-
I divided the detection models(efficientdet, ssd_mobilenet, ...) into 4 segments with edgetpu_compiler v16 and pop in the pipeline.
However, the following error occurred:
```python
--------------…
-
### Description
Hello all, I am using USB Coral TPU. I want to update my code from libedgetpu to Pycoral. I am using tensorflow 2.6, pycoral version: 2.0 and tflite_runtime : 2.5.0.post. I have suc…
-
For a software project, I want to do object detection with many individual images over some time (hours/days).
When using the Coral Edge TPU Accelerator (USB) on a RasPi 4 (4 GB) with the Raspberry…
-
compile for edge TPU: https://coral.ai/docs/edgetpu/compiler/
And see how much faster the model is compared to the fp16 model (4s per inference)
-
### Description
Hi, I'm a new user of coral devboard mini.
I'm trying to fix the Smart Bird Feeder project to the pycoral API and run it.
In particular, I've edited ”bird_classify.py” to …
-
### Description
### What i am trying to do and why
I am currently trying to integrate a dual edge tpu into our system.
The problem i face is that due to other packages we are using i am bound to s…
-
As mentioned, looking forward to Semantic Segmentation using TFLite API
-
# Error
```bash
python3 examples/classify_image.py --model test_data/mobilenet_v2_1.0_224_inat_bird_quant_edgetpu.tflite --labels test_data/inat_bird_labels.txt --input test_data/parrot.jpg
Traceba…
-
Hi,
I needed some help in understanding how user_callback function.
In classify.py, the function user_callback takes in "input_tensor, src_size, inference_box" arguments. If i replace "run_interp…
-
Hardware : Google Coral Board Mini
Host Computer : RPI 4
I'm just testing the Coral board.
An error occurred at the beginning part as shown in the picture below.
![image](https://user-images.gi…