machine-learning

问题 I am new to Keras and trying to implement a neural network machine learning model. The input tensor looks like (X1, X2) and outputs (Y). Note X1 and X2 are correlated. In the model, only X1 will be used for training, but both X1 and X2 will be passed to the loss function that is a function of X1, X2, y_pred and y_true. Below is a pseudocode for loss function. def customLossFunctionWrapper(input_tensor): def LossFunction(y_pred, y_true): loss_value = f(X1, X2, y_pred, y_true) return loss_value

问题 I am new to Keras and trying to implement a neural network machine learning model. The input tensor looks like (X1, X2) and outputs (Y). Note X1 and X2 are correlated. In the model, only X1 will be used for training, but both X1 and X2 will be passed to the loss function that is a function of X1, X2, y_pred and y_true. Below is a pseudocode for loss function. def customLossFunctionWrapper(input_tensor): def LossFunction(y_pred, y_true): loss_value = f(X1, X2, y_pred, y_true) return loss_value

问题 I'm new to python and ubuntu. i got killed after running python code. The file I'm using for the code is around 2.7 GB and I have 16 GB RAM with one tera hard ... what should I do to avoid this problem because I'm searching and found it seems to be out of memory problem I used this command free -mh I got total used free shared buff/cache available Mem: 15G 2.5G 9.7G 148M 3.3G 12G Swap: 4.0G 2.0G 2.0G the code link I tried Link import numpy as np import matplotlib.pyplot as plt class

问题 I have a feature array which is created from ORB with this code part: orb = cv2.ORB_create() #keypoints and descriptors kpO, desO = orb.detectAndCompute(gray_image, None) I create this gray image from colored one. And des0.shape is (500,32). Also shape of my original image(colored one) is (422, 750, 3). And I want to decisionTreeRegression from these arrays for predict the colored version of grayscale image which is I created from colored version. But the problem is starting here , feature

问题 One of the challenges that I have been facing when applying ANN to regression tasks on my job is that in order to find the optimal out for a given range of inputs, I have to feed a multidimensional meshgrid to my model and then simply pick the highest value. However, this is overall a very computationally costly solution. The lenght of the text bellow might be scary but it just my attempt to better explain it. Let me explain with other words. Supposing that I have 9 inputs for my ANN, and

问题 I have the following situation: a Python Flask app running on Google App engine; this app serves predictions from a Spacy machine learning model. Throughout the day, there is a workflow in place which adds new training data for this model, and the App has a cron job that retrains the model taking this new training data into account every evening. The problem is that I want each App instance to reference this newly trained model after it becomes available. I can upload the model somewhere (say

问题 I have the following situation: a Python Flask app running on Google App engine; this app serves predictions from a Spacy machine learning model. Throughout the day, there is a workflow in place which adds new training data for this model, and the App has a cron job that retrains the model taking this new training data into account every evening. The problem is that I want each App instance to reference this newly trained model after it becomes available. I can upload the model somewhere (say

问题 I have the following situation: a Python Flask app running on Google App engine; this app serves predictions from a Spacy machine learning model. Throughout the day, there is a workflow in place which adds new training data for this model, and the App has a cron job that retrains the model taking this new training data into account every evening. The problem is that I want each App instance to reference this newly trained model after it becomes available. I can upload the model somewhere (say

问题 I have the following situation: a Python Flask app running on Google App engine; this app serves predictions from a Spacy machine learning model. Throughout the day, there is a workflow in place which adds new training data for this model, and the App has a cron job that retrains the model taking this new training data into account every evening. The problem is that I want each App instance to reference this newly trained model after it becomes available. I can upload the model somewhere (say

问题 I have the following situation: a Python Flask app running on Google App engine; this app serves predictions from a Spacy machine learning model. Throughout the day, there is a workflow in place which adds new training data for this model, and the App has a cron job that retrains the model taking this new training data into account every evening. The problem is that I want each App instance to reference this newly trained model after it becomes available. I can upload the model somewhere (say