Questions tagged [training]

The tag has no usage guidance.

Filter by
Sorted by
Tagged with
0
votes
0answers
14 views

Keras: equivalence of `epochs=1000, steps_per_epoch=1` and `epochs=1, steps_per_epoch=1000`

I am training a Keras model on randomly generated data using fit_generator. Except for monitoring purposes, is A: ...
0
votes
1answer
21 views

How to re-train a model from false positives

I'm still a bit new to deep learning. What I'm still struggling, is what is the best practice in re-training a good model over time? I've trained a deep model for my binary classification problem (...
1
vote
1answer
17 views

Finding the appropriate CNN Model Architecture and Parameters

I am currently creating a CNN model that classifies whether the font is Arial, Verdana, ...
0
votes
0answers
17 views

What are the downsides of using TPUs instead of GPUs when performing neural network training or inference?

What are the downsides of using TPUs instead of GPUs when performing neural network training or inference? From what I read on https://www.predictiveanalyticsworld.com/machinelearningtimes/should-you-...
3
votes
2answers
99 views

How to train my model efficiently?

I am new to ML and have been reading online about training bottlenecks when there are frequent updates to data. Let's say I have a built a model based on a dataset of 10M records. Now, in another 2 ...
0
votes
0answers
7 views

Reweighting training data after kernel density estimation?

I have a problem where my training set can have a bit different distribution than my test set, and I'm trying to rectify this by doing a kernel density estimation on my test set, and then applying ...
0
votes
1answer
15 views

is validation and train set should be all different files?

Let say I have train set and validation set if 'A' included in the train set. 'A' should not be include in the validation set? or some is ok?
1
vote
1answer
21 views

Data augmentation in deep training

I'm trying to understand the role of data augmentation and how it can affect the performance/accuracy of a deep model. My target application is a fire classification (fire or not, on video frames), ...
0
votes
0answers
18 views

Local RTX 2080 is 3x faster than V100 on GCP?

I have a gaming rig with an i9 CPU, 32GB RAM and RTX 2080, and I have a GCP VM with 4 vCPU, 52 GB RAM and V100. I try to train the same dataset using the same toolchain on both machines and these are ...
0
votes
2answers
23 views

Auto-Encoder customized layer training

My question is related with model-weights optimization during back propagation. In this image I'm trying to represent an auto-encoder having 7 layers where 4th one is center layer. If my ...
0
votes
0answers
34 views

Train a neural network through comparisons between images using Keras

I have a Dataset composed of 2 arrays of images and an array of desired outputs. Arrays have the same length. I have to train a neural network using keras able to recognize who is younger/older/same ...
0
votes
1answer
27 views

Does keras' model.fit() remember learning rate when called multiple times?

Let's say I'm using the Adam optimizer, and calling fit() on my model multiple times. What parameters does the fit function remember? From what I've observed, the loss function/metrics seem to ...
2
votes
1answer
36 views

A bump in CV score curve! What does it mean?

My learning curve is behaving strangely and I don't know if I'm doing anything wrong or it is because of the dataset nature. I'm using a Neural network with (30,30,15,1) layers and 'ReLU' activation ...
1
vote
1answer
17 views

Is there a link between Training, Test errors based on k fold CV and not doing CV?

I am using Matlab to train a feedforward NN using Cross validation (CV) approach. My understanding of CV approach is the following. (Please correct me where wrong) Let ...
1
vote
0answers
40 views

How to predict using the pickle model?

I am new to data science and trying to learn something. I was able to complete the prediction with 98% accuracy and i saved it as pickle model. Now while trying to predict using this model I am ...
1
vote
0answers
13 views

How many augmentated data points for each training image?

What are some useful rules of thumb for picking the number of augmenters per training image? I realize this is a hyperparameter I can vary and test: I'm just trying to get a sense for reasonable ...
1
vote
2answers
29 views

How many trees does a random forest need?

At first, I did a GridsearchCV and the best parameter is a random forest with just 100 trees. My trainset has 80.000 rows and 669 columns. My test set has 20.000 rows and 669 columns. How is it ...
1
vote
1answer
51 views

How to keep the test data from leaking into the training process of a machine learning algorithm?

I read in many different sources that I need to split my data into a training set and a test set. Then I have to make sure that the algorithm is trained only on the training data, and do my best to ...
0
votes
0answers
12 views

Is it normal that CUDA will sporadically run out of memory?

Sometimes I will train a model successfully, othertimes CUDA will run out of memory in the middle of training with the exact same network, batch size, etc. Similar behaviour like models not loading ...
0
votes
1answer
20 views

What is the main concept of using lexical,linguistic, semantic or syntactic approach in NLP for cyberbullying

I am really in need of some explanation, I am working on an NLP cyber-bullying detection tool which I will deploy to the web using Django framework, however, am stuck on some idea, can someone explain ...
0
votes
2answers
18 views

Present results of the best or the last iteration on dev set?

Which is the correct way - presenting the results of the best or the last iteration on the dev set in a paper? In research papers I usually see only one value, is it the best iteration of all? I'm ...
1
vote
1answer
46 views

Incremental training and Auto Machine Learning for big datasets

I built a NLP sentence classifier, which uses vectors from word embedding as features. Training dataset is big (100k sentences). Every sentence has 930 features. I found the best model using an auto ...
30
votes
8answers
6k views

What would I prefer - an over-fitted model or a less accurate model?

Let's say we have two models trained. And let's say we are looking for good accuracy. The first has an accuracy of 100% on training set and 84% on test set. Clearly over-fitted. The second has an ...
1
vote
0answers
16 views

Vector Autoregression forecasting with large dataset

I am trying to use VAR to forecast electricity price for a whole day and I have a dataset with over 20000 observations (price for every hour) from 2015-2017. My first intuition was to select 19975 ...
0
votes
0answers
25 views

InvalidArgumentError: Incompatible shapes while training

InvalidArgumentError: Incompatible shapes: [15,31744] vs. [15,31680][[{{node loss_4/output_loss/logistic_loss/mul}}]] Has anyone of you ever got this kind of ...
1
vote
1answer
22 views

Including the validation file in the training process after tunning

Should I include the validation file in the training process after finishing the tuning process (e.g. searching for params using the validation file)?
1
vote
2answers
45 views

How to train the machine so that it can give 'out of bound/classes' as an output for neural network

I know I was not able to word the title of the question properly. So I am trying to explain the problem here: Suppose, I built and trained a CNN to identify numbers from 0 to 9. However, when I ...
0
votes
1answer
44 views

splitting into train test by train_test_split of float values?

How to split into train test by train_test_split of float values ? I used LabelEncoder but I have about 300K lines and when I used the cross_val I saw ...
0
votes
0answers
13 views

How to convert non image data to lmdb format for caffe

I have data where the input is of size [1,1,625] ( width and height is 1 and number of channels is 625). The input size cannot be changed since I need to use the weights of a pretrained model which ...
1
vote
1answer
166 views

Is it reasonable that a problem “solved” by a traditional ANN can also be solved by a CNN?

There is a data science numerical problem, which me and my team were able to get an ANN model that predicts down to a 1% MAPE error (with roughly 70000+ trainable parameters). Given the nature of the ...
0
votes
0answers
20 views

Loss is decreasing but the predictions are not getting well

I am trying to implement a Dependency Parsing model using the transformer model in here with a few changes. On the training, my loss has decreasing trend; but the predictions at the end of 20 epochs ...
1
vote
1answer
64 views

What's the best way to train a NER model?

I am trying to do a project using NLP. My goal is to process Cyber Threat Intelligence articles like this to extract information such as actor’s name, malwares and tools used… To do that I want to ...
0
votes
0answers
15 views

Best model for removing a consistent background image

I'm working on an ML driven background replacement from photos, where the background will always be consistent, but the objects in front of that background (in this case humans) will be different - ...
0
votes
0answers
27 views

What will cause high accuracy but a big loss?

In the question of What is the relationship between the accuracy and the loss in deep learning?, @Jérémy Blain gave a fantastic interpretation of 'relationship' between accuracy and loss: 1 - low ...
0
votes
0answers
15 views

Find Correspondence between Image Pair

I have a problem with the following provided: (for some reason I can't disclose the dataset) Dataset My dataset is a bunch of raw images with a lot of strip-like objects. Each image has a lot of ...
0
votes
1answer
32 views

How to treat time based ticket prices for train/test split

I have a dataset of airfare price tickets that were scraped throughout a 6 month period where each observation represents a particular price for a specific flight on a specific date that it was ...
1
vote
2answers
51 views

Accuracy of KFold Cross Validation for Neural Network

I have a neural network that Im evaluating using 10 -Fold cross validation. The validation accuracy for a fold changes alot during training in the range of -+10% So for example the validation ...
4
votes
1answer
43 views

Overfitting due to features correlating with training set generation rules

As background, I am using a Deep Neural Network built using Keras to classify inputs into 5 categories. The current structure of the network is: Input layer (~450 nodes) Dense layer (750 nodes) ...
0
votes
0answers
8 views

should I re-initialize my optimizer and my scheduler before I try to fine tune my neural network on the different dataset?

I am doing NLP, and I have this block of Transformer body that was already trained on dataset A. Now I am interested in fine tuning this same Transformer on a new dataset B. In my Python code, should ...
0
votes
2answers
31 views

Can I use more features for my training data than my test data will supply?

I am pretty new to the data science game so pardon me, if the answer to my question should be a no-brainer. We are looking at manufacturing / quality data where products are labeled 'okay' or 'not ...
1
vote
1answer
32 views

Error: An operation has `None` for gradient with categorical_crossentropy

I am trying to train my discriminator network using Keras with TensorFlow backend. The network is meant to classify the input into one of the 9 output labels. I am passing a 2D input (height, width, ...
0
votes
0answers
14 views

How to best use Large images in training set for deep learning

I would like to ask you about how I should deal with the images I have. They are really large. They have this shape: (3000, 4000, 3). I'm working on a multilabel classification model. And I want to ...
0
votes
0answers
39 views

saving a model during training of an RL agent

I am training an RL agent using PPO2 algorithm. Iam using stable-baselines library. During the training process, my rewards are slowly increasing and stabilizing, but are falling down suddenly. I ...
0
votes
1answer
32 views

Target encoding before split on skewed data

Hi My data is distributed like follow: And I only have categorical variables on many many levels. As I need to make a regression task I thought about doing leave one out encoding on my categories. ...
0
votes
0answers
18 views

CNN models comparison

I coded a 38 layer CNN and 8 layer CNN but there's something wrong in my 38 layer CNN, which doesn't learn anything. Not able to fugure out what's wrong. They were trained on CIFAR.
4
votes
2answers
250 views

Training a model sample by sample

I'm training a Scikit model but it seems that in all examples, they call the fit method on the entire training set. What I want to do however is call it per sample (...
0
votes
0answers
5 views

Training Algorithm for pointcloud data (3d point data)

I have a "PointNet" neural network which theoretically can work with any number of points as input. I have trained the model using an equal number of points from each object. That is fairly simple and ...
0
votes
0answers
12 views

Accuracy to big when train yolov3

I am trainning yolov3. My result is not as my expected. I think accuracy must be less then 1.0 But I got accuracy and avg too large, in this case is 1577.76 average. Do I still working well?
0
votes
2answers
21 views

Suggestions on how to explain 'models' & 'algorithms'

I guess other members of this Stack have ran in to this before, but I may be wrong: Have you ever been approached and asked to explain the difference between models and algorithms? This happened to be ...
1
vote
0answers
12 views

Grape disease detection

i'm trying to realize a detector for diseased grape leaves, for this par of the project i'm just interested in detecting lets say, the percentage of diseased to healty leaves and/or place a flag where ...

1 2 3 4 5 7