Recent content by richlaji

Hi, when will the mobile ai 2022 be held? Thank you~

Hi, Can you provide a python code for inference with the model_none.tflite? I want to know whether the converted model is right. #read model interpreter = tf.lite.Interpreter(model_path=model_path) #read image & raw_img is int8 np array raw_img = np.array(Image.open(imgName).convert('RGB'))...

ok~I understand what you mean for inference part, but I am confused about that both zero point & scale are generated after tf model to quantization tflite (is it right?) and how to add these op to tflite Thank you~

Thank you for your reply~ Can the quantization part be integrated into int8 model? The type of scale & zero point is float and is produced after converting tf model to tflite model.

Hi, the email said I inference my int8 tflite model with the following code #load int8 model and get int quantization info(zero point & scale for input and output) interpreter = tf.lite.Interpreter(model_path) input_details = interpreter.get_input_details() output_details =...

Hi, I want to know (1) whether the model submitted this week will be tested for running time and show in here. https://docs.google.com/spreadsheets/d/e/2PACX-1vSrVUUgwcjGzEzDr5p7It7DRpCP45f2jY9nUiOB78uQzziq8Ejy6w2_7qhP7Fmy5K5X4jfa9iZC5xpb/pubhtml (2) when will the test set be available for...

Hi, thank you for your advise and I can use quantization-aware training now~ I trained a small model with quantization-aware training now. (1) inference with tf model, the psnr is 29.33892 (2) inference with tflite int8, the psnr is 29.24394 I want to know is it reasonable. Thank you again~

Thank you very much!!!

Hi, you can refer to it here https://github.com/aiff22/MAI-2021-Workshop/blob/main/fsrcnn_quantization/fsrcnn.py and uncomment line 64-65

Thank you for your sharing~ I try to use Lambda layer and get another error.(same to tf.concat). Do you train successfully by passing a `tfmot.quantization.keras.QuantizeConfig` instance to the `quantize_annotate_layer`?

Hi, I try to use quantization-aware training and failed. The error is "TypeError: tf__call() got an unexpected keyword argument 'block_size'". I print the layer of my model and find that the depth_to_space layer has a parameter 'block_size' It seems that "tf.nn.depth_to_space" layer cannot be...

Hello I got "Inference fails" in https://docs.google.com/spreadsheets/d/e/2PACX-1vSrVUUgwcjGzEzDr5p7It7DRpCP45f2jY9nUiOB78uQzziq8Ejy6w2_7qhP7Fmy5K5X4jfa9iZC5xpb/pubhtml. But it run sucessfully in AI Benchmark with Int8 and CPU option. And shape of input tensor is [1,360,640,3], shape of output...

Hello, I am confused the dimension of AI Benchmark input since the input shape is dynamic. I successfully used tflite with model.resize_tensor_input on the linux platform but crashed on AI Benchmark.