Questions tagged [convolutional-neural-network]
257 questions
-1
votes
1 answer
Im not getting correct accuracy for convolutional neural network
I'm not getting output on dog vs. cat classification problem. I have used dataset from kaggle to classifiy dog and cat, I have used Adam optimizer with learning rate of 1e-3, It is not giving the desired accuracy.the model is based on convolutional…
![](../../users/profiles/7481779.webp)
Chitrarth Patel
- 43
- 3
-1
votes
1 answer
Is it advisable to use three separate channel in a RGB image to extract feature with CNN?
I am trying to extract features from CIFAR10 dataset using autoencoder. But it's not giving good accuracy when I use those features. Should I try to use grayscale images or Continue with RGB images?
![](../../users/profiles/7730672.webp)
Nitin Mukesh
- 1
- 3
-1
votes
2 answers
Why YoloV3 has very poor detection rate in testing?
I trained YoloV3 for object detection.
I trained to reach Avg Recall: almost 1.0 for all images in the batch and Avg IOU is above 0.9.
But when I go for testing with images (but they are very similar to those trained images) not included in…
![](../../users/profiles/2467772.webp)
batuman
- 6,072
- 17
- 79
- 178
-1
votes
1 answer
Result of a prediction in CNN
I am working on the following link
https://becominghuman.ai/building-an-image-classifier-using-deep-learning-in-python-totally-from-a-beginners-perspective-be8dbaf22dd8
How do I know that “one” in “result[0][0]” is the prediction of a “dog” and…
![](../../users/profiles/9763803.webp)
charbel el hachem
- 11
- 6
-1
votes
1 answer
Image pre-processing for convolutional neural network
I want to make mushroom classifier with tensorflow using CNN.
But, I wonder about image data pre-processing.
Should I remove background of picture as black color or just use raw picture?
Also, if any pre-processing step before cnn what I do, please…
![](../../users/profiles/8975304.webp)
R.HEE
- 5
- 2
-1
votes
1 answer
"The name 'y_pred:0' refers to a Tensor which does not exist. The operation, 'y_pred', does not exist in the graph."
I've defined y_pred, still, it's giving this error. Any kind of help will be good.
with graph.as_default():
# Input data
tf_train_dataset = tf.placeholder(
tf.float32, shape=(batch_size, image_size, image_size, num_channels),name
=…
-1
votes
1 answer
What exactly is a Softmax output layer?
I'm trying to make a simple conv net in c#, and I want to make a Softmax outputlayer, but I don't really now what it is. Is it a fully connected layer with Softmax activation or just a layer which outputs the softmax of the data?
![](../../users/profiles/6788664.webp)
h0r1z0n
- 31
- 7
-1
votes
1 answer
Keras convolutional net classification adding 1D extra feature possible?
I have built a successful convolutional net using Keras classifying certain brain activity from the EEG. I would however like to improve it by adding an extra feature of which we know it is predictive of this brain activity; age, which is of course…
![](../../users/profiles/8178528.webp)
Hannekevd
- 31
- 3
-1
votes
2 answers
python keeps crashing whenever CNN model is being trained
I am really looking for your help.
I have GTX-1070 which is 8vram.
I downloaded tensorflow-gpu, cuda 9.0, cudnn 7.0 for cuda 9.0.
and everything works fine with DNN. GPU is also working fine.
but whenever I try to train any model that has to do with…
![](../../users/profiles/9640920.webp)
NewbieOfNewbiesYW
- 13
- 3
-2
votes
1 answer
How to extract activation from CNN layers using tensorflow?
I want to extract the neural activation from the Fully connected layers. In Caffe i was doing like this net.blobs[layer_name].data
How can i do the same in tensorflow?
![](../../users/profiles/7462399.webp)
Surajit Saikia
- 31
- 1
- 3
-2
votes
1 answer
How to reject false alarm in object detection using SSD?
I used SSD for my object detection. But there are some false detection from some other objects in the image.
That is happening consistently from same objects. So is there a way to reject those components in training?
![](../../users/profiles/2467772.webp)
batuman
- 6,072
- 17
- 79
- 178
-2
votes
1 answer
Normalization method for Convolutional Neural Network
There have three common image data normalization methods, which are
1. X = (X - X.mean) / X.std
2. X /= 255. # (based on formula: (X - min) / (max - min) which can converge data into [0, 1].)
3. X = 2 * (X - min) / (max - min) - 1 # converge into…
![](../../users/profiles/6699243.webp)
Molly Huang
- 79
- 1
- 6
-2
votes
1 answer
Prediction using Keras
I learned to implement an image classifier from a code which i got from a post and it was very helpful,but i don't know how to predict on an image.I tried but its giving a Value Error.I am still a beginner
Keras Code:-
from __future__ import…
-3
votes
1 answer
Open source tools for implementing machine learning algorithm on FPGA
Is there any open source tools/programs available for implementing machine learning algorithms like CNN on FPGA fabric?
![](../../users/profiles/5131901.webp)
GSAT
- 87
- 4
-3
votes
1 answer
Setting train array dimensions for face recognition for python
I'm trying to find an equivalent code for python to set the following dimensions that I set in R:
dim(train_array) = c(28, 28, 1, ncol(train_x))
train_x is a matrix of 28 by 28 resized (grey scale) olivetti face images digitized into 784 (28 * 28)…
![](../../users/profiles/8197225.webp)
Phillip1982
- 149
- 1
- 1
- 9