0 votes
0 answers
16 views
how to fix R and Keras : TypeError: Cannot convert the argument `type_value`: None to a TensorFlow DTypei have want to compile & implement from scratch deep learning layer_naive_dense <- function(input_size, output_size, activation){ self <- new.env(parent = emptyenv()) attr(self, "...
asked 14 hours ago0 votes
0 answers
27 views
GradientTape won't calculate gradients after restoring a model from ModelCheckpoint (TensorFlow)I'm training a CNN on Tensorflow for binary classification and executing my code in Google Colab. CNN_model = tf.keras.Sequential([ tf.keras.layers.Input(shape=(IMAGE_SIZE, IMAGE_SIZE, 3)), tf....
asked 22 hours ago-4 votes
0 answers
46 views
Errors while converting huggingface dataset to Tensorflow dataset while using cuda [closed]I am trying to do finetuning using a dataset from huggingface. I keep getting InternalError. My GPU set up is as follows: +------------------------------------------------------------------------------...
asked yesterday0 votes
1 answer
23 views
Custom TFJS layer no trainable variables found during trainingI made a custom layer in TensorFlow.js that consists of sublayers but not weights of its own. Here is a simplified example import * as tf from "@tensorflow/tfjs"; import { LayerArgs } from &...
asked yesterday-1 votes
0 answers
37 views
Why does my multi-task Keras model show high L1 training accuracy but low L1 test accuracy with low test loss? [closed]I'm training a multi-task deep learning model using TensorFlow/Keras to classify car images with two objectives: L2 Task: Binary classification — Car vs. No Car L1 Task: Binary classification — among ...
asked yesterday0 votes
2 answers
43 views
unable to load a model with KerasI wanted to create a speech recognition application and I was following this tutorial : Transformer ASR. After training it for 1 epoch, I saved the model and it saved successfully: model.save("...
asked 2 days ago-3 votes
0 answers
31 views
Data leakage with MNIST dataset [closed]On first epoch I get around 0.6 accuracy on training set and around .98 on validation set. Can't see how is this possible if I'm using sklearn.train_test_split(). Preparing data: for j in range(10): ...
asked Jul 8 at 15:180 votes
0 answers
26 views
ImportError: cannot import name 'Generator' from 'model' (unknown location) in GAN training scriptI'm running a GAN training pipeline in Google Colab. The preprocessing scripts run without any issues: GitHub repository !python run_preprocess.py --dataset custom --train_num 500 !python ...
asked Jul 7 at 22:40-1 votes
0 answers
16 views
Unequal size of batches created by timeseriesdata_from_array [closed]I am creating sequences of samples using tf.keras.preprocessing.timeseries_dataset_from_array. The last batch in the input samples contains less samples than the last batch of the target samples.[13,...
asked Jul 7 at 10:48-1 votes
0 answers
26 views
How to fix overly smooth LSTM forecasts in volatility time series prediction?I'm facing an issue with forecasting volatility using LSTM and Gridsearch for find the best Hyperparameter for model. param_grid = { 'units': [32, 64, 128], 'dropout': [0.2, 0.5], '...
asked Jul 6 at 20:360 votes
1 answer
41 views
Using pd.from_dummies to get the values in target variable back (after one-hot encoding) but getting Value ErrorI'm participating in the curent Kaggle playground series and I decided to use a neural network for the binary classification problem because I am practicing making simple ones. I converted the target ...
asked Jul 6 at 20:00-3 votes
1 answer
35 views
there is an issue regarding imgaug in google colab? [closed]I tried to run the code of Breast Tumor Classification Using EfficientNet Deep Learning Model paper in there they use import imgaug.augmenters as iaa this and i cant import this there is version issue ...
asked Jul 6 at 13:250 votes
0 answers
30 views
Add Feature extraction as part of a keras modelIs it possible to add feature extraction as part of a keras model, so when a user runs inference there is no need for computing those features as that part is done inside the model. Im looking for a ...
asked Jul 5 at 14:580 votes
0 answers
16 views
Distributed Tensorflow with mulitple GPUS training MNIST with Optuna is stuck when trainingI created a 5 GPU Cluster using three nodes/machines locally using the tensorflow.distributed.MultiWorkerMirrored Strategy. One machine has the Apple M1 Pro Metals GPU, the other two nodes has NVIDIA ...
asked Jul 4 at 19:530 votes
0 answers
37 views
How to use Replicate Trained Model after Training is finished?I am developing an AI Headshot SaaS and I am having a bit of trouble getting the Replicate models to work correctly and it's kind of confusing me. Everything works up to Replicate Training Model but I ...
asked Jul 3 at 18:04RetroSearch is an open source project built by @garambo | Open a GitHub Issue
Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo
HTML:
3.2
| Encoding:
UTF-8
| Version:
0.7.4