Upload 4 files

app.py

@@ -0,0 +1,125 @@
+import random
+
+import onnxruntime
+import pandas as pd
+import plotly.express as px
+import streamlit as st
+import torch
+from lang_map import langs
+from PIL import Image
+from transformers import AutoTokenizer, CLIPProcessor
+
+st.set_page_config(layout="wide")
+
+options = list(langs.keys())
+
+
+class SessionState:
+    def __init__(self, **kwargs):
+        for key, val in kwargs.items():
+            setattr(self, key, val)
+
+
+def get_state(**kwargs):
+    if "session_state" not in st.session_state:
+        st.session_state["session_state"] = SessionState(**kwargs)
+    return st.session_state["session_state"]
+
+
+def add_selectbox_and_input(key):
+    col1, col2 = st.columns(2)
+    with col1:
+        select = st.selectbox("Select a language", options, key=f"{key}_select")
+    with col2:
+        user_input = st.text_input("Input text", key=f"{key}_text")
+
+    state.inputs[key] = (select, user_input)
+
+
+state = get_state(count=1, inputs={})
+
+st.title("Zero-shot image classification with CLIP in 201 languages")
+
+col1, col2 = st.columns(2)
+
+image: Image.Image = None
+with col1:
+    st.subheader("Image")
+    uploaded_file = st.file_uploader("Choose an image", type=["png", "jpg", "jpeg"])
+    if uploaded_file is not None:
+        image = Image.open(uploaded_file)
+        st.image(image, caption="Uploaded Image.", use_column_width=True)
+
+
+def process():
+    session_options = onnxruntime.SessionOptions()
+    session_options.graph_optimization_level = (
+        onnxruntime.GraphOptimizationLevel.ORT_ENABLE_ALL
+    )
+    onnx_path = "model-quant.onnx"
+    ort_session = onnxruntime.InferenceSession(onnx_path, session_options)
+
+    processor = CLIPProcessor.from_pretrained(
+        "openai/clip-vit-base-patch32"
+    ).image_processor
+
+    tokenizer = AutoTokenizer.from_pretrained("facebook/nllb-200-distilled-600M")
+
+    image_inputs = processor(images=image, return_tensors="pt")
+
+    classes = []
+    languages = []
+    for key, value in state.inputs.items():
+        languages.append(str(value[0]))
+        classes.append(str(value[1]))
+
+    languages = [langs[lang] for lang in languages]
+
+    input_ids = []
+    attention_mask = []
+    for i, _ in enumerate(languages):
+        tokenizer.set_src_lang_special_tokens(languages[i])
+        input = tokenizer.batch_encode_plus(
+            [classes[i]],
+            return_tensors="pt",
+            padding="max_length",
+            truncation=True,
+            max_length=100,
+        )
+        input_ids.append(input["input_ids"])
+        attention_mask.append(input["attention_mask"])
+    input_ids = torch.concat(input_ids, dim=0)
+    attention_mask = torch.concat(attention_mask, dim=0)
+
+    ort_inputs = {
+        "pixel_values": image_inputs["pixel_values"].numpy(),
+        "input_ids": input_ids.numpy(),
+        "attention_mask": attention_mask.numpy(),
+    }
+    ort_outputs = ort_session.run(None, ort_inputs)
+    logits = torch.tensor(ort_outputs[0])
+    probabilities = logits.softmax(dim=-1).squeeze().detach().numpy()
+
+    chart_data = pd.DataFrame({"Class": classes, "Probability": probabilities})
+    chart_data = chart_data.sort_values(by=["Probability"], ascending=True)
+    fig = px.bar(chart_data, x="Probability", y="Class", orientation="h")
+    with col2:
+        st.subheader("Predictions")
+        st.write(fig)
+
+
+with col2:
+    st.subheader("Classes")
+    add_selectbox_and_input("Input 1")
+
+    for i in range(2, state.count + 1):
+        add_selectbox_and_input(f"Input {i}")
+
+    if st.button("Add class"):
+        state.count += 1
+        add_selectbox_and_input(f"Input {state.count}")
+
+    st.markdown("""---""")
+    if st.button("Generate"):
+        with st.spinner("Processing the data"):
+            process()

lang_map.py

@@ -0,0 +1,203 @@
+langs = {
+    "Acehnese (Arabic script)": "ace_Arab",
+    "Acehnese (Latin script)": "ace_Latn",
+    "Mesopotamian Arabic": "acm_Arab",
+    "Ta'izzi-Adeni Arabic": "acq_Arab",
+    "Tunisian Arabic": "aeb_Arab",
+    "Afrikaans": "afr_Latn",
+    "South Levantine Arabic": "ajp_Arab",
+    "Akan": "aka_Latn",
+    "Amharic": "amh_Ethi",
+    "North Levantine Arabic": "apc_Arab",
+    "Modern Standard Arabic": "arb_Arab",
+    "Najdi Arabic": "ars_Arab",
+    "Moroccan Arabic": "ary_Arab",
+    "Egyptian Arabic": "arz_Arab",
+    "Assamese": "asm_Beng",
+    "Asturian": "ast_Latn",
+    "Awadhi": "awa_Deva",
+    "Central Aymara": "ayr_Latn",
+    "South Azerbaijani": "azb_Arab",
+    "North Azerbaijani": "azj_Latn",
+    "Bashkir": "bak_Cyrl",
+    "Bambara": "bam_Latn",
+    "Balinese": "ban_Latn",
+    "Belarusian": "bel_Cyrl",
+    "Bemba": "bem_Latn",
+    "Bengali": "ben_Beng",
+    "Bhojpuri": "bho_Deva",
+    "Banjar (Arabic script)": "bjn_Arab",
+    "Banjar (Latin script)": "bjn_Latn",
+    "Standard Tibetan": "bod_Tibt",
+    "Bosnian": "bos_Latn",
+    "Buginese": "bug_Latn",
+    "Bulgarian": "bul_Cyrl",
+    "Catalan": "cat_Latn",
+    "Cebuano": "ceb_Latn",
+    "Czech": "ces_Latn",
+    "Chokwe": "cjk_Latn",
+    "Central Kurdish": "ckb_Arab",
+    "Crimean Tatar": "crh_Latn",
+    "Welsh": "cym_Latn",
+    "Danish": "dan_Latn",
+    "German": "deu_Latn",
+    "Southwestern Dinka": "dik_Latn",
+    "Dyula": "dyu_Latn",
+    "Dzongkha": "dzo_Tibt",
+    "Greek": "ell_Grek",
+    "English": "eng_Latn",
+    "Esperanto": "epo_Latn",
+    "Estonian": "est_Latn",
+    "Basque": "eus_Latn",
+    "Ewe": "ewe_Latn",
+    "Faroese": "fao_Latn",
+    "Fijian": "fij_Latn",
+    "Finnish": "fin_Latn",
+    "Fon": "fon_Latn",
+    "French": "fra_Latn",
+    "Friulian": "fur_Latn",
+    "Nigerian Fulfulde": "fuv_Latn",
+    "Scottish Gaelic": "gla_Latn",
+    "Irish": "gle_Latn",
+    "Galician": "glg_Latn",
+    "Guarani": "grn_Latn",
+    "Gujarati": "guj_Gujr",
+    "Haitian Creole": "hat_Latn",
+    "Hausa": "hau_Latn",
+    "Hebrew": "heb_Hebr",
+    "Hindi": "hin_Deva",
+    "Chhattisgarhi": "hne_Deva",
+    "Croatian": "hrv_Latn",
+    "Hungarian": "hun_Latn",
+    "Armenian": "hye_Armn",
+    "Igbo": "ibo_Latn",
+    "Ilocano": "ilo_Latn",
+    "Indonesian": "ind_Latn",
+    "Icelandic": "isl_Latn",
+    "Italian": "ita_Latn",
+    "Javanese": "jav_Latn",
+    "Japanese": "jpn_Jpan",
+    "Kabyle": "kab_Latn",
+    "Jingpho": "kac_Latn",
+    "Kamba": "kam_Latn",
+    "Kannada": "kan_Knda",
+    "Kashmiri (Arabic script)": "kas_Arab",
+    "Kashmiri (Devanagari script)": "kas_Deva",
+    "Georgian": "kat_Geor",
+    "Central Kanuri (Arabic script)": "knc_Arab",
+    "Central Kanuri (Latin script)": "knc_Latn",
+    "Kazakh": "kaz_Cyrl",
+    "Kabiyè": "kbp_Latn",
+    "Kabuverdianu": "kea_Latn",
+    "Khmer": "khm_Khmr",
+    "Kikuyu": "kik_Latn",
+    "Kinyarwanda": "kin_Latn",
+    "Kyrgyz": "kir_Cyrl",
+    "Kimbundu": "kmb_Latn",
+    "Northern Kurdish": "kmr_Latn",
+    "Kikongo": "kon_Latn",
+    "Korean": "kor_Hang",
+    "Lao": "lao_Laoo",
+    "Ligurian": "lij_Latn",
+    "Limburgish": "lim_Latn",
+    "Lingala": "lin_Latn",
+    "Lithuanian": "lit_Latn",
+    "Lombard": "lmo_Latn",
+    "Latgalian": "ltg_Latn",
+    "Luxembourgish": "ltz_Latn",
+    "Luba-Kasai": "lua_Latn",
+    "Ganda": "lug_Latn",
+    "Luo": "luo_Latn",
+    "Mizo": "lus_Latn",
+    "Standard Latvian": "lvs_Latn",
+    "Magahi": "mag_Deva",
+    "Maithili": "mai_Deva",
+    "Malayalam": "mal_Mlym",
+    "Marathi": "mar_Deva",
+    "Minangkabau (Latin script)": "min_Latn",
+    "Macedonian": "mkd_Cyrl",
+    "Plateau Malagasy": "plt_Latn",
+    "Maltese": "mlt_Latn",
+    "Meitei (Bengali script)": "mni_Beng",
+    "Halh Mongolian": "khk_Cyrl",
+    "Mossi": "mos_Latn",
+    "Maori": "mri_Latn",
+    "Burmese": "mya_Mymr",
+    "Dutch": "nld_Latn",
+    "Norwegian Nynorsk": "nno_Latn",
+    "Norwegian Bokmål": "nob_Latn",
+    "Nepali": "npi_Deva",
+    "Northern Sotho": "nso_Latn",
+    "Nuer": "nus_Latn",
+    "Nyanja": "nya_Latn",
+    "Occitan": "oci_Latn",
+    "West Central Oromo": "gaz_Latn",
+    "Odia": "ory_Orya",
+    "Pangasinan": "pag_Latn",
+    "Eastern Panjabi": "pan_Guru",
+    "Papiamento": "pap_Latn",
+    "Western Persian": "pes_Arab",
+    "Polish": "pol_Latn",
+    "Portuguese": "por_Latn",
+    "Dari": "prs_Arab",
+    "Southern Pashto": "pbt_Arab",
+    "Ayacucho Quechua": "quy_Latn",
+    "Romanian": "ron_Latn",
+    "Rundi": "run_Latn",
+    "Russian": "rus_Cyrl",
+    "Sango": "sag_Latn",
+    "Sanskrit": "san_Deva",
+    "Sicilian": "scn_Latn",
+    "Shan": "shn_Mymr",
+    "Sinhala": "sin_Sinh",
+    "Slovak": "slk_Latn",
+    "Slovenian": "slv_Latn",
+    "Samoan": "smo_Latn",
+    "Shona": "sna_Latn",
+    "Sindhi": "snd_Arab",
+    "Somali": "som_Latn",
+    "Southern Sotho": "sot_Latn",
+    "Spanish": "spa_Latn",
+    "Tosk Albanian": "als_Latn",
+    "Sardinian": "srd_Latn",
+    "Serbian": "srp_Cyrl",
+    "Swati": "ssw_Latn",
+    "Sundanese": "sun_Latn",
+    "Swedish": "swe_Latn",
+    "Swahili": "swh_Latn",
+    "Silesian": "szl_Latn",
+    "Tamil": "tam_Taml",
+    "Tatar": "tat_Cyrl",
+    "Telugu": "tel_Telu",
+    "Tajik": "tgk_Cyrl",
+    "Tagalog": "tgl_Latn",
+    "Thai": "tha_Thai",
+    "Tigrinya": "tir_Ethi",
+    "Tamasheq (Latin script)": "taq_Latn",
+    "Tamasheq (Tifinagh script)": "taq_Tfng",
+    "Tok Pisin": "tpi_Latn",
+    "Tswana": "tsn_Latn",
+    "Tsonga": "tso_Latn",
+    "Turkmen": "tuk_Latn",
+    "Tumbuka": "tum_Latn",
+    "Turkish": "tur_Latn",
+    "Twi": "twi_Latn",
+    "Central Atlas Tamazight": "tzm_Tfng",
+    "Uyghur": "uig_Arab",
+    "Ukrainian": "ukr_Cyrl",
+    "Umbundu": "umb_Latn",
+    "Urdu": "urd_Arab",
+    "Northern Uzbek": "uzn_Latn",
+    "Venetian": "vec_Latn",
+    "Vietnamese": "vie_Latn",
+    "Waray": "war_Latn",
+    "Wolof": "wol_Latn",
+    "Xhosa": "xho_Latn",
+    "Eastern Yiddish": "ydd_Hebr",
+    "Yoruba": "yor_Latn",
+    "Yue Chinese": "yue_Hant",
+    "Chinese (Simplified)": "zho_Hans",
+    "Chinese (Traditional)": "zho_Hant",
+    "Standard Malay": "zsm_Latn",
+    "Zulu": "zul_Latn",
+}

model-quant.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e480324809ba9e7ba30e3a804f7a8d98ec445855abe11cded716abcd956c554
+size 504902375

requirements.txt

@@ -0,0 +1,6 @@
+streamlit
+plotly
+pandas
+onnx
+onnxruntime
+transformers