You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hello, everyone:
I run this script with author's dataset well, but i get into into trouble like title when i train the model with my own dataset.
some pics of my dataset:
these pics are 30x500, 25 chars in each pic. i used about 260k of these to train, 65k to validate.
words in pics are randomly selected from some drug infos like this: with open('thistxt', 'r', encoding='utf-8') as f: # read each line into a list all_lines = f.read().split('\n').strip() # link each line to a string data_str = ''.join(all_lines) # generate word with random index rand_word = data_str[a_rand_num, a_rand_num + word_length]
there are 196 unique chars in this txt, so my num_classes in the model is 196. is my dataset not large enough or what? i'd appreciate if anyone can help. 中文也可以
The text was updated successfully, but these errors were encountered:
Hello, everyone:
![333](https://user-images.githubusercontent.com/30395926/42667562-e7ef7c76-867e-11e8-9056-1d4092df2eec.png)
![1000072_13 169 121 122 123 10 11 12 149 150 53 84 151 152 66 67 68 69 50 40 39 43 45 51 46](https://user-images.githubusercontent.com/30395926/42666793-d3c50932-8679-11e8-8943-1621400b1a9d.jpg)
![1000060_168 169 13 14 15 21 25 169 170 20 13 169 171 54 172 173 22 52 53 54 55 36 20 13 13](https://user-images.githubusercontent.com/30395926/42666830-1a96260c-867a-11e8-907f-ace68fc33c40.jpg)
![1000018_61 62 63 29 64 65 53 66 67 68 69 121 122 123 10 11 12 176 177 22 112 13 20 56 115](https://user-images.githubusercontent.com/30395926/42666839-2753c23c-867a-11e8-8174-39b8b71c713c.jpg)
![1000016_172 173 22 52 53 54 55 36 20 13 13 20 174 174 70 56 18 153 154 155 156 175 158 65 53](https://user-images.githubusercontent.com/30395926/42666873-4e100bce-867a-11e8-8ea4-93143b1a4a64.jpg)
![222](https://user-images.githubusercontent.com/30395926/42667037-6026e520-867b-11e8-82e3-b686816b0b74.png)
I run this script with author's dataset well, but i get into into trouble like title when i train the model with my own dataset.
some pics of my dataset:
these pics are 30x500, 25 chars in each pic. i used about 260k of these to train, 65k to validate.
words in pics are randomly selected from some drug infos like this:
with open('thistxt', 'r', encoding='utf-8') as f:
# read each line into a list
all_lines = f.read().split('\n').strip()
# link each line to a string
data_str = ''.join(all_lines)
# generate word with random index
rand_word = data_str[a_rand_num, a_rand_num + word_length]
there are 196 unique chars in this txt, so my
num_classes
in the model is 196. is my dataset not large enough or what? i'd appreciate if anyone can help. 中文也可以The text was updated successfully, but these errors were encountered: