tensorflow-example | TensorFlow examples for Valohai platform | Machine Learning library

I have had problems here, here and there installing TensorFlow 2 over the last year or so. So I am trying Miniconda.

I have an AMD Radeon hd 6670 and an AMD Radeon hd 6450.

I just downloaded Miniconda and made an environment and did a pip install --upgrade tensorflow in a Miniconda prompt on Windows 8.1 and got TensorFlow 2.2.

When I try to import tensorflow I get the stack trace below.

I did download Visual Studio to get the latest redistributebles (I think).

seems like this occurs near this line: from tensorflow.python.pywrap_tensorflow_internal import *

Edit 1: I used this yaml file for python 3.6 (the other was 3.7), but it produced the same error.

Edit 2: I upgraded to Conda 4.8.3 and Python 3.7 (in the yaml file) and got the same error. This is the line in pywrap internal that shows the problem:

https://www.tensorflow.org/lite/tutorials/model_maker_image_classification

I am running through the tensorflow lite example and get an import error when trying to import image classifier.

I am trying TF-lite converter with TF1.12. And found that the accuracy of TF-lite is not correct after quantization. Take MNIST for example, if convert to f32 with the following command, it still can tell the correct when run convolution_test_lite.py with conv_net_f32.tflite.

I am in the process of re-writing code that is compatible with TF 2.0. Unfortunately, almost every example provided by the website uses the keras API. I, however, want to write code with raw tensorflow functions.

At some point, the new way of calculating and applying gradients during the training process looks something like this (code stolen from here):

I have data in a tensorflow record file (data.record), and I seem to be able to read that data. I want to do something simple: just display the (png-encoded) image for a given example. But I can't get the image as a numpy array and simply show it. I mean, the data are in there how hard can it be to just pull it out and show it? I imagine I am missing something really obvious.

I'm totally new to TensorFlow and Python, so please excuse me for posting such a basic question, but I'm a bit overwhelmed with learning both things at once. EDIT: I found a solution myself and posted it below, however, more efficient solutions are wellcome

Short version of the question: How can I extract every weight and bias at any point from a neural network using TensorFlow and store it into a Python array with the shape [layers][neurons-previous-layer][neurons-current-layer]. The goal is NOT to store on the hdd but in variables with the same shape and type as the one explained below the last code snipet. I'd also like to know, which is the most efficient way to do so.

The task I want to perform is to create a neural network with pre-trained weights and biases (not obtained from Tensor, but from totally different source), refine the training with Tensor and then return the refined weights to the program.

I've investigated how to create NN's in Tensor Flow as well as made my way through a way to initialize the weights of the network using previously created lists in Python based on some Tensor tutorials and some unrelated questions from StackOverflow.

So, my question is, given a trained network in TensorFlow, how can I extract every weight and bias to variables (my network has around 2,8 million weights and biases) in the fastest possible way? (keep in mind that this operation is going to be repeated over and over)

To clarify the question, here's some code:

First of all, the entire network creation and training process (except the network layout) is based on this post: Autoencoder Example.

The relevant parts of the code for this example are the following (I cut the output part because it is not necessary to explain the way I create the network):

I'm trying to run a simple cnn on cifar10, combining code from 2 examples: https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/6_MultiGPU/multigpu_cnn.py

https://github.com/exelban/tensorflow-cifar-10

I'm getting OOM errors.

I first tried the code with the complete cnn , without multi-gpu support, and it is working ok. Next I used the multi-gpu code, ran ok too. Combining them is not working.

I'm trying to create a model to classify some plants, just so I can learn how to use TensorFlow. The problem is that every good example that I can use as reference is loading a .csv dataset and I want to load a .jpeg dataset (could be .png or .jpg as well).

Those examples even use a built in dataset like:

I've downloaded the newest Nsight Compute profiling tool and I want to use it to benchmark Tensorflow applications. The code I'm using is here. It runs perfectly fine when I execute it and when I benchmark it with nvprof ./mnist.py it had no problem at all. However, when I try to run it with command sudo ./nv-nsight-cu-cli [path to the file] I get the following error:

ImportError: libcublas.so.9.0: cannot open shared object file: No such file or directory

I suspect that nv-nsight-cu-cli somehow didn't recognized the environment variable at all. Is there any fix around?