All Questions
7 questions
1
vote
0
answers
30
views
How do i resolve error with model.fit output [duplicate]
import tensorflow as tf
import random
import cv2, os
import numpy as np
import matplotlib.pyplot as plt
data = "/content/drive/MyDrive/data_sample"
Classes = ["facemask", &...
- 25
0
votes
1
answer
2k
views
Keras custom layer with custom function
I want to create custom layer with built in an image processing function, for example mask, or some kind of blur/noise/color changing etc.
I wrote this code, but I don't know what should I do with
...
user14711430
0
votes
1
answer
459
views
Training model for image classifier on RockPaperScissors.zip file using Tensorflow and Keras
I tried to make an image classifier for RockPaperScissors.zip file and i had trouble in training the model. Here's my code:
import tensorflow as tf
from tensorflow import keras
from keras import ...
- 21
1
vote
1
answer
4k
views
Val_loss is very high (over 100)
I'm trying to create a neural network for image classification. This is my Model summary. I have done normalization to my dataset and shuffling to my data.
. When I run model.fit the val_loss is very ...
1
vote
1
answer
2k
views
ValueError: strides should be of length 1, 1 or 3 but was 2
train input shape : (13974, 100, 6, 5)
train output shape : (13974, 1,1)
test input shape : (3494, 100, 6, 5)
test output shape : (3494, 1, 1)
I am developing the following model. of 2D ...
- 115
0
votes
0
answers
151
views
2D Local Maximum Search and Summation Layer in Keras
I need a (non-trainable) layer in Keras which does a local maximum search for a 2-dim input and sums up all entries in a certain environment around that maximum. The input shape to the layer is ...
- 29
3
votes
0
answers
621
views
Error when using TimeDistributed layer with keras
I want to build a deep learning network with keras(version 2.1.3) to analyse video stream frame by frame. I tried to use TimeDistributed layer and got my network like this:
video = keras.Input(shape=(...
- 31