Initial version of the app

app.py

@@ -0,0 +1,137 @@
+import os
+import re
+import gradio as gr
+import torch
+from huggingface_hub import hf_hub_download
+from torch.utils.data import DataLoader, Dataset
+
+
+
+
+model_file_path = hf_hub_download("meliascosta/wiki_hiagm", "hiagm_dyn_quant.p",
+                        use_auth_token=os.environ['TOKEN'])
+vocab_file_path = hf_hub_download("meliascosta/wiki_hiagm", "vocab/word.dict",
+                        use_auth_token=os.environ['TOKEN'])
+label_file_path = hf_hub_download("meliascosta/wiki_hiagm", "vocab/label.dict",
+                        use_auth_token=os.environ['TOKEN'])
+
+# Load model
+# m = torch.load('./temp_dyn.p')
+model = torch.load(model_file_path, map_location=torch.device('cpu'))
+
+model.eval()
+
+MAX_INPUT_LENGTH = 256
+K_TOP = 3
+BATCH_SIZE = 512
+P_THRESHOLD = 0.5
+
+class CustomImageDataset(Dataset):
+    def __init__(self, samples):
+        self.samples = samples
+
+    def __len__(self):
+        return len(self.samples)
+
+    def __getitem__(self, idx):
+        return self.samples[idx]
+
+
+# Load vocab mappings 
+
+v2i = {}
+i2v = {}
+with open(vocab_file_path) as f:
+     for i, line in enumerate(f):
+        data = line.rstrip().split('\t')
+        assert len(data) == 2
+        v2i[data[0]] = i
+        i2v[i] = data[0]
+
+v2i_lab = {}
+i2v_lab = {}
+with open(label_file_path) as f:
+     for i, line in enumerate(f):
+        data = line.rstrip().split('\t')
+        assert len(data) == 2
+        v2i_lab[data[0]] = i
+        i2v_lab[i] = data[0]
+
+
+### PREPROCESSING
+
+english_stopwords = ['i', 'me', 'my', 'myself', 'we', 'our', 'ours', 'ourselves', 'you', "you're", "you've", "you'll",
+                     "you'd", 'your', 'yours', 'yourself', 'yourselves', 'he', 'him', 'his', 'himself', 'she', "she's",
+                     'her', 'hers', 'herself', 'it', "it's", 'its', 'itself', 'they', 'them', 'their', 'theirs',
+                     'themselves', 'what', 'which', 'who', 'whom', 'this', 'that', "that'll", 'these', 'those', 'am',
+                     'is', 'are', 'was', 'were', 'be', 'been', 'being', 'have', 'has', 'had', 'having', 'do', 'does',
+                     'did', 'doing', 'a', 'an', 'the', 'and', 'but', 'if', 'or', 'because', 'as', 'until', 'while',
+                     'of', 'at', 'by', 'for', 'with', 'about', 'against', 'between', 'into', 'through', 'during',
+                     'before', 'after', 'above', 'below', 'to', 'from', 'up', 'down', 'in', 'out', 'on', 'off',
+                     'over', 'under', 'again', 'further', 'then', 'once', 'here', 'there', 'when', 'where', 'why',
+                     'how', 'all', 'any', 'both', 'each', 'few', 'more', 'most', 'other', 'some', 'such', 'no', 'nor',
+                     'not', 'only', 'own', 'same', 'so', 'than', 'too', 'very', 's', 't', 'can', 'will', 'just', 'don',
+                     "don't", 'should', "should've", 'now', 'd', 'll', 'm', 'o', 're', 've', 'y', 'ain', 'aren',
+                     "aren't", 'couldn', "couldn't", 'didn', "didn't", 'doesn', "doesn't", 'hadn', "hadn't", 'hasn',
+                     "hasn't", 'haven', "haven't", 'isn', "isn't", 'ma', 'mightn', "mightn't", 'mustn', "mustn't",
+                     'needn', "needn't", 'shan', "shan't", 'shouldn', "shouldn't", 'wasn', "wasn't", 'weren', "weren't",
+                     'won', "won't", 'wouldn', "wouldn't", '\\.', '\\?', ',', '\\!', "'s", '']
+
+
+def clean_stopwords(sample):
+    """
+    :param sample: List[Str], lower case
+    :return:  List[Str]
+    """
+    return [token for token in sample if token not in english_stopwords]
+
+
+def clean_str(string):
+    """
+    Original Source:  https://github.com/yoonkim/CNN_sentence/blob/master/process_data.py
+    :param string: Str
+    :return -> Str
+    """
+    string = string.strip().strip('"')
+    string = re.sub(r"[^A-Za-z(),!?\.\'\`]", " ", string)
+    string = re.sub(r"\'s", " \'s", string)
+    string = re.sub(r"\'ve", " \'ve", string)
+    string = re.sub(r"n\'t", " n\'t", string)
+    string = re.sub(r"\'re", " \'re", string)
+    string = re.sub(r"\'d", " \'d", string)
+    string = re.sub(r"\'ll", " \'ll", string)
+    string = re.sub(r",", " , ", string)
+    string = re.sub(r"\.", " \. ", string)
+    string = re.sub(r"\"", " , ", string)
+    string = re.sub(r"!", " ! ", string)
+    string = re.sub(r"\(", " \( ", string)
+    string = re.sub(r"\)", " \) ", string)
+    string = re.sub(r"\?", " \? ", string)
+    string = re.sub(r"\s{2,}", " ", string)
+    return string.strip().lower()
+
+
+def preprocess_line(sample):
+    """
+    :param sample: Str, "The sample would be tokenized and filtered according to the stopwords list"
+    :return: token_list -> List[Str]
+    """
+    sample = clean_str(sample.lstrip().rstrip())
+    token_list = clean_stopwords(sample.split(' '))
+    return {'token': token_list, 'label': []}
+
+
+
+def predict(line):
+    preprocessed_line = preprocess_line(line)
+    sample  = {}
+    sample["token"] = [v2i.get(v.lower(), v2i['<OOV>']) for v in preprocessed_line['token']]
+    sample["token_len"] = len(sample['token'])
+    sample["token"] = torch.tensor(sample["token"])
+    sample["token_len"] = torch.tensor(sample["token_len"])
+    output_logits = model(next(iter(DataLoader(CustomImageDataset([sample])))))
+    output_probs = torch.sigmoid(output_logits).cpu().tolist()
+    return {i2v_lab[i]:p for i, p in enumerate(output_probs[0]) if p > P_THRESHOLD}
+
+iface = gr.Interface(fn=predict, inputs="text", outputs=gr.Label(num_top_classes=5))
+iface.launch()

requirements.txt

@@ -0,0 +1,2 @@
+gradio
+torch