search

Kladdy / neutrino-dnn

Deep-learning applied to neutrino property reconstruction
0 stars 0 forks source link

Coral AI dev board inference tests #39

Closed Kladdy closed 3 years ago

Kladdy commented 3 years ago

Edge TPU Compiler version 15.0.340273435

Model compiled successfully in 697 ms.

Input model: model.runF1.1_quantized.tflite Input size: 5.27MiB Output model: model.runF1.1_quantized_edgetpu.tflite Output size: 5.33MiB On-chip memory used for caching model parameters: 5.24MiB On-chip memory remaining for caching model parameters: 2.30MiB Off-chip memory used for streaming uncached model parameters: 8.00KiB Number of Edge TPU subgraphs: 1 Total number of operations: 28 Operation log: model.runF1.1_quantized_edgetpu.log

Model successfully compiled but not all operations are supported by the Edge TPU. A percentage of the model will instead run on the CPU, which is slower. If possible, consider updating your model to use only operations supported by the Edge TPU. For details, visit g.co/coral/model-reqs. Number of operations that will run on Edge TPU: 26 Number of operations that will run on CPU: 2 See the operation log file for individual operation details.

Kladdy commented 3 years ago

Edge TPU Compiler version 15.0.340273435 Input: model.runF1.1_quantized.tflite Output: model.runF1.1_quantized_edgetpu.tflite

Operator Count Status

RESHAPE 1 Mapped to Edge TPU ADD 1 Mapped to Edge TPU CONV_2D 12 Mapped to Edge TPU MUL 1 Mapped to Edge TPU QUANTIZE 1 Operation is otherwise supported, but not mapped due to some unspecified limitation AVERAGE_POOL_2D 4 Mapped to Edge TPU DEQUANTIZE 1 Operation is working on an unsupported data type L2_NORMALIZATION 1 Mapped to Edge TPU FULLY_CONNECTED 6 Mapped to Edge TPU