ambr89
ambr89
Hi! Yes, my train in 2-3 hours converge! BUT, if I insert perspective transform my train does not exceed than 0.7. Any idea? Can I improve this?
Hello, can you share with me the code to detect image?
Hi @jonghoon-park with DW2TF you can obtain yolov3-tiny.pb yolov3-tiny.ckpt.meta yolov3-tiny.ckpt.meta yolov3-tiny.ckpt.data-00000-of-00001 How you can test this new weight?
Hi @willbattel , did you be able to obtain INT8 weight? Anyone can do this?
Hi! **Yes**, I've obtain a Quantized .tflite ```bash $ bazel run tensorflow/lite/toco:toco -- \ --input_file=mymodel.pb \ --output_file=output.tflite \ --input_shapes=1,416,416,3 \ --input_arrays='input_1' \ --output_format=TFLITE \ --output_arrays='output_0','output_1' \ --inference_type=QUANTIZED_UINT8 \ --std_dev_values=128 --mean_values=128...
Hi @dexception ! Did you have solved this problem? Thanks in advance!
Hi @shubham305337 ! Have you found a good solution?
Does anyone found the solution? I've Android device and I receive the push message only if ap is in the background but not killed. Android 8.0.0
I've downgraded tensorflow to 1.3 and I resolve this problem