Bleu | Android Bluetooth Messaging Application based on Material | Android library

Hello to any competent people out there who would stumble upon my post.
I require assistance like never before.

My problem is here:

so i have food list data that i stored in JSON here :

I’m currently trying to train a Spanish to English model using yaml scripts. My data set is pretty big but just for starters, I’m trying to get a 10,000 training set and 1000-2000 validation set working well first. However, after trying for days, I think I need help considering that my validation accuracy goes down the more I train while my training accuracy goes up.

My data comes from the ES-EN coronavirus commentary data set from ModelFront found here https://console.modelfront.com/#/evaluations/5e86e34597c1790017d4050a. I found the parallel sentences to be pretty accurate. And I’m using the first 10,000 parallel lines from the dataset, skipping sentences that contain any digits. I then take the next 1000 or 2000 for my validation set and the next 1000 for my test set, only containing sentences without numbers. Upon looking at the data, it looks clean and the sentences are lined up with each other in the respective lines.

I then use sentencepiece to build a vocabulary model. Using the spm_train command, I feed in my English and Spanish training set, comma separated in the argument, and output a single esen.model. In addition, I chose to use unigrams and a vocab size of 16000

As for my yaml configuration file: here is what I specify

My source and target training data (the 10,000 I extracted for English and Spanish with “sentencepiece” in the transforms [])

My source and target validation data (2,000 for English and Spanish with “sentencepiece” in the transforms [])

My vocab model esen.model for both my Src and target vocab model

Encoder: rnn Decoder: rnn Type: LSTM Layers: 2 bidir: true

Optim: Adam Learning rate: 0.001

Training steps: 5000 Valid steps: 1000

Other logging data.

Upon starting the training with onmt_translate, my training accuracy starts off at 7.65 and goes into the low 70s by the time 5000 steps are over. But, in that time frame, my validation accuracy goes from 24 to 19.

I then use bleu to score my test set, which gets a BP of ~0.67.

I noticed that after trying sgd with a learning rate of 1, my validation accuracy kept increasing, but the perplexity started going back up at the end.

I’m wondering if I’m doing anything wrong that would make my validation accuracy go down while my training accuracy goes up? Do I just need to train more? Can anyone recommend anything else to improve this model? I’ve been staring at it for a few days. Anything is appreciated. Thanks.

!spm_train --input=data/spanish_train,data/english_train --model_prefix=data/esen --character_coverage=1 --vocab_size=16000 --model_type=unigram

I have this json file used to list material by ref -> color and size:

As I am completely new to pandas, I would like to ask.

I have two CSV files.

One of them has all the colors of different languages in one column:

I have color blue in three rows here: azul, bleu all means blue in different languages, so they should be in the same group 1. rouge and rojo means red, so they are also in the same group, so they should have 2.

Here is my first table colors:

and so on, in my csv this column group is empty and I have to fill it

I have also second CSV file, when it looks like this

Table colors_language:

I want to fill the column group in the first CSV file by comparing it to the second CSV file which has information.

I have found out how to compare on one column, but how I compare on column from one csv to three columns from another csv to fill the group column in the first CSV?

I have two data frames df (with 15000 rows) and df1 ( with 20000 rows)

Where df looks like

Hope you're fine. What I'm trying to do is using an icon with fontawesome, and be able to use it as a button. Here is my code :

I am trying to read images from WikiArt dataset. However, I cannot load some images which contain non-ascii characters: For example: fã©lix-del-marle_nu-agenouill-sur-fond-bleu-1937.jpg' although the file exists in the directory. I also compared the output string name from os.listdir() and the one from FileNotFoundError: No such file: '/wiki_art_paintings/rescaled_600px_max_side/Expressionism/fã©lix-del-marle_nu-agenouill-sur-fond-bleu-1937.jpg' by doing 'fã©lix-del-marle_nu-agenouill-sur-fond-bleu-1937.jpg' == 'fã©lix-del-marle_nu-agenouill-sur-fond-bleu-1937.jpg'. The output is False.

What can be a problem here?

I have a a model to train in python using keras and my training dataset contains 30 000 images. Those images represents animals for a total of 6 classes.

My problem is when i come to choose an image_shape for the training, the images have different shapes so i am not very sure what to do in this case. I thought about finding the max/min height and max/min width to see what should be a decent shape to choose.