Category "deep-learning"

NaN for Keras Tuner score for RandomSearch

I am trying out Keras (2.8.0) autotuner for a regression problem. Here is my code: import pandas as pd from tensorflow import keras from keras import layers, lo

Tensorflow "decode_png" keeps printing "Cleanup called..."

I'm using tensorflow to open some .png images and every image it opens, an annoying message is printed. def open_img(path): img = tf.io.read_file(path)

ModuleNotFoundError: No module named 'fastai.vision'

I am trying to use ImageDataBunch from fastai, and it worked fine, but recently when I ran my code, it showed this error ModuleNotFoundError: No module named 'f

Error while defining observation space in gym custom environment

I am working on a reinforcement algorithm, I am very new to this and trying to get a hold of things. Player1Env looks upon a 7x6 Connect4 playing grid. I am ini

Keras loss is NaN when training for semantic segmentation

I am using the headsegmentation dataset. A single mask looks like this All mask images are a single channel. This is my code: image_size = 512 batch = 4 labels

OSError while calling Detectron2LayoutModel

After successfully installing Layout Parser in Windows, getting the below OS Error. Code Used: model = lp.Detectron2LayoutModel(config_path="lp://PubLayNet/mask

Input 0 of layer "sequential_3" is incompatible with the layer: expected shape=(None, 256, 256, 3), found shape=(None, 324, 500, 3)

I'm having an issue if anyone can help please comment input_shape=(BATCH_SIZE,256,256,3) model=models.Sequential([ resize_and_rescale, data_aug

Pytorch RuntimeError: element 0 of tensors does not require grad and does not have a grad_fn

This code is built up as follows: My robot takes a picture, some tf computer vision model calculates where in the picture the target object starts. This informa

Tensorflow seq2seq - keep max three checkpoints not working

I am writing a seq2seq and would like to keep only three checkpoints; I thought I was implementing this with: checkpoint_dir = './training_checkpoints' checkpoi

tensorflow:Can save best model only with val_acc available, skipping

I have an issue with tf.callbacks.ModelChekpoint. As you can see in my log file, the warning comes always before the last iteration where the val_acc is calcula

Cannot Train Wav2vec XLSR Model With Common Voice Data

I am trying to train a transformer ASR model with wav2vec XLSR in the danish language, but whenever I try to pull the danish dataset with datasets library it's

LSTM/GRU setting states to random noise instead or resetting to zero

I train the following model based on GRU, note that I am passing the argument stateful=True to the GRU builder. class LearningToSurpriseModel(tf.keras.Model):

making GRU/LSTM states trainable in Tensorflow/Keras and add some random noise

I train the following model based on GRU, note that I am passing the argument stateful=True to the GRU builder. class LearningToSurpriseModel(tf.keras.Model):

How to properly initialize TensorFlow GRU-layer with noisy states?

I wish to experiement with noisy GRU states instead of resetting them to zero for each batch. I try below an implementation. My initial code was resetting initi

Is it possible to automatically infer the class_weight from flow_from_directory in Keras?

I have an imbalanced multi-class dataset and I want to use the class_weight argument from fit_generator to give weights to the classes according to the number o

How to Merge two CNN models?

I have 1D-CNN model and 2D-CNN model and want to merge them as mention in this paper , How can i merge them ? any help will appreciate , Thank you very much!

Keras: network doesn't train with fit_generator()

I'm using Keras on the large dataset (Music autotagging with MagnaTagATune dataset). So I've tried to use fit_generator() fuction with a custom data generator.

numpy random choice in Tensorflow

Is there an equivalent function to numpy random choice in Tensorflow. In numpy we can get an item randomly from the given list with its weights. np.random.c

Are modern CNN (convolutional neural network) as DetectNet rotate invariant?

As known nVidia DetectNet - CNN (convolutional neural network) for object detection is based on approach from Yolo/DenseBox: https://devblogs.nvidia.com/paralle

Whenever i try to print classification report, in accuracy column it prints some other value 0.50 but my accuracy is 0.96

Importing libraries import matplotlib.pyplot as plt import seaborn as sns import keras from keras.layers import * from keras.models import * from sklearn.metric