Stack Overflow
Stack Overflow

Questions tagged [custom-training]

90 questions
10
votes
1 answer

Memory leak for custom tensorflow training using @tf.function

I am trying to write my own training loop for TF2/Keras, following the official Keras walkthrough. The vanilla version works like a charm, but when I try to add the @tf.function decorator to my training step, some memory leak grabs all my memory and…
este_banquito
  • 101
  • 4
9
votes
1 answer

Constraining a neural network's output to be within an arbitrary range

I have a custom neural network that I am training on data and seek to constrain the network's output values to always be between two arbitrary constants: [lower_bound,upper_bound]. Are there any best practices for encoding this constraint in a loss…
Mathews24
  • 681
  • 10
  • 30
4
votes
1 answer

Chess evaluation Neural Network is converging to the average

I'm currently working on a Chess AI. The idea behind this project is to create a neural network that learns how to evaluate a board state and then traverse the next moves using Monte Carlo tree search to find the "best" move to play (evaluated by…
Bertil Braun
  • 56
  • 4
4
votes
0 answers

Why is YOLO training loss not decreasing significantly & mean IoU not increasing?

I am trying to implement Yolo (the paper did not mention it as v1 but it's the first paper so I think it's v1) from this paper. I am implementing on Google Colab using Keras and Tensorflow 1.x. TLDR; Results: Starting Epochs: Iteration, 0 Train on…
prc777
  • 211
  • 1
  • 7
3
votes
1 answer

While training Model on Google Colab, should I remain connected?

Do I need to remain connected with Colab and the internet when training a dataset model (Darknet) for Object detection on Google Colab? As the training is going on Colab and connected to my drive, here Weight files will be saved on my google drive…
Anas Abdullah Jhaggar
  • 33
  • 4
2
votes
0 answers

Training time for dolly-v2-12b on a custom dataset with an A10 gpu

Hi I am trying to train the dolly-v2-12b or any of the dolly model using a custom dataset using A10 gpu. I am coding in pycharm, windows os. The task is similar to a Q&A. I am trying to use this as communication assistant that can answer the…
Sneha T S
  • 21
  • 6
2
votes
1 answer

Azure Form Recognizer Training Issue - InvalidContentSourceFormat Error

I have been experiencing with the Form Recognizer resource on Azure. Despite following the instructions and guidelines provided meticulously, I have been encountering consistent errors during the AI training process. The specific error message that…
Guillermo López Gómez
  • 21
  • 2
2
votes
2 answers

Metrics using batches v/s metrics using full dataset

I am using training an image classification model using the pre-trained mobile network. During training, I am seeing very high values (more than 70%) for Accuracy, Precision, Recall, and F1-score on both the training dataset and validation…
learner
  • 828
  • 2
  • 19
  • 36
2
votes
0 answers

How to increase frequency of validation in fastai?

In fastai during training, the validation loss and evaluation metric is calculated every epoch and best epoch is saved if we use the SaveModelCallback() callback. However we could increase the frequency of this process and evaluate the metric after…
Aditya Bansal
  • 21
  • 1
2
votes
0 answers

ValueError: [E024] Could not find an optimal move to supervise the parser. while training custom NER using Spacy v3.x

while training my custom NER model using spacy v3.x, !python -m spacy train /content/drive/MyDrive/Interview_Buddy/config.cfg --output ./output it is throwing me above error. " ValueError("[E024] Could not find an optimal move to supervise the…
akshay kadam
  • 33
  • 3
2
votes
1 answer

Evaluation using iou_threshold 0.5 is 0.000000

I'm working using the PixelLib to create a custom training. These are my training steps: train_maskrcnn = instance_custom_training() train_maskrcnn.modelConfig(network_backbone = "resnet101", num_classes= 2, batch_size =…
Leonardo AGNUSDEI
  • 21
  • 1
2
votes
1 answer

Trying to pass custom loss but it will not allow me to. AttributeError: 'float' object has no attribute 'backward'

I have a custom loss function that I am trying to use on my model however when i use loss.backward() in Pytorch is not working. This is my loss function: class Neg_Pearson(nn.Module): # Pearson range [-1, 1] so if < 0, abs|loss| ; if >0, 1- loss …
NeuralNew
  • 96
  • 1
  • 10
2
votes
1 answer

Tensorflow2.x custom data generator with multiprocessing

I just upgraded to tensorflow 2.3. I want to make my own data generator for training. With tensorflow 1.x, I did this: def get_data_generator(test_flag): item_list = load_item_list(test_flag) print('data loaded') while True: X = [] Y =…
user1941407
  • 2,722
  • 4
  • 27
  • 39
2
votes
0 answers

"Shapes of all inputs must match" error loss function when trying to do custom training with tf.GradientTape()

I'm using Python 3.7.7. and Tensorflow 2.1.0 with Functional API and Eager Execution. I'm trying to do custom training, with an encoder extracted from a U-Net pretrained network: I get the U-Net model without compile it. I have loaded the weights…
VansFannel
  • 45,055
  • 107
  • 359
  • 626
2
votes
0 answers

Data Augmentation in darknet and train YOLO

I had been wondering whether data augmentation is done using config file of yolo or is implemented in src/image.c. I am talking with reference to darknet and study of issue #1408. I am addressing this issue after a lot of research. If i look into…
Sanpreet
  • 103
  • 8
1
2 3 4 5 6