Recent Releases of thermal-face
thermal-face - v1.0
Model files
Model metadata
json
{
"inferenceType": "QUANTIZED_UINT8",
"inputShape": [
1,
192,
192,
3
],
"inputTensor": "normalized_input_image_tensor",
"maxDetections": 500,
"outputTensorRepresentation": [
"bounding_boxes",
"class_labels",
"class_confidences",
"num_of_boxes"
],
"outputTensors": [
"TFLite_Detection_PostProcess",
"TFLite_Detection_PostProcess:1",
"TFLite_Detection_PostProcess:2",
"TFLite_Detection_PostProcess:3"
]
}
Edge TPU compiler log
``` Edge TPU Compiler version 14.1.317412892 Input: thermalfaceautomledgefast.tflite Output: /out/thermalfaceautomledgefast_edgetpu.tflite
Operator Count Status
RESHAPE 12 Tensor has unsupported rank (up to 3 innermost dimensions mapped) RESHAPE 32 More than one subgraph is not supported ADD 19 More than one subgraph is not supported ADD 12 Mapped to Edge TPU MAXPOOL2D 9 More than one subgraph is not supported MAXPOOL2D 6 Mapped to Edge TPU MEAN 8 Mapped to Edge TPU DEPTHWISECONV2D 19 Mapped to Edge TPU DEPTHWISECONV2D 23 More than one subgraph is not supported CONV2D 23 More than one subgraph is not supported CONV2D 63 Mapped to Edge TPU LOGISTIC 6 More than one subgraph is not supported LOGISTIC 11 Mapped to Edge TPU CONCATENATION 2 More than one subgraph is not supported PACK 24 Tensor has unsupported rank (up to 3 innermost dimensions mapped) CUSTOM 1 Operation is working on an unsupported data type REDUCEMAX 3 Mapped to Edge TPU REDUCEMAX 5 More than one subgraph is not supported MUL 10 Mapped to Edge TPU MUL 6 More than one subgraph is not supported ```
- Shell
Published by maxbbraun almost 6 years ago
