sign-language | recognize Sign language in realtime using Tensorflow | Computer Vision library

First, you can create default DataGenerator to plot original images easily

Kaggle recommends using their own API instead of wget or rsync.

First, make an API token for Kaggle. On Kaggle's website go to "My Account", Scroll to API section and click on "Create New API Token" - It will download kaggle.json file on your machine.

Then run the following in Google Colab:

If your cnn_tf module comes from this Sign Language Github progect, as it seems, notice that in the project requirements it is explicitly mentioned Tensorflow 1.5, and not Tensorflow 2.1. There have been some major changes in the transition from Tensorflow 1.x to 2.x, and the tf.logging module is probably not included in v2.1.

You should create a virtual environment and install Tensorflow 1.5 in order to run it successfully; keeping in mind the specific versions of the other requirements is also highly advised.

The repo is clearly written for OpenCV 3.x. But, you are running on OpenCV 4.1. Repo code takes find_contour's second return value for contours( find_contours(...)[1] ). You should change 1 to 0.

I believe you need a codebase where you can train your model on the dataset that you generate. Based on things like your background, light settings etc. That would be better than using a pre-trained model which is trained on the data from the different distribution

I would recommend using this where you can start video feed and training images will be automatically taken for the gestures. You also can select the number of classes you want. That can improve your performance. Or else you can use the original code Emojinator which can detect 13 hand gestures

Is the image "a.jpg" part of the same data set?

If the answer is no -> you should keep in mind that an NN can only predict images that have similar characteristics to the training images. If the NN is trained with a wide type of images, it could predict a wide range of images, but if the NN is trained with a very static data set (white background, same size, hand centered, etc.) it would fail if the Input image is very different.

If the answer is yes -> if you obtained 80% accuracy, the image may be misclassified. If you used a set of test data to validate your NN, you must obtain the same results by using them as a group or by passing them one by one.

The problem is that there are spaces in your column names; here is what I get when I save your data and load the dataframe as you have done:

Welcome to the community. That looks like a nice way to start off.

Like @hilverts_drinking_problem suggested, I would recommend looking at sklearn documentation. But here's a quick explanation of what's going on.

The train, test split function randomly splits the dataset into two datasets for the sake of training and testing. test_size = 0.2 means 20% of the data will be in the test set, remaining 80% in train.

The next two lines are just separating out the inputs (features) and outputs (targets) for training. Same for test in the next two lines.

Finally, you create an SVM object, train the model using model.fit, and get its score using .score. You then use the model to predict stuff for the test set. Finally, you print the accuracy score for your test set, along with its confusion matrix.

If you need me to clarify/detail something, let me know!

The problem is that you have made it a float on this line: