Category "tensorflow"

A simple case of Graph visualization in TensorFlow 2.0

I would like to simply define a model and visualize its graph in TensorBoard for initial architectural examination. Thus, I would not like to compute anything f

Use different metrics in tf.keras.metrics for mutli-classification model

I am using the TensorFlow federated framework for a multiclassification problem. I am following the tutorials and most of them use the metric (tf.keras.metrics.

ImportError: cannot import name 'keras' from 'tensorflow'

I'm try learning TensorFlow but i have a problem. I'm importing TensorFlow like in official website but i take a error. import pandas as pd import numpy as np i

Reload Keras-Tuner Trials from the directory

I'm trying to reload or access the Keras-Tuner Trials after the Tuner's search has completed for inspecting the results. I'm not able to find any documentation

Tensorflow: Getting scalar tensor value as int for pass to set_shape()

I'm attempting to load 3D images and their labels from a numpy array to TensorFlow records, then read them from a queue while training my network. The code for

Issues running a Keras model with custom layers

I am currently working on my bachelor's thesis at FIIT STU, the primary goal of which is to attempt to replicate and verify the results of the following study.

Why does BERT Model fail to find an option that matches my input positional arguments?

While attempting an NLP exercise, I tried to make use of BERT architecture to get a good training model. So I defined a function that builds and compiles the mo

Tensorflow Equivalent of skimage.transform.warp or scipy.ndimage.interpolation.map_coordinates

Does Tensorflow have an equivalent of skimage.transform.warp or scipy.ndimage.interpolation.map_coordinates? I am looking for some way to "warp an image accordi

How to decode raw_outputs/box_encodings from Tensorflow Object detection ssd-mobilenet without nms

In order to deploy my own ssd-mobile model on android and use NNAPI acceleration , I retrained the model without NMS post processing according to the tensorflo

TensorFlow, Keras download issue on Raspberry Pi 3B+

I need help installing TensorFlow/Keras on raspberry pi 3B+ Python version 3.9.2 Keras version 2.8.0 TensorFlow version 1.8.0 I downloaded them via pip3 on pro

"Could not load dynamic library 'libcudnn.so.8'" when running tensorflow on ubuntu 20.04

Note: there are many similar questions but for different versions of ubuntu and somewhat different specific libraries. I have not been able to figure out what

Using String parameter for nvidia triton

I'm trying to deploy a simple model on the Triton Inference Server. It is loaded well but I'm having trouble formatting the input to do a proper inference reque

Tensorflow serving error: "Data loss: Can't parse saved_model.pb as binary proto"

I used google collaboratory to train a simple mnist example model to get myself familiar with tensorflow serving but my tensorflow model server is not able to r

Tensorflow1 tf.Session Ignore GPU certification

When I limit GPU by os.environ["CUDA_VISIBLE_DEVICES"]="1" and load trained model like below, tacotron1.15.5[horovod] load model to all GPUs(8) with same proces

ran into TensorFlow ValueError during my TensorFlow Course with Udemy

I have being trying to fit the error during my Tensorflow course (Section 3: Neural network Regression with Tensorflow) with Udemy. import tensorflow as tf impo

Keras history callback loss does not match with console output of loss

I am Training a cnn in Keras at the moment. Now I want to log the history of the training process for later visualizations, which I do with: history_callback =

Jupyter Kernel Dies Importing Keras

I am running an Apple Macbook with 16 GB of RAM and the M1 chip. I am trying to import Keras through the command: from tensorflow.keras.models import Sequential

tflite: get_tensor on non-output tensors gives random values

I'm trying to debug my tflite model, that uses custom ops. I've found the correspondence between op names (in *.pb) and op ids (in *.tflite), and I'm doing a la

ValueError: cannot reshape array of size 921600 into shape (224,224,3)

I trained a model using Transfer Learning(InceptionV3) and when I tried to predict the results it shows: ValueError: cannot reshape array of size 921600 into sh

ValueError: Input 0 of layer is incompatible with the layer: expected shape=(None, 224, 224, 3), found shape=(224, 224, 3)

"after converting the dataset to the tfrecord file format, I tried to train the model I created with it, but I couldn't convert it to the input format suitable