Initial commit

src/models/globals.py

@@ -0,0 +1,26 @@
+# Formula image(grayscale) mean and variance
+IMAGE_MEAN = 0.9545467
+IMAGE_STD  = 0.15394445
+
+# Density value for pdf to image conversion
+TEXTELL_DENSITY = 200
+
+# Vocabulary size for TexTeller
+VOCAB_SIZE = 10000
+
+# Fixed size for input image for TexTeller
+FIXED_IMG_SIZE = 448
+
+# Image channel for TexTeller
+IMG_CHANNELS = 1  # grayscale image
+
+# Max size of token for embedding
+MAX_TOKEN_SIZE = 512
+
+# Scaling ratio for random resizing when training
+MAX_RESIZE_RATIO = 1.15
+MIN_RESIZE_RATIO = 0.75
+
+# Minimum height and width for input image for TexTeller
+MIN_HEIGHT = 12
+MIN_WIDTH  = 30