Hello Stack Overflow community, I'm currently working on a Python project where I need to integrate both trained and testing data into my code The global algorithm has been implemented in C++. However, I'm feeling a bit lost as to whether I've placed the pretrained data in the right locations or not. I've attempted to add the data, but I'm uncertain if it's in the correct places. Additionally, I'm facing challenges in testing the code with my own dataset and analyzing the output. If anyone could provide guidance or suggestions on the proper placement of pretrained data and offer insights into ..read more

I need WMT news data with human score. I looked at github link https://github.com/wmt-conference/wmt22-news-systems , there is an xml folder which contains the source, reference, translated data. And there is another folder with name humaneval, there human scoring is provided. I am facing challenge to connect both the data. In humaneval data SID column is provided but that has different value than source_id provided in xml data. If anyone can help in guiding the connection between those two data folder, that would be helpful ..read more

I'm not sure how to solve this problem. Problem statement is: Consider the binary classification problem where X = R d and Y = {0, 1}. Consider the class of Binary classifiers given by intersection of three half-spaces. Show that proper learning w.r.t. this class of intersection of three half-spaces (the class F) is computationally hard to learn properly unless NP = RP. Specifically Hint: Remember we are thinking of only proper learning. Try a reduction using the 3 term DNF class. An extra hint is use d = 2m, m coordinates for the inclusion of each coordinate and m coordinates for inclusion of ..read more

Apologies for asking such a dumb question. I'm new to all of this and have not used this function before. I'm required to do this for an assignment, and looked all over google to find if anyone has run into this problem but I haven't seen anyone asking about this. Why is tf.image.rgb_to_grayscale not producing an actual grayscale image? Or is this just the "grayscale" image that is widely accepted? rgb_to_grayscale does not produce grayscale pictures input_images = tf.image.rgb_to_grayscale(target_images) This is what I did to produce the input images. I'm not sure if I'm using it wrong but th ..read more

When I train a model using randomForest, and then attempt to predict, in the following manner, there are no issues: rf <- randomForest(price_category~., data=train_set, ntree=300,importance=TRUE) test_set$ClassPredicted <- predict(rf, newdata = test_set, "class") However, when I attempt to chose the predictors, and structure it in the following way: rf1 <- randomForest(price_category = living_area + year + n_photos + energy_label, data = train_set, ntree=1000, importance=TRUE) test_set$ClassPredicted <- predict(rf1, newdata = test_set, "class") This error pops up: Error in ..read more

Im trying to follow the Roboflow guide to training RTMDet on a custom dataset. I don't have a high end GPU so I'm trying to use a colab environment. When I try to initialize the Model using the rtmdet_m weights and config file I get a filenotfound error even though I'm 100% positive the files exist in the drive directory. I believe the issue has something to do with the Base within the config file below _base_ = '/content/drive/MyDrive/RTMDet_Models/rtmdet_l_syncbn_fast_8xb32-300e_coco.py' # ========================modified parameters====================== deepen_factor = 0.67 widen_factor ..read more

I am trying to convert images generated in to a dataset. (All I have is just png images in n folders and there is no label or meta data) This is what I aspire to do: I am using torch audio to convert audio formats to Mel spectrogram and save the images as png format. Status:done Now I have n number of folders(classes) with images so I am curious if I could convert the newly generated images into data and target as in normal datasets, so that I can use sklearn to do the test train splits sklearn.model_selection.train_test_split . Status:not done eg: fetch mnist dataset ds_mnist = sklearn ..read more

I am trying to convert images generated in to a dataset.(All I ahve is just png images in n folders and there is no label or meta data) This is what I aspire to do: I am using torch audio to convert audio formats to Mel spectrogram and save the images as Png format. Status:done Now I have ‘n’ number of folders(classes) with images so I am curious if I could convert the newly generated images into data and target as in normal datasets, so that I can use sklearn to do the test train splits sklearn.model_selection.train_test_split . Status:not done eg: fetch mnist dataset ds_mnist = sklear ..read more

I have Python 3.12.0. My project called for TensorFlow, however it can only be used with Python 3.11. The same is true for PyTorch. Is anyone aware of other libraries I can use in place of those I mentioned, compatible with Python 3.12? Tried to install TensorFlow and PyTorch ..read more

I have trained a SequentialFeatureSelector from sklearn and am now interested in the best model (based on the given scoring method) it produced. Is there a possible way of extracting the parameters and using them generate the model that was used? I have seen that there exists a get_params() function for the SequentialFeatureSelector, but I don't undestand how to interpret the output and retrieve the best estimator ..read more