Tag: deep-learning

Transfer Learning with Quantization Aware Training using Functional API

deep-learning keras machine-learning python tensorflow

I have a model that I am using transfer learning for MobileNetV2 and I’d like to quantize it and compare the accuracy difference against a non-quantized model with transfer learning. However, they do not entirely support recursive quantization, but according to this, this method should quantize my model: https://github.com/tensorflow/model-optimization/issues/377#issuecomment-820948555 What I tried doing was: It is still giving me the

Python argmax of dot product of weighted matrix and vector (mnist)

deep-learning mlp mnist numpy python

What does argmax mean in this context? I am following the tutorial in this colab notebook: https://colab.research.google.com/github/chokkan/deeplearningclass/blob/master/mnist.ipynb It looks like this is saying that for every record x and its truth value y, in the vectors Xtrain and Ytrain, take the max value of the dot product of the weighted matrix W and the record x. Does this mean it

Reading files with .h5 format and using it in dataset

deep-learning h5py python pytorch vision

I have two folders( one for train and one for test) and each one has around 10 files in h5 format. I want to read them and use them in a dataset. I have a function to read them, but I don’t know how I can use it to read the file in my class. Do you have a suggestion?

How can we Read just float values from the lines of a file?

deep-learning file python

I want to read a file line by line and use some elements written in that file as the learning rate, epochs, and batch size in my neural network to configure it. My code is like this: and the result is like this: Do you have any idea how I can assign the values written in each line to my

Keras Confusion Matrix does not look right

confusion-matrix deep-learning keras python tensorflow

I am running a Keras model on the Breast Cancer dataset. I got around 96% accuracy with it, but the confusion matrix is completely off. Here are the graphs: And here is my confusion matrix: The matrix is saying that I have no true negatives and they’re actually false negatives, when I believe that it’s the reverse. Another thing that

How does Tokenizer in tensorflow deal with out of vocabulary tokens if I don’t provide oov_token?

deep-learning keras python tensorflow

I didn’t get any error with that code even though I didn’t provide oov_token argument. I expected to get an error in test_tweets = tokenizer.texts_to_sequences(X_test) How does tensorflow deal with out of vocabulary words during the test time when you don’t provide the oov_token? Answer OOV words will be ignored / discarded by default, if oov_token is None:

What does Tensor[batch_mask, …] do?

bilstm deep-learning lstm python pytorch

I saw this line of code in an implementation of BiLSTM: I assume this is some kind of “masking” operation, but found little information on Google about the meaning of …. Please help:). Original Code: Answer I assume that batch_mask is a boolean tensor. In that case, batch_output[batch_mask] performs a boolean indexing that selects the elements corresponding to True in

Tensorflow ValueError: Shapes (64, 1) and (1, 1) are incompatible

deep-learning neural-network python siamese-network tensorflow

I’m trying to build a Siamese Neural Network to analyze the MNIST dataset, however when trying to fit the model to the dataset I encounter this problem according to which I have training data and labels shapes’ mismatch. I tried changing the loss function as well as tried to squeeze the labels array, and neither of “solutions” worked. Here are

Try to replace the nan values by pandas , but Error: Columns must be same length as key

deep-learning error-handling kaggle pandas python

It is a simple project in Kaggle, just imitating one blog, but failed. enter image description here train_inf[‘Age’]=train_inf.fillna(train_inf[‘Age’].median()) ValueError: Columns must be same length as key just this code I am searching for a long time on net. But no use. Please help or try to give some ideas how achieve this. Thanks in advance. Answer You are close, need

How to draw the precision-recall curve for a segmentation model?

deep-learning keras python scikit-learn tensorflow

I am using an U-Net for segmenting my data of interest. The masks are grayscale and of size (256,256,1). There are 80 images in the test set. The test images (X_ts) and their respective ground-truth masks (Y_ts) are constructed, saved, and loaded like this: The shape of Y_ts (ground truth) is therefore (80,256,256,1) and these are of type “Array of