Category "tensorflow"

How the TensorFlow Output Dense layers nodes mapping to labels?

I'm starting to study the tensorflow with the image classification sample which is the first sample on the tensorflow official document. It creates the Keras Se

Load numpy array in google-cloud-ml job

In the model I want to launch, I have some variables which have to be initialized with specific values. I currently store these variables into numpy arrays but

How to see metrics of a loaded keras model?

I have trained a model with keras and saved it, can I see what the computed metrics during training were, after I load back the mode with keras.models import lo

Tensorflow doesn't seem to see my gpu

I've tried tensorflow on both cuda 7.5 and 8.0, w/o cudnn (my GPU is old, cudnn doesn't support it). When I execute device_lib.list_local_devices(), there is

How to avoid augmenting data in validation split of Keras ImageDataGenerator?

I'm using the following generator: datagen = ImageDataGenerator( fill_mode='nearest', cval=0, rescale=1. / 255, rotation_range=90, width_sh

Integrating a 2D Medical Imaging X-Ray classifier which was trained on jpegs with a script which receives DCM files to be able to diagnose dicom files

Below is the order of how I am going to present my problem: First I will show you the script .py that I am using to run the web app in a local host(flask app).

UnimplementedError: Fused conv implementation does not support grouped convolutions for now

I am trying to build a CNN model to recognise human sketch using the TU-Berlin dataset. I downloaded the png zip file, imported the data to Google Colab and the

How do you read Tensorboard files programmatically?

How can you write a python script to read Tensorboard log files, extracting the loss and accuracy and other numerical data, without launching the GUI tensorboar

failed to install tensorflow on a EC2 instance Ubuntu 20.04

I have a flask application that I would like to run it on an EC2 instance and TensorFlow is needed cause it is image classification. However, after the necessar

How to shape the labels to match the output layer for classification(ANN)?

I am trying to learn and understand how to implement multiclass classification using ANN. In my case, I have 16 classes(0-15), and my label dataset contains one

Error using MultiWorkerMirroredStrategy to train object detection research model ssd_mobilenet_v1_fpn_640x640_coco17_tpu-8

I'm trying to train research model ssd_mobilenet_v1_fpn_640x640_coco17_tpu-8 using the MultiWorkerMirroredStrategy (by setting --num_workers=2 in the invocation

ModuleNotFoundError: No module named 'tensorflow.python.keras.applications'

I am trying to import import tensorflow.python.keras.applications but it gives the bellow error: ModuleNotFoundError: No module named 'tensorflow.python.keras.

conda install matplotlib results in huge list on incompatibilities

I have a conda env that I build from a requirements.yml file that I obtained from a classmate so we could work on a project together. I tried installing matplot

Derivates from a class instance in TF1

I am using the Physics Informed Neural Networks (PINNs) methodology to solve non-linear PDEs in high dimension. Specifically, I am using this class https://git

How is the smooth dice loss differentiable?

I am training a U-Net in keras by minimizing the dice_loss function that is popularly used for this problem: adapted from here and here def dsc(y_true, y_pred)

logits and labels must be broadcastable error in Tensorflow RNN

I am new to Tensorflow and deep leaning. I am trying to see how the loss decreases over 10 epochs in my RNN model that I created to read a dataset from kaggle w

Find Unique values in a 2D Tensor using Tensorflow

tf.unique currently only works on 1D tensors. How can I find unique values in a 2D tensor. ip=tf.constant([[1,2,1],[3,4,1],[5,6,1],[1,2,1]]) #op should be = [

Find Unique values in a 2D Tensor using Tensorflow

tf.unique currently only works on 1D tensors. How can I find unique values in a 2D tensor. ip=tf.constant([[1,2,1],[3,4,1],[5,6,1],[1,2,1]]) #op should be = [

TensorFlow convert from .pb to .tflite failes due to ops error

Hey everyone this is my first question post. If I do something wrong or u need more information please just tell me I will try to give my best. I tried to creat

How to run tensorflow inference for multiple models on GPU in parallel?

Do you know any elegant way to do inference on 2 python processes with 1 GPU tensorflow? Suppose I have 2 processes, first one is classifying cats/dogs, 2nd on