- Sort Score
- Result 10 results
- Languages All
Results 51 - 57 of 57 for fully_connected (0.9 sec)
-
tensorflow/compiler/mlir/lite/experimental/tac/tests/raise-target-subgraphs.mlir
%5 = "tfl.pseudo_const"() {value = dense<1.000000e+00> : tensor<128x128xf32>} : () -> tensor<128x128xf32> %6 = "tfl.pseudo_const"() {value = dense<1.000000e+00> : tensor<128xf32>} : () -> tensor<128xf32> %7 = "tfl.fully_connected"(%4, %5, %6) {tac.device = "CPU", tac.inference_type = "FLOAT", fused_activation_function = "NONE", keep_num_dims = false, weights_format = "DEFAULT"} : (tensor<128x128xf32>, tensor<128x128xf32>, tensor<128xf32>) -> tensor<128x128xf32>
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu May 02 09:41:17 UTC 2024 - 74.9K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/ir/tfl_ops.td
std::vector<int> GetQuantizableOperandIndices() { return {1}; } }]; } // TODO(jpienaar): Update post discussion on semantics of FC OP. def TFL_FullyConnectedOp : TFL_Op<"fully_connected", [ Pure, AccumulatorUniformScale<2, 0, 1>, AffineQuantizedOpInterface, AffineOpCoefficient<0, 1>, TFL_SparseOp, DeclareOpInterfaceMethods<TFL_ArithmeticCount>, QuantizableResult,
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/lite/tf_tfl_translate_cl.cc
llvm::cl::init("")); // NOLINTNEXTLINE opt<bool> unfold_batchmatmul( "unfold_batchmatmul", llvm::cl::desc( "Whether to unfold TF BatchMatMul to a set of TFL FullyConnected ops."), llvm::cl::init(false)); // NOLINTNEXTLINE opt<bool> unfold_large_splat_constant( "unfold-large-splat-constant", llvm::cl::desc("Whether to unfold large splat constant tensors to reduce "
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue Mar 05 20:53:17 UTC 2024 - 7.9K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/transforms/dense_to_sparse.cc
} else { result.can_compress = false; return result; } // Currently we only support compressing weights of ops: // Conv, DepthwiseConv, TransposeConv, whose filter has rank 4, and // FullyConnected, whose filter has rank 2. if (type.getRank() != 2 && type.getRank() != 4) { result.can_compress = false; return result; } float random_sparsity = CalculateRandomSparsity(attr, type);
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Apr 25 16:01:03 UTC 2024 - 16.1K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/transforms/legalize_patterns.td
def LegalizeDiv : Pat<(TF_DivOp $lhs, $rhs), (TFL_DivOp $lhs, $rhs, TFL_AF_None)>; // When batch size is known, TF BatchMatMul gets unfolded to TFL FullyConnected // with additional ops. In the case of unknown batch size, the match will // fall through to here and convert to TF Lite BatchMatMul. // TODO(b/207064634): CreateEmptyBoolAttr is a temporary workaround for this bug.
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue Jun 04 13:30:42 UTC 2024 - 28.5K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/schema/schema_generated.h
"ADD", "AVERAGE_POOL_2D", "CONCATENATION", "CONV_2D", "DEPTHWISE_CONV_2D", "DEPTH_TO_SPACE", "DEQUANTIZE", "EMBEDDING_LOOKUP", "FLOOR", "FULLY_CONNECTED", "HASHTABLE_LOOKUP", "L2_NORMALIZATION", "L2_POOL_2D", "LOCAL_RESPONSE_NORMALIZATION", "LOGISTIC", "LSH_PROJECTION", "LSTM", "MAX_POOL_2D", "MUL",
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue May 21 18:21:50 UTC 2024 - 1M bytes - Viewed (0) -
RELEASE.md
modified to return nan when they have seen less or equal to 1 unit of weight. * Adds time series models to contrib. See contrib/timeseries/README.md for details. * Adds FULLY_CONNECTED Op to tensorflow/lite/schema.fbs ## Known Issues * Tensorflow_gpu compilation fails with Bazel 0.5.3. ## Bug Fixes and Other Changes
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue Jun 11 23:24:08 UTC 2024 - 730.3K bytes - Viewed (0)