Alvaro de Castro

I trained 3 models already with this software all the way down to .5 accuracy, and in all cases it detects NOTHING The only time I was able to make...

We are running inference on pb models with these commands on one particular product we trained and it works fine: it detects, shows a green box around it, etc options...

Training stuck at 8%

4

We are training a model with 83 thousand pictures of (2592x1944 ) of 200 different supermarket products in 200 classes. To simplify, we created a single class for all products...

Nothing comes out: just a grey, black, or white screen depending on the weight

19

I understand this software should generate black and white images separating the cells found However, I only get plain black, white, or grey images depending on what value I put...

It is impossible to make this work with the GPU

4

I put os.environ["CUDA_VISIBLE_DEVICES"] = "0" as instructed in the issues and still nothing. It takes forever to train with the CPU

UIKit is not available when building for macOS.

E tensorflow/stream_executor/cuda/cuda_blas.cc:226] failed to create cublas handle: CUBLAS_STATUS_NOT_INITIALIZED

3

Put the following code below import tensorflow as tf at demo.py config = tf.compat.v1.ConfigProto() config.gpu_options.allow_growth = True session = tf.compat.v1.Session(config=config) otherwise you will get E tensorflow/stream_executor/cuda/cuda_blas.cc:226] failed to create cublas...

It does nothing: just keeps showing a moving bar on top. Tried with 2 websites

Connection reset by peer

2

I can't seem to be able to do anything as I keep getting "connection reset by peer" during ssl I checked and the SSL is properly configured in the server

I am using a Raspberry 4 on Ubuntu 22 over a UART connection to a pn532 It is stuck at "starting" as soon as I type import nfc I tried...