Mihai Maruseac ce945d5b0e [tflite] Ensure ResolveAxis properly handles negative inputs. ... In Python, a list `l` of length `n` allows indexing with negative indices, `l[i]`. The only constraint is that `n + i` becomes positive. Code in `ResolveAxis` assumes the constraints and only checks it using a `DCHECK`. But the macro is a no-op in non-debug builds and that can result in reading from negative offsets (buffer underflows). PiperOrigin-RevId: 332530683 Change-Id: I464e073fee618054ae3719a3679739007bb3f3bc		2020-09-19 18:19:28 -07:00
..
optimized	Fix compilation error, use vreinterpreq instead.	2019-08-04 22:28:49 -07:00
reference	[tflite] Ensure ResolveAxis properly handles negative inputs.	2020-09-19 18:19:28 -07:00
averagepool_quantized_test.cc	Fix shape populating.	2019-05-14 00:07:09 -07:00
batch_to_space_nd_test.cc
BUILD	Move binary functions to a separate header.	2019-08-05 19:51:02 -07:00
common.h	Fix for SparkFun Edge build problem	2019-06-25 23:48:36 -07:00
compatibility.h
depthwiseconv_float_test.cc	Don't access CpuBackendContext concurrently from multiple threads.	2019-05-30 12:38:39 -07:00
depthwiseconv_per_channel_quantized_test.cc	change depthwise_conv 3x3 filter offset add logic since for per-channel case we're always using symmetric quantization.	2019-05-28 22:32:07 -07:00
depthwiseconv_quantized_test.cc	Make TfLiteInternalBackendContext as a interface-only abstract class.	2019-07-22 19:34:07 -07:00
kernel_utils.cc
kernel_utils.h
legacy_types.h
log_quantized_test.cc	Create int8 log softmax.	2019-02-19 13:20:27 -08:00
logsoftmax_quantized_test.cc	Create int8 log softmax.	2019-02-19 13:20:27 -08:00
maxpool_quantized_test.cc	Fix shape populating.	2019-05-14 00:07:09 -07:00
mfcc_dct.cc	Avoid ambiguous math overloads	2019-04-16 16:38:16 -07:00
mfcc_dct.h
mfcc_mel_filterbank.cc	Replace log(1 + x) with numerically more stable log1p(x)	2019-02-27 00:35:53 +00:00
mfcc_mel_filterbank.h
mfcc.cc
mfcc.h
quantization_util_test.cc
quantization_util.cc
quantization_util.h
resize_bilinear_test.cc	Rein in some zealous tests, now that we care about their latency in slower configs, such as ARM emulator and various sanitizers.	2019-05-13 14:22:41 -07:00
resize_nearest_neighbor_test.cc
round.h	Arduino project generation	2019-03-26 15:57:42 -07:00
softmax_quantized_test.cc	Optimize 8bit Softmax op handler	2019-08-02 17:52:28 -07:00
spectrogram.cc	Avoid ambiguous math overloads	2019-04-16 16:38:16 -07:00
spectrogram.h	Add missing declarations for explicit instantiations.	2019-06-12 18:28:50 -07:00
strided_slice_logic.h
tensor_ctypes.h	Add missing TfLiteFloat16 specialization to GetTensorData.	2019-07-22 15:16:36 -07:00
tensor_test.cc
tensor_utils_test.cc	Require that the batch size be less than or equal to the size of the	2019-03-05 05:45:13 -08:00
tensor_utils.cc	Add x86 vector code using SSE 4.1 for MatrixBatchVectorMultiplyAccumulate and SparseMatrixBatchVectorMultiplyAccumulate, int8 versions only.	2019-06-26 17:55:26 -07:00
tensor_utils.h	Internal change	2019-05-29 14:35:13 -07:00
tensor.h	Add string support to slice.	2019-04-04 18:00:53 -07:00
test_util.cc
test_util.h
types.h	[tflite] Ensure MatchingDim does not allow buffer overflow.	2020-09-19 18:09:52 -07:00