Questions tagged [overfitting-underfitting]
143 questions
1
vote
0 answers
Training CNN on Matlab gives different results compared to training the same network on python using keras
I'm using Keras to train a netwok for classification problem on python, the model that i am using is as follows:
filter_size = (2,2)
maxpool_size = (2, 2)
dr = 0.5
inputs = Input((12,8,1), name='main_input')
main_branch = Conv2D(20,…
Delaram
- 11
- 3
1
vote
2 answers
Validation loss goes up after some epoch transfer learning
My validation loss decreases at a good rate for the first 50 epoch but after that the validation loss stops decreasing for ten epoch after that. I'm using mobilenet and freezing the layers and adding my custom head. my custom head is as follows:
def…
kuro
- 194
- 9
1
vote
1 answer
How does one tackle over-fitting in NLP based CNN models for multiclass text classification with word embeddings?
(Problem: Overfitting issues in a multiclass text classification problem)
In my personal project, the objective is to classify the industry tags of a company based on the company description. The steps I've taken are:
Removing stopwords,…
Srinivas
- 11
- 2
1
vote
1 answer
How to fine tune using XGboost
I'm trying to get a generalized model for the Mercedes Greener Manufacturing dataset. So, I'm trying to achieve the same using XGBoost Regressor. I have used a loop ranging from 1-100 as the seed of the train test set so as to get better sampling. I…
kilmonger
- 41
- 7
1
vote
0 answers
How effective is early stopping when the validation accuracy varies
I am building a time series model for future forecasting which consists of 2 BILSTM layers followed by a dense layer. I have a total of 120 products to forecast their values. And I have a relatively small dataset (Monthly data for a period of 2…
I. A
- 2,252
- 26
- 65
0
votes
0 answers
Getting r2_score negative
I have only two independent columns in my data, that too they are categorical with more than 30 unique categories in each column (cuisine and location) and I am trying to build model to predict the price which is continuous.
I applied one hot…
0
votes
1 answer
Torch loaded model accuracy is downed
I have trained a ResNet model and saved its weights to a .pt file as shown below.
## This is file 1 ##
model = resnet50()
model.to(device)
optimizer = Adam(model.parameters(), eps=1e-08, lr = 0.001, weight_decay=1e-4, betas=(0.9, 0.999))
criterion =…
No Yeah
- 61
- 7
0
votes
0 answers
Need insights on how to reduce overfitting with MLPClassifier
I am new to data science. Please bear with me as I ask this long question. I am trying to do Speech Emotion Recognition with MLPCLassifier on RAVDESS and Crema datasets. I am getting high validation loss and large training-validation accuracy gap.
I…
0
votes
1 answer
Regularization in Fasttext
I am currently training a FastText classifier and I'm facing the issue of overfitting.
model = fasttext.train_supervised( f'train{runID}.txt', lr=1.0, epoch=10, wordNgrams=2, dim=300, thread=2, verbose=100)
The model seems to be fitting the…
Amin Tabatabaei
- 65
- 6
0
votes
0 answers
Did I store the training loss and validation loss in a wrong way?
Did I store the training loss and validation loss in a wrong way? Because the training loss is greater than the validation loss somehow.
def train(dataloader, model, loss_fn, optimizer):
size = len(dataloader.dataset)
model.train()
…
ZeL
- 1
0
votes
0 answers
Cross validation score/Training score/Test score : what should i considered to say whether a model is a well generalised model?
I am new to Machine learning domain and I want to clear my doubt. My model is a multi class classification model based on smiles notation dataset. And my dataset is less than 1000 rows and also it is an imbalance dataset.
Suppose i am getting high…
Sudarshan Murmu
- 1
- 1
0
votes
0 answers
What insights can the training and validation losses curve provide for my sound separation model's performance?
I trained sound separation model with 10000samples and the same number of sample was used in validation with number of epochs =10 and 32 batch and 4 number of worker using Adam optimizer . I need someone explain to me the output training and…
0
votes
0 answers
Avoiding overfitting in panel data and explainable ai
I have panel data consisting of yearly credit ratings as a target variable and some features for its estimation. Each year of my 20 year time series i have around 400 firms.
I use shap to analyse some of those features and analyse how this results…
Soph
- 1
0
votes
1 answer
Validation accuracy doesn't change at all while training a CNN network
So, I was trying to implement AlexNet on the Intel image dataset for classification. However, although during training I get high accuracy scores (0.84), validation accuracy does not change and it is very low (0.16). I have tried different…
rasul12345
- 3
- 2
0
votes
0 answers
Finetuning gpt2, validation loss increases with accuracy and f1 score
I am finetuning gpt2 on text classification with the huggingface trainer. I observed that after 2 epochs, my validation loss start to increase, but my validation accuracy and f1 score still increases too. I have tried with 2 different seed but I…
HCY
- 1
- 1