- Sort Score
- Result 10 results
- Languages All
Results 1 - 10 of 66 for conv_3d (0.15 sec)
-
tensorflow/compiler/mlir/lite/tests/prepare-tf-with-allowing-bf16-and-f16-type-legalization.mlir
%0 = "tf.Conv2D"(%arg0, %arg1) {T = "tfdtype$DT_FLOAT", data_format = "NHWC", dilations = [1, 2, 3, 1], padding = "SAME", strides = [1, 4, 5, 1]} : (tensor<256x32x32x3xbf16>, tensor<3x3x3x16xbf16>) -> tensor<256x8x7x16xbf16> func.return %0 : tensor<256x8x7x16xbf16> // CHECK: "tfl.conv_2d" } // CHECK-LABEL: fused_batch_norm_v3_bf16
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu May 26 23:53:32 UTC 2022 - 2.2K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/tensorflow/tests/insert_quantized_functions.mlir
// CHECK: func private @quantized_matmul_with_relu_fn // CHECK: func private @quantized_matmul_with_relu6_fn // CHECK: func private @quantized_conv3d_with_bias_fn // CHECK-SAME: tf_quant.quantized_ops = ["Conv3D", "BiasAdd"] // CHECK: func private @quantized_batch_matmul_with_bias_fn // CHECK-SAME: tf_quant.quantized_ops = ["BatchMatMul", "BiasAdd"] // CHECK: func private @quantize_i8 // CHECK: func private @dequantize_i8
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue Aug 29 01:13:58 UTC 2023 - 3.3K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/tests/optimize_functional_ops.mlir
else_branch = @_functionalize_if_else_branch_00, is_stateless = false, then_branch = @_functionalize_if_then_branch_00} : (tensor<i1>, tensor<i1>, tensor<3x15x14x3xf32>, tensor<3x15x14x3xf32>) -> tensor<i1>
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed Mar 30 10:34:48 UTC 2022 - 8.4K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/tensorflow/passes/quantized_function_library_xla_weight_only.mlir
parameters[ {"quantized_ops": ["MatMul"], "internal_func_name": "internal_matmul_fn"}, {"quantized_ops": ["Conv2D"], "internal_func_name": "internal_conv2d_fn"}, {"quantized_ops": ["DepthwiseConv2D"], "internal_func_name": "internal_depthwise_conv2d_fn"}, {"quantized_ops": ["Conv3D"], "internal_func_name": "internal_conv3d_fn"}, {"quantized_ops": ["BatchMatMul"], "internal_func_name": "internal_batch_matmul_fn"} ]
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Fri Mar 03 15:43:38 UTC 2023 - 7K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/experimental/tac/transforms/device_transform_patterns.h
PatternRewriter& rewriter) const override; }; // Ensure bias for conv2d op. struct EnsureBiasForConv2d : public OpRewritePattern<TFL::Conv2DOp> { using OpRewritePattern<TFL::Conv2DOp>::OpRewritePattern; LogicalResult matchAndRewrite(TFL::Conv2DOp conv_op, PatternRewriter& rewriter) const override; }; // Pad slice to 4d.
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Mar 03 16:37:16 UTC 2022 - 4.3K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/common/quantization_lib/quantization.td
tensor<64x3x3x3xf32> %conv = "tfl.conv_2d"(%input_act, %w, %bias) but if it is supported, it will be rewritten as: %q_w = "tfl.pseudo_qconst"() { qtype = tensor<64x3x3x3x!quant.uniform<i8<-127:127>:f32, 1.000000e+00>> %conv = "tfl.conv_2d"(%input_act, %q_w, %bias) Note that this is part of reaching feature parity with the old quantizer for
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue Mar 05 07:39:40 UTC 2024 - 8.3K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir/optional_input.json
// This test is to test that if the flatbuffer omits the last optional input `bias` of tfl.conv_2d op, the flatbuffer_importer will automatically adds `none` value to tfl.conv_2d. // CHECK: %[[CST:.*]] = "tfl.no_value"() <{value}> : () -> none
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu May 02 09:41:17 UTC 2024 - 1.8K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/tensorflow/ops/tf_op_quant_spec.cc
if (function_name.contains("with_bias")) { spec->biases_params[2] = {{0, 1}, quant::GetUniformQuantizedTypeForBias}; } } else if (function_name.contains("conv3d")) { spec->coeff_op_quant_dim[1] = 4; if (function_name.contains("with_bias")) { spec->biases_params[2] = {{0, 1}, quant::GetUniformQuantizedTypeForBias}; }
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Apr 25 16:01:03 UTC 2024 - 6.3K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/tests/optimize-after-quantization.mlir
%dq = "tfl.dequantize"(%q) : (tensor<3x3x3x3x!quant.uniform<i8:f32, 0.1:1>>) -> tensor<3x3x3x3xf32>
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Fri Jan 05 18:35:42 UTC 2024 - 1.4K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir/import_json.json
// RUN: json_to_flatbuffer %p/test_schema.fbs %s | flatbuffer_translate --tflite-flatbuffer-to-mlir -o - | FileCheck %s // CHECK: %[[CST:.*]] = "tfl.no_value"() <{value}> : () -> none // CHECK: %[[RES0:.*]] = "tfl.conv_2d"(%arg0, %arg1, %[[CST]]) <{dilation_h_factor = 1 : i32, dilation_w_factor = 1 : i32, fused_activation_function = "NONE", padding = "SAME", stride_h = 1 : i32, stride_w = 1 : i32}> : (tensor<256x32x32x3xf32>, tensor<16x3x3x3xf32>, none) -> tensor<256x32x32x16xf32>
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu May 02 09:41:17 UTC 2024 - 1.8K bytes - Viewed (0)