // StableHLO Quantizer output: // * input: per-tensor qi8 // * filter: per-channel qi8 (`quantization_dimension` = 3)
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Mon Apr 22 09:00:19 UTC 2024 - 99.8K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/transforms/optimize.cc
// with a 0-d constant, e.g. before this optimization, // %cst = arith.constant dense<1.0> : tensor<16x16x4xf32> // %0 = "tfl.conv_2d"... // %1 = "tfl.add"(%0, %cst) : (tensor<16x16x4xf32>, tensor<16x16x4xf32>) // After this optimization: // %cst = arith.constant dense<1.0> : tensor<f32> // %0 = "tfl.conv_2d"... // %1 = "tfl.add"(%0, %cst) : (tensor<16x16x4xf32>, tensor<f32>)
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue Apr 30 00:40:15 UTC 2024 - 102.3K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/stablehlo/transforms/legalize_hlo.cc
auto conv_result = rewriter.create<mhlo::ConvolutionOp>( conv_op.getLoc(), new_output_type, sliced_input, sliced_kernel, conv_op.getWindowStridesAttr(), conv_op.getPaddingAttr(), conv_op.getLhsDilationAttr(), conv_op.getRhsDilationAttr(), conv_op.getWindowReversalAttr(), conv_op.getDimensionNumbers(), 1, 1, conv_op.getPrecisionConfigAttr()); conv_results.push_back(conv_result);
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Apr 25 16:01:03 UTC 2024 - 154.9K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/ir/tfl_ops.td
in the flatbuffer. }]; let arguments = (ins I32Attr:$buffer_index); let results = (outs AnyTensor:$output); } def TFL_Conv2DOp : TFL_ConvOp<"conv_2d", "Convolution", 0, [DeclareOpInterfaceMethods<InferTypeOpInterface>, DeclareOpInterfaceMethods<TFL_ArithmeticCount>, DynamicRangeQuantizedOpInterface]> { let arguments = (
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Jun 06 19:09:08 UTC 2024 - 186K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/tensorflow/python/integration_test/quantize_model_test.py
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Fri May 17 03:36:50 UTC 2024 - 235.6K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/tests/legalize-tf.mlir
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed Jun 05 01:54:33 UTC 2024 - 153.4K bytes - Viewed (0) -
tensorflow/compiler/mlir/tensorflow/transforms/tf_passes.td
%device_launch = "tf_device.cluster_func"(%input,...) {func = @_func,...) return ... } func @_func(%input: tensor<2x224x224x3xf32>, %filter: tensor<7x7x3x64xf32>) { %6 = "tf.Conv2D"(%input, %filter) {strides = [1, 2, 2, 1]}: (tensor<2x230x230x3xf32>, tensor<7x7x3x64xf32>) -> tensor<2x112x112x64xf32> } } ``` The program will be transformed into: ```mlir
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed Jun 12 21:18:05 UTC 2024 - 99.6K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/ir/tfl_ops.cc
return emitOptionalError(location, "invalid padding format provided"); } // Output always have rank 4. All dimensions are initialized to // dynamic size and can be partially inferred. // TFL's conv2d is always NHWC format & the filter is OHWI. SmallVector<int64_t, 4> return_shape(4, ShapedType::kDynamic); return_shape[0] = input_ty.getDimSize(0); return_shape[3] = filter_ty.getDimSize(0);
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu May 02 09:41:17 UTC 2024 - 169.2K bytes - Viewed (0)