| Add | |
| AveragePool2d | No fused activation function. |
| Concatenation | No fused activation function. If any input is a compile-time constant tensor, there must be only 2 inputs, and this constant tensor must be all zeros (effectively, a zero-padding op). |
| Conv2d | Must use the same dilation in x and y dimensions. |
| DepthwiseConv2d | Must use the same dilation in x and y dimensions. |
| ExpandDims | |
| FullyConnected | Only the default format is supported for fully-connected weights. Output tensor is one-dimensional. |
| L2Normalization | |
| Logistic | |
| LSTM | Unidirectional LSTM only. |
| Maximum | |
| MaxPool2d | No fused activation function. |
| Mean | No reduction in batch dimension. If a z-reduction, the z-dimension must be multiple of 4. |
| Minimum | |
| Mul | |
| Pack | No packing in batch dimension. |
| Pad | No padding in batch dimension. |
| PReLU | Alpha must be 1-dimensional (only the innermost dimension can be >1 size). If using Keras PReLU with 4D input (batch, height, width, channels), then shared_axes must be [1,2] so each filter has only one set of parameters. |
| Quantize | |
| ReduceMax | Cannot operate on the batch dimension. |
| ReduceMin | Cannot operate on the batch dimension. |
| ReLU | |
| ReLU6 | |
| ReLUN1To1 | |
| Reshape | Certain reshapes might not be mapped for large tensor sizes. |
| ResizeBilinear | Input/output is a 3-dimensional tensor. Depending on input/output size, this operation might not be mapped to the Edge TPU to avoid loss in precision. |
| ResizeNearestNeighbor | Input/output is a 3-dimensional tensor. Depending on input/output size, this operation might not be mapped to the Edge TPU to avoid loss in precision. |
| Rsqrt | |
| Slice | |
| Softmax | Supports only 1-D input tensor with a max of 16,000 elements. |
| SpaceToDepth | |
| Split | No splitting in batch dimension. |
| Squeeze | |
| StridedSlice | Supported only when all strides are equal to 1 (that is, effectively a Stride op), and with ellipsis-axis-mask == 0, and new-axis-max == 0. |
| Sub | |
| Sum | Cannot operate on the batch dimension. |
| Squared-difference | |
| Tanh | |
| Transpose | |
| TransposeConv | |