Duplicate from vincentclaes/emoji-tagging

Co-authored-by: claes <vincentclaes@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,31 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

Makefile

@@ -0,0 +1,3 @@
+install:
+	poetry install
+	poetry run pip list --format=freeze > requirements.txt

README.md

@@ -0,0 +1,20 @@
+---
+title: Emoji Tagging
+emoji: 😇
+colorFrom: Blue
+colorTo: indigo
+sdk: gradio
+sdk_version: 3.3.1
+app_file: app.py
+pinned: false
+license: apache-2.0
+duplicated_from: vincentclaes/emoji-tagging
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+
+# Emoji Tagging
+
+```bash
+make setup
+```

adjectives.txt

@@ -0,0 +1,228 @@
+adorable
+adventurous
+aggressive
+agreeable
+alert
+alive
+amused
+angry
+annoyed
+annoying
+anxious
+arrogant
+ashamed
+attractive
+average
+awful
+bad
+beautiful
+better
+bewildered
+black
+bloody
+blue
+blue-eyed
+blushing
+bored
+brainy
+brave
+breakable
+bright
+busy
+calm
+careful
+cautious
+charming
+cheerful
+clean
+clear
+clever
+cloudy
+clumsy
+colorful
+combative
+comfortable
+concerned
+condemned
+confused
+cooperative
+courageous
+crazy
+creepy
+crowded
+cruel
+curious
+cute
+dangerous
+dark
+dead
+defeated
+defiant
+delightful
+depressed
+determined
+different
+difficult
+disgusted
+distinct
+disturbed
+dizzy
+doubtful
+drab
+dull
+eager
+easy
+elated
+elegant
+embarrassed
+enchanting
+encouraging
+energetic
+enthusiastic
+envious
+evil
+excited
+expensive
+exuberant
+fair
+faithful
+famous
+fancy
+fantastic
+fierce
+filthy
+fine
+foolish
+fragile
+frail
+frantic
+friendly
+frightened
+funny
+gentle
+gifted
+glamorous
+gleaming
+glorious
+good
+gorgeous
+graceful
+grieving
+grotesque
+grumpy
+handsome
+happy
+healthy
+helpful
+helpless
+hilarious
+homeless
+homely
+horrible
+hungry
+hurt
+ill
+important
+impossible
+inexpensive
+innocent
+inquisitive
+itchy
+jealous
+jittery
+jolly
+joyous
+kind
+lazy
+light
+lively
+lonely
+long
+lovely
+lucky
+magnificent
+misty
+modern
+motionless
+muddy
+mushy
+mysterious
+nasty
+naughty
+nervous
+nice
+nutty
+obedient
+obnoxious
+odd
+old-fashioned
+open
+outrageous
+outstanding
+panicky
+perfect
+plain
+pleasant
+poised
+poor
+powerful
+precious
+prickly
+proud
+putrid
+puzzled
+quaint
+real
+relieved
+repulsive
+rich
+scary
+selfish
+shiny
+shy
+silly
+sleepy
+smiling
+smoggy
+sore
+sparkling
+splendid
+spotless
+stormy
+strange
+stupid
+successful
+super
+talented
+tame
+tasty
+tender
+tense
+terrible
+thankful
+thoughtful
+thoughtless
+tired
+tough
+troubled
+ugliest
+ugly
+uninterested
+unsightly
+unusual
+upset
+uptight
+vast
+victorious
+vivacious
+wandering
+weary
+wicked
+wide-eyed
+wild
+witty
+worried
+worrisome
+wrong
+zany
+zealous

app.py

@@ -0,0 +1,76 @@
+import os
+
+import torch
+import boto3
+
+import gradio as gr
+import pandas as pd
+
+from transformers import CLIPProcessor, CLIPModel
+
+checkpoint = "vincentclaes/emoji-predictor"
+adjectives = pd.read_table("./adjectives.txt", header=None)[0].to_list()
+K = 10
+THRESHOLD = 0.05
+APP_NAME = "emoji-tagging"
+BUCKET = "drift-pilot-ml-model"
+
+processor = CLIPProcessor.from_pretrained(checkpoint)
+model = CLIPModel.from_pretrained(checkpoint)
+
+
+def log_inference():
+    if os.environ["CLIENT"]:
+        boto3.client("s3").put_object(
+            Body=more_binary_data,
+            Bucket=BUCKET,
+            Key=f"${APP_NAME}/",
+        )
+
+
+def get_tag(emoji, tags="", expected="", model=model, processor=processor, K=K):
+    if tags:
+        tags = tags.strip().split(",")
+    else:
+        tags = adjectives
+    inputs = processor(
+        text=tags, images=emoji, return_tensors="pt", padding=True, truncation=True
+    )
+    outputs = model(**inputs)
+
+    # we take the softmax to get the label probabilities
+    probs = outputs.logits_per_text.softmax(dim=0)
+    probs_formatted = torch.tensor([prob[0] for prob in probs])
+    values, indices = probs_formatted.topk(K)
+    return "Tag (confidence): " + ", ".join(
+        [f"{tags[i]} ({round(v.item(), 2)})" for v, i in zip(values, indices) if v >= THRESHOLD]
+    )
+
+
+title = "Tagging an Emoji"
+description = """You provide an Emoji and our few-shot fine tuned CLIP model will suggest some tags that are appropriate.\n
+
+- We use the [228 most common adjectives in english](https://grammar.yourdictionary.com/parts-of-speech/adjectives/list-of-adjective-words.html).\n
+- We show max 10 tags and only when the confidence is higher than 5% (0.05)
+
+"""
+
+examples = [[f"emojis/{i}.png"] for i in range(32)]
+
+text = gr.inputs.Textbox(
+    placeholder="Enter a text and we will try to predict an emoji..."
+)
+app = gr.Interface(
+    fn=get_tag,
+    inputs=[
+        gr.components.Image(type="pil", label="emoji"),
+    ],
+    outputs=gr.Textbox(),
+    examples=examples,
+    examples_per_page=32,
+    title=title,
+    description=description,
+)
+
+if __name__ == "__main__":
+    app.launch()

pyproject.toml

@@ -0,0 +1,22 @@
+[tool.poetry]
+name = "emoji-tagging"
+version = "0.1.0"
+description = ""
+authors = ["Vincent Claes <vincent.v.claes@gmail.com>"]
+readme = "README.md"
+
+[tool.poetry.dependencies]
+python = "^3.10"
+torch = "^1.12.1"
+transformers = "^4.22.2"
+gradio = "^3.4.1"
+boto3 = "^1.24.89"
+
+
+
+[tool.poetry.group.dev.dependencies]
+black = "^22.10.0"
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"

requirements.txt

@@ -0,0 +1,79 @@
+aiohttp==3.8.3
+aiosignal==1.2.0
+anyio==3.6.1
+async-timeout==4.0.2
+attrs==22.1.0
+bcrypt==4.0.0
+black==22.10.0
+boto3==1.24.89
+botocore==1.27.89
+certifi==2022.9.24
+cffi==1.15.1
+charset-normalizer==2.1.1
+click==8.1.3
+contourpy==1.0.5
+cryptography==38.0.1
+cycler==0.11.0
+fastapi==0.85.0
+ffmpy==0.3.0
+filelock==3.8.0
+fonttools==4.37.4
+frozenlist==1.3.1
+fsspec==2022.8.2
+gradio==3.4.1
+h11==0.12.0
+httpcore==0.15.0
+httpx==0.23.0
+huggingface-hub==0.10.0
+idna==3.4
+Jinja2==3.1.2
+jmespath==1.0.1
+kiwisolver==1.4.4
+linkify-it-py==1.0.3
+markdown-it-py==2.1.0
+MarkupSafe==2.1.1
+matplotlib==3.6.1
+mdit-py-plugins==0.3.1
+mdurl==0.1.2
+multidict==6.0.2
+mypy-extensions==0.4.3
+numpy==1.23.3
+orjson==3.8.0
+packaging==21.3
+pandas==1.5.0
+paramiko==2.11.0
+pathspec==0.10.1
+Pillow==9.2.0
+pip==22.0.4
+platformdirs==2.5.2
+pycparser==2.21
+pycryptodome==3.15.0
+pydantic==1.10.2
+pydub==0.25.1
+PyNaCl==1.5.0
+pyparsing==3.0.9
+python-dateutil==2.8.2
+python-multipart==0.0.5
+pytz==2022.4
+PyYAML==6.0
+regex==2022.9.13
+requests==2.28.1
+rfc3986==1.5.0
+s3transfer==0.6.0
+setuptools==65.4.1
+setuptools-scm==7.0.5
+six==1.16.0
+sniffio==1.3.0
+starlette==0.20.4
+tokenizers==0.12.1
+tomli==2.0.1
+torch==1.12.1
+tqdm==4.64.1
+transformers==4.22.2
+typing_extensions==4.4.0
+uc-micro-py==1.0.1
+urllib3==1.26.12
+uvicorn==0.18.3
+websockets==10.3
+wheel==0.37.1
+yarl==1.8.1