Modify several 1.2 nn operation specs.
- Add TENSOR_QUANT8_ASYMM to RESIZE_BILINEAR
- Change the spec of batch_split in
* GENERATE_PROPOSALS
* ROI_ALIGN
* ROI_POOLING
* AXIS_ALIGNED_BBOX_TRANSFORM
* BOX_WITH_NMS_LIMIT
- Add new op RESIZE_NEAREST_NEIGHBOR
- Fix minor specification error in
* AXIS_ALIGNED_BBOX_TRANSFORM
* GENERATE_PROPOSALS
Bug: 124060811
Bug: 124061329
Bug: 124061327
Test: 1.2 VTS tests with sample driver
Change-Id: If8b8cabd249f17247d8a5278b8360685c97c68e6
Merged-In: If8b8cabd249f17247d8a5278b8360685c97c68e6
(cherry picked from commit b9319bd3bf64e4a643045ad0493bedce60786474)
diff --git a/current.txt b/current.txt
index 60241f9..8f93d8e 100644
--- a/current.txt
+++ b/current.txt
@@ -420,7 +420,7 @@
92714960d1a53fc2ec557302b41c7cc93d2636d8364a44bd0f85be0c92927ff8 android.hardware.neuralnetworks@1.2::IExecutionCallback
83885d366f22ada42c00d8854f0b7e7ba4cf73ddf80bb0d8e168ce132cec57ea android.hardware.neuralnetworks@1.2::IPreparedModel
e1c734d1545e1a4ae749ff1dd9704a8e594c59aea7c8363159dc258e93e0df3b android.hardware.neuralnetworks@1.2::IPreparedModelCallback
-a42fb6a33e242e0035de32cdcd4b743d46ae93d65a1e316f3bffe7218ade82cb android.hardware.neuralnetworks@1.2::types
+313b341f1f6196a48cf304eaf067f67510c1ebc04df8c7cd536db5611df5c5c2 android.hardware.neuralnetworks@1.2::types
cf7a4ba516a638f9b82a249c91fb603042c2d9ca43fd5aad9cf6c0401ed2a5d7 android.hardware.nfc@1.2::INfc
abf98c2ae08bf765db54edc8068e36d52eb558cff6706b6fd7c18c65a1f3fc18 android.hardware.nfc@1.2::types
4cb252dc6372a874aef666b92a6e9529915aa187521a700f0789065c3c702ead android.hardware.power.stats@1.0::IPowerStats
diff --git a/neuralnetworks/1.2/types.hal b/neuralnetworks/1.2/types.hal
index 3bddbe8..06bdc6a 100644
--- a/neuralnetworks/1.2/types.hal
+++ b/neuralnetworks/1.2/types.hal
@@ -1528,6 +1528,7 @@
* Supported tensor {@link OperandType}:
* * {@link OperandType::TENSOR_FLOAT16} (since API level 29)
* * {@link OperandType::TENSOR_FLOAT32}
+ * * {@link OperandType::TENSOR_QUANT8_ASYMM} (since API level 29)
*
* Supported tensor rank: 4, with "NHWC" or "NCHW" data layout.
* With the default data layout NHWC, the data is stored in the order of:
@@ -2212,6 +2213,7 @@
* Supported tensor {@link OperandType}:
* * {@link OperandType::TENSOR_FLOAT16}
* * {@link OperandType::TENSOR_FLOAT32}
+ * * {@link OperandType::TENSOR_QUANT16_ASYMM}
*
* Inputs:
* * 0: A 2-D Tensor of shape [num_rois, 4], specifying the locations of the
@@ -2228,7 +2230,8 @@
* {@link OperandType::TENSOR_QUANT16_ASYMM}, this tensor should be
* of {@link OperandType::TENSOR_QUANT8_ASYMM}.
* * 2: An 1-D {@link OperandType::TENSOR_INT32} tensor, of shape
- * [batches], specifying the number of output boxes for each batch.
+ * [num_rois], specifying the batch index of each box. Boxes with
+ * the same batch index are grouped together.
* * 3: A 2-D Tensor of shape [batches, 2], specifying the information of
* each image in the batch, each line with format
* [image_height, image_width].
@@ -2557,8 +2560,9 @@
* {@link OperandType::TENSOR_QUANT8_ASYMM}, this tensor should be of
* {@link OperandType::TENSOR_QUANT16_ASYMM}, with zeroPoint of 0 and
* scale of 0.125.
- * * 2: A 1-D Tensor of shape [batches], specifying the number of boxes
- * for each image in the batch.
+ * * 2: A 1-D {@link OperandType::TENSOR_INT32} tensor, of shape
+ * [num_rois], specifying the batch index of each box. Boxes with
+ * the same batch index are grouped together.
* * 3: An {@link OperandType::FLOAT32} scalar, score_threshold. Boxes
* with scores lower than the threshold are filtered before sending
* to the NMS algorithm.
@@ -2584,7 +2588,8 @@
* [num_output_rois], specifying the class of each output box. The
* sequential order of the boxes corresponds with output0.
* * 3: A 1-D {@link OperandType::TENSOR_INT32} tensor, of shape
- * [batches], specifying the number of output boxes for each image.
+ * [num_rois], specifying the batch index of each box. Boxes with
+ * the same batch index are grouped together.
*
* Available since API level 29.
*/
@@ -2878,6 +2883,9 @@
* {@link OperandType::TENSOR_QUANT16_SYMM}, with scale of 0.125.
* * 3: A 2-D Tensor of shape [batches, 2], specifying the size of
* each image in the batch, with format [image_height, image_width].
+ * For input0 of type {@link OperandType::TENSOR_QUANT8_ASYMM}, this
+ * tensor should be of {@link OperandType::TENSOR_QUANT16_SYMM}, with
+ * scale of 0.125.
* * 4: An {@link OperandType::FLOAT32} scalar, specifying the ratio
* from the height of original image to the height of feature map.
* * 5: An {@link OperandType::FLOAT32} scalar, specifying the ratio
@@ -2904,14 +2912,15 @@
* each batch is not guaranteed. For type of
* {@link OperandType::TENSOR_QUANT8_ASYMM}, the scale and zero
* point must be the same as input0.
- * * 1: A tensor of the same {@link OperandType} as input1, of shape
+ * * 1: A tensor of the same {@link OperandType} as input3, of shape
* [num_output_rois, 4], specifying the coordinates of each output
* bounding box for each class, with format [x1, y1, x2, y2].
* The sequential order of the boxes corresponds with output0.
* For type of {@link OperandType::TENSOR_QUANT16_ASYMM}, the
* scale must be 0.125 and the zero point must be 0.
* * 2: A 1-D {@link OperandType::TENSOR_INT32} tensor, of shape
- * [batches], specifying the number of output boxes for each image.
+ * [num_rois], specifying the batch index of each box. Boxes with
+ * the same batch index are grouped together.
*
* Available since API level 29.
*/
@@ -3904,7 +3913,8 @@
* this tensor should be of {@link OperandType::TENSOR_QUANT16_ASYMM},
* with zeroPoint of 0 and scale of 0.125.
* * 2: An 1-D {@link OperandType::TENSOR_INT32} tensor, of shape
- * [batches], specifying the number of output boxes for each batch.
+ * [num_rois], specifying the batch index of each box. Boxes with
+ * the same batch index are grouped together.
* * 3: An {@link OperandType::INT32} scalar, specifying the output
* height of the output tensor.
* * 4: An {@link OperandType::INT32} scalar, specifying the output
@@ -3960,7 +3970,8 @@
* this tensor should be of {@link OperandType::TENSOR_QUANT16_ASYMM},
* with zeroPoint of 0 and scale of 0.125.
* * 2: An 1-D {@link OperandType::TENSOR_INT32} tensor, of shape
- * [batches], specifying the number of output boxes for each batch.
+ * [num_rois], specifying the batch index of each box. Boxes with
+ * the same batch index are grouped together.
* * 3: An {@link OperandType::INT32} scalar, specifying the output
* height of the output tensor.
* * 4: An {@link OperandType::INT32} scalar, specifying the output
@@ -4441,6 +4452,42 @@
* Available since API level 29.
*/
UNIDIRECTIONAL_SEQUENCE_RNN = 93,
+
+ /**
+ * Resizes images to given size using the nearest neighbor interpretation.
+ *
+ * Resized images must be distorted if their output aspect ratio is not the
+ * same as input aspect ratio. The corner pixels of output may not be the
+ * same as corner pixels of input.
+ *
+ * Supported tensor {@link OperandType}:
+ * * {@link OperandType::TENSOR_FLOAT16}
+ * * {@link OperandType::TENSOR_FLOAT32}
+ * * {@link OperandType::TENSOR_QUANT8_ASYMM}
+ *
+ * Supported tensor rank: 4, with "NHWC" or "NCHW" data layout.
+ * With the default data layout NHWC, the data is stored in the order of:
+ * [batch, height, width, channels]. Alternatively, the data layout could
+ * be NCHW, the data storage order of: [batch, channels, height, width].
+ *
+ * Inputs:
+ * * 0: A 4-D tensor, of shape [batches, height, width, depth], specifying
+ * the input.
+ * * 1: An {@link OperandType::INT32} scalar, specifying the output
+ * height of the output tensor.
+ * * 2: An {@link OperandType::INT32} scalar, specifying the output
+ * width of the output tensor.
+ * * 3: An {@link OperandType::BOOL} scalar, default to false.
+ * Set to true to specify NCHW data layout for input0 and output0.
+ *
+ * Outputs:
+ * * 0: The output 4-D tensor, of shape
+ * [batches, new_height, new_width, depth].
+ *
+ * Available since API level 29.
+ */
+ RESIZE_NEAREST_NEIGHBOR = 94,
+
/**
* DEPRECATED. Since NNAPI 1.2, extensions are the preferred alternative to
* OEM operation and data types.
@@ -4463,7 +4510,7 @@
enum OperationTypeRange : uint32_t {
BASE_MIN = 0,
FUNDAMENTAL_MIN = 0,
- FUNDAMENTAL_MAX = 93,
+ FUNDAMENTAL_MAX = 94,
OEM_MIN = 10000,
OEM_MAX = 10000,
BASE_MAX = 0xFFFF,