clovaai
Poor predictions and 0 accuracy on Arabic
Here is the .yml file I used:
lang_char: ""
character: "0123456789!"#$%&'()*+,-./:;<=>?@[\]^_`{|}~ abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ\u0660
\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669\xAB\xBB\u061F\u060C\u061B
\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0627\u064B\u0628\u0629\u062A\u062B\u062C
\u062D\u062E\u062F\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063A
\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064A\u064B\u064C\u064D\u064E
\u064F\u0650\u0651\u0652\u0653\u0654\u0670\u0671\u0679\u067E\u0686\u0688\u0691\u0698
\u06A9\u06AD\u06AF\u06BA\u06BE\u06C0\u06C1\u06C2\u06C3\u06C6\u06C7\u06C8\u06CB\u06CC
\u06D0\u06D2\u06D3\u06D5"
experiment_name: 'arabic'
train_data: 'all_data/en_train_filtered'
valid_data: 'all_data/en_val'
manualSeed: 1111
workers: 6
batch_size: 2
num_iter: 50000
valInterval: 1000
saved_model: 'saved_models/arabic.pth'
FT: False
optim: False # default is Adadelta
lr: 0.1
beta1: 0.9
rho: 0.95
eps: 0.00000001
grad_clip: 5
#Data processing
select_data: 'en_train_filtered' # this is dataset folder in train_data
batch_ratio: '1'
total_data_usage_ratio: 1.0
batch_max_length: 34
imgH: 64
imgW: 600
rgb: False
contrast_adjust: False
sensitive: True
PAD: True
contrast_adjust: 0.0
data_filtering_off: False
Model Architecture
Transformation: 'None' FeatureExtraction: 'ResNet' SequenceModeling: 'BiLSTM' Prediction: 'CTC' num_fiducial: 20 input_channel: 1 output_channel: 512 hidden_size: 512 decode: 'greedy' new_prediction: True freeze_FeatureFxtraction: False freeze_SequenceModeling: False
sample of dataset :
