Category "tensorflow"

Select a column without "losing" a dimension

Suppose I execute the following code W = tf.random.uniform(shape = (100,1), minval = 0, maxval = 1) Z = tf.random.uniform(shape = (100,1), minval = 0, maxval =

TensorFlow: TypeError when itterating through model architectures

I have a script which goes through a simple 2d CNN and I'm trying to run through a range of different values for the number of layers and neurons per layer in m

Weighted categorical cross entropy

please I'm trying to build an NLP classifier on top of BERT but I'm struggling with data imbalance. I'm looking for an implementation of weighted CategoricalCro

About 2D convolutions and how they produce a 1 channel image

Trying to understand 2D convolutions, I ran into the following image, which has me confused: If I understood correctly: the blue shape is the input the orange

How can I use tensorflow-privacy in SeqGAN in a right way?

i'm trying to use DPAdamGaussianOptimizer from tensorflow privacy to switch my original optimizer so i could protect privacy during the training. but when i cre

`generator` yielded an element of shape (8, 0) where an element of shape (None,) was expected. Traceback (most recent call last):

I was training a network and I decided to add more data for training. my data set is selected from another data but both have (460,620,3) and Uint8 type. but wh

Why is my Pytorch code significantly slower than Tensorflow?

I am trying to move my code from Tensorflow to Pytorch. Before doing this, I just simply test myself two frameworks. I expected two frameworks should show simil

'NoneType' object has no attribute '_inbound_nodes'

I have a code to forecast a time series using an attention mechanism. Here's what I've got so far, but I'm getting an error. def dot_product(x, kernel): if

Is there a way to change GPU / CPU on tensorflow during code execution?

I have 2 tensorflow (1.15.4) models running sequentially. The output from the first model will be fed into the second model. Is there a way to run the first mod

Lookup table in TensorFlow with key is string and value is list of strings

I would like to generate a Lookup table in TensorFlow with key is string and value is list of strings. But it seems currently no classes in tf.lookup support th

Matterport's mask rcnn doesn't train after setting up parameters

Task: Mask RCNN train_shapes.ipynb tutorial. Training to segment different shapes in the artificially generated shapes dataset. Problem: Matterport's Mask RCNN

Generic requirements.txt for TensorFlow on both Apple M1 and other devices

I have a new MacBook with the Apple M1 chipset. To install tensorflow, I follow the instructions here, i.e., installing tensorflow-metal and tensorflow-macos in

Upgrade CUDNN to 8.2 in google colab

I wan to use upgrade the CUDNN version from 8.0 to 8.1 and CUDA version to 11.2, but I am not sure how we can do this on colab. Below is the script I wrote to r

Image segementation dataset format

I'm following this tutorial: Tensorflow Image Segmentation I want to make my own dataset. Ideally, following the same format as the Oxford pet dataset used in

Tensorflow doesn't work with gpu - too much memory is used. How to solve it?

I use tensorflow for image classification (20 classes) with convolutions. My dataset contains about 20000 train images and 5000 test images. Images (RGB) have 2

No such file or directory when using DataLoader.from_pascal_voc

I'm having trouble using DataLoader.from_pascal_voc from TFLite Model Maker. I've successfully mounted Google Drive into Google Colab and when I printed the len

Bert Model Compile Error - TypeError: Invalid keyword argument(s) in `compile`: {'steps_per_execution'}

I have been using bert and trying to compile the model using the below line of code. model = TFBertForSequenceClassification.from_pretrained('bert-base-uncased'

GlobalAveragePooling1D equivalence with Lambda Layer

Is the GlobalAveragePooling1D Layer the same like calculating the mean with a custom Lambda Layer? The data is temporal, so x has shape (batch, time, features)

Create a Tensorflow Dataset from a Pandas data frame with numerous labels?

I am trying to load a pandas dataframe into a tensor Dataset. The columns are text[string] and labels[a list in string format] A row would look something like:

Keras/Tensorflow network inference performance

I am using a Keras network which I am calling predict() many times on a single input. A rough calculation based on the layers gives ~3Mops. Running on my CPU sh