Jaesung Chung 2d40649f53 Check the dynamic tensor existence of the subgraph outputs at the beginning ... Forwarding inputs without modification won't be not evaluated in the subgraph's operators. So, it needs to look up the subgraph's output tensors at the beginning. PiperOrigin-RevId: 352703717 Change-Id: If299e706cf5c9d4c722e0f85751e7d085a0cd4c3		2021-01-19 19:31:34 -08:00
..
0_subgraphs.bin
2_subgraphs.bin
add_quantized_int8.bin
add_quantized_int8.json
add_quantized.bin
add_quantized.json
add_shared_tensors.bin
add.bin
add.json
custom_lstm.bin	Support calibration of models with 8bit matmul output.	2020-10-30 08:20:41 -07:00
double_flex.bin	Add tests for user's defined op in Flex delegate	2020-11-30 18:24:41 -08:00
dynamic_shapes.bin
empty_model.bin
lstm.bin
multi_add_flex.bin	Flex delegate: Do not use dynamic tensors if possible	2020-09-21 20:11:04 -07:00
multi_add.bin
multi_add.json
multi_add.pb
no_subgraphs.bin
segment_sum_invalid_buffer.bin	[tflite] Ensure input tensors don't have nullptr buffers.	2020-09-18 14:34:47 -07:00
softplus_flex.bin
sparse_tensor.bin
sparse_tensor.json
string_input_model.bin
test_input.csv
test_min_runtime.bin
test_model_broken.bin
test_model_broken.json
test_model_versioned_ops.bin
test_model.bin
two_subgraphs.bin
unidirectional_sequence_lstm.bin	Register Unidirectional_sequence_lstm logging op in calibrator.	2020-10-16 10:26:16 -07:00
while_op_with_forwarding_input.bin	Check the dynamic tensor existence of the subgraph outputs at the beginning	2021-01-19 19:31:34 -08:00