ADD float models

[kyakuno]

Add float models for debug

[kyakuno]

https://storage.googleapis.com/ailia-models-tflite/blazeface/face_detection_front.tflite https://storage.googleapis.com/ailia-models-tflite/blazehand/hand_landmark_new_256x256_float32.tflite https://storage.googleapis.com/ailia-models-tflite/blazepalm/palm_detection_builtin.tflite https://storage.googleapis.com/ailia-models-tflite/deeplabv3plus/deeplab_v3_plus_mnv2_decoder_256.tflite https://storage.googleapis.com/ailia-models-tflite/facemesh/face_landmark.tflite https://storage.googleapis.com/ailia-models-tflite/mobilenetv1/mobilenetv1_float.tflite

[kyakuno]

TBD : yolov3-tiny, yolox-tiny

[kyakuno]

yolov3-tiny Repo : https://github.com/hunglc007/tensorflow-yolov4-tflite Weiht : https://pjreddie.com/darknet/yolo/ Command :

python save_model.py --weights yolov3-tiny.weights --output ./checkpoints/yolov3-tiny-416 --input_size 416 --model yolov3 --tiny --framework tflite
python convert_tflite.py --weights ./checkpoints/yolov3-tiny-416 --output ./checkpoints/yolov3-tiny-416.tflite

[kyakuno]

tfliteへの変換で batch_normalization/moving_mean"): error: is not immutable, try removing mutable variables in your model since mutable variables are currently not supported through this converter のエラーが出るため、tensorflow==2.3が必要 https://github.com/tensorflow/tensorflow/issues/44790