Add application file

Dockerfile

@@ -0,0 +1,31 @@
+FROM python:3.11-slim
+
+ENV PYTHONDONTWRITEBYTECODE=1 \
+    PYTHONUNBUFFERED=1 \
+    PIP_NO_CACHE_DIR=1 \
+    PORT=7860 \
+    HF_HOME=/home/user/.cache/huggingface \
+    TORCH_HOME=/home/user/.cache/torch \
+    OMP_NUM_THREADS=1 \
+    MKL_NUM_THREADS=1
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    ca-certificates \
+    libgomp1 \
+ && rm -rf /var/lib/apt/lists/*
+
+RUN useradd -m -u 1000 user
+USER user
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:$PATH
+
+WORKDIR $HOME/app
+
+COPY --chown=user:user requirements.txt .
+RUN pip install --upgrade pip && pip install -r requirements.txt
+
+COPY --chown=user:user . .
+
+EXPOSE 7860
+
+CMD ["sh", "-c", "uvicorn app:app --host 0.0.0.0 --port ${PORT:-7860} --workers 1"]

app.py

@@ -0,0 +1,441 @@
+# app.py
+import io
+import uuid
+import json
+import threading
+import hashlib
+from contextvars import ContextVar
+from typing import Optional, Dict, Any
+
+import torch
+import torch.nn.functional as F
+import timm
+from PIL import Image
+
+from fastapi import FastAPI, UploadFile, File, Query, HTTPException
+from fastapi.middleware.cors import CORSMiddleware
+from fastapi.responses import JSONResponse
+
+from timm.layers.pos_embed import resample_abs_pos_embed
+try:
+    from timm.layers.patch_embed import resample_patch_embed
+except Exception:
+    resample_patch_embed = None
+
+
+# -----------------------
+# Config
+# -----------------------
+MODEL_NAME = "flexivit_large.300ep_in1k"
+TARGET_IMG = 96
+TARGET_PATCH = 32
+NEW_GRID = (TARGET_IMG // TARGET_PATCH, TARGET_IMG // TARGET_PATCH)  # (3,3)
+
+DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
+
+# ImageNet normalization
+IMNET_MEAN = torch.tensor([0.485, 0.456, 0.406]).view(3, 1, 1)
+IMNET_STD  = torch.tensor([0.229, 0.224, 0.225]).view(3, 1, 1)
+
+
+# -----------------------
+# Load labels (local file recommended)
+# -----------------------
+def load_imagenet_labels(path="imagenet_classes.txt"):
+    try:
+        with open(path, "r", encoding="utf-8") as f:
+            return [line.strip() for line in f.readlines() if line.strip()]
+    except FileNotFoundError:
+        # If missing, still works but without names.
+        return None
+
+IMAGENET_LABELS = load_imagenet_labels()
+
+
+# -----------------------
+# Build & adapt model once
+# -----------------------
+def adapt_flexivit_to_3x3(model: torch.nn.Module):
+    # --- Resize patch embedding conv weight ---
+    with torch.no_grad():
+        proj = model.patch_embed.proj
+        w = proj.weight.detach().cpu()  # [embed_dim, in_chans, old_ps, old_ps]
+        b = proj.bias.detach().cpu() if proj.bias is not None else None
+        old_ps = w.shape[-1]
+
+        if old_ps != TARGET_PATCH:
+            if resample_patch_embed is not None:
+                w2 = resample_patch_embed(w, (TARGET_PATCH, TARGET_PATCH))
+            else:
+                ed, ic, _, _ = w.shape
+                w_ = w.reshape(ed * ic, 1, old_ps, old_ps)
+                w_ = F.interpolate(w_, size=(TARGET_PATCH, TARGET_PATCH), mode="bicubic", align_corners=False)
+                w2 = w_.reshape(ed, ic, TARGET_PATCH, TARGET_PATCH)
+        else:
+            w2 = w
+
+        embed_dim, in_chans, _, _ = w2.shape
+        new_proj = torch.nn.Conv2d(
+            in_channels=in_chans,
+            out_channels=embed_dim,
+            kernel_size=TARGET_PATCH,
+            stride=TARGET_PATCH,
+            padding=0,
+            bias=(b is not None),
+        )
+        new_proj.weight.copy_(w2)
+        if b is not None:
+            new_proj.bias.copy_(b)
+
+        model.patch_embed.proj = new_proj.to(DEVICE)
+
+        # Update patch embed metadata if present
+        if hasattr(model.patch_embed, "patch_size"):
+            model.patch_embed.patch_size = (TARGET_PATCH, TARGET_PATCH)
+        if hasattr(model.patch_embed, "img_size"):
+            model.patch_embed.img_size = (TARGET_IMG, TARGET_IMG)
+        if hasattr(model.patch_embed, "grid_size"):
+            model.patch_embed.grid_size = NEW_GRID
+        if hasattr(model.patch_embed, "num_patches"):
+            model.patch_embed.num_patches = NEW_GRID[0] * NEW_GRID[1]
+
+    # --- Resize absolute positional embeddings to 3x3 ---
+    if hasattr(model, "pos_embed") and model.pos_embed is not None:
+        with torch.no_grad():
+            pe = model.pos_embed.detach()
+
+            # infer prefix tokens (cls, dist, etc.)
+            prefix = int(getattr(model, "num_prefix_tokens", 0))
+            if prefix == 0 and hasattr(model, "cls_token") and model.cls_token is not None:
+                prefix = 1
+
+            # infer old grid
+            old_grid = None
+            if hasattr(model, "patch_embed") and hasattr(model.patch_embed, "grid_size"):
+                old_grid = tuple(model.patch_embed.grid_size)
+
+            if old_grid is not None:
+                grid_tokens = old_grid[0] * old_grid[1]
+                if pe.shape[1] == grid_tokens:
+                    prefix = 0
+                elif pe.shape[1] == grid_tokens + prefix:
+                    pass
+                else:
+                    prefix = 0
+                    old_grid = None
+
+            if old_grid is None:
+                n = pe.shape[1] - prefix
+                g = int(n ** 0.5)
+                old_grid = (g, g)
+
+            pe2 = resample_abs_pos_embed(
+                pe,
+                new_size=NEW_GRID,
+                old_size=old_grid,
+                num_prefix_tokens=prefix,
+                interpolation="bicubic",
+                antialias=True,
+            )
+            model.pos_embed = torch.nn.Parameter(pe2)
+
+    return model
+
+
+def build_model():
+    model = timm.create_model(MODEL_NAME, pretrained=True).to(DEVICE).eval()
+
+    # (Recommended) disable fused attention if present (helps hooks)
+    for blk in model.blocks:
+        if hasattr(blk.attn, "fused_attn"):
+            blk.attn.fused_attn = False
+
+    model = adapt_flexivit_to_3x3(model)
+    return model
+
+
+MODEL = build_model()
+print(f"[server] model={MODEL_NAME} device={DEVICE} grid={NEW_GRID}")
+
+
+# -----------------------
+# Hooks using ContextVar (safe-ish for concurrent requests)
+# -----------------------
+_attn_var: ContextVar[Optional[list]] = ContextVar("_attn_var", default=None)
+_tok_var: ContextVar[Optional[list]] = ContextVar("_tok_var", default=None)
+
+def _save_attn_drop_input(module, inp, out):
+    lst = _attn_var.get()
+    if lst is not None and len(inp) > 0 and torch.is_tensor(inp[0]):
+        # inp[0]: [B, H, N, N]
+        lst.append(inp[0].detach().cpu())
+
+def _save_block_out(module, inp, out):
+    lst = _tok_var.get()
+    if lst is not None and torch.is_tensor(out):
+        # out: [B, N, D]
+        lst.append(out.detach())
+
+
+# Register hooks once
+ATTN_HOOKS = []
+TOK_HOOKS = []
+for blk in MODEL.blocks:
+    ATTN_HOOKS.append(blk.attn.attn_drop.register_forward_hook(_save_attn_drop_input))
+    TOK_HOOKS.append(blk.register_forward_hook(_save_block_out))
+
+
+# -----------------------
+# Preprocess
+# -----------------------
+def preprocess(pil_img: Image.Image) -> torch.Tensor:
+    img = pil_img.convert("RGB")
+    w, h = img.size
+    s = min(w, h)
+    left = (w - s) // 2
+    top = (h - s) // 2
+    img = img.crop((left, top, left + s, top + s)).resize((TARGET_IMG, TARGET_IMG), Image.BICUBIC)
+
+    x = torch.from_numpy(
+        (torch.ByteTensor(torch.ByteStorage.from_buffer(img.tobytes()))
+         .view(TARGET_IMG, TARGET_IMG, 3).numpy()).astype("float32") / 255.0
+    )
+    x = x.permute(2, 0, 1)  # CHW
+    x = (x - IMNET_MEAN) / IMNET_STD
+    return x.unsqueeze(0)   # [1,3,H,W]
+
+
+# -----------------------
+# Compute logit lens + attention export
+# -----------------------
+def compute_logit_lens_from_tokens(tokens_per_layer, model):
+    logits_list = []
+    probs_list = []
+    with torch.no_grad():
+        for x_l in tokens_per_layer:
+            x_ln = model.norm(x_l) if hasattr(model, "norm") and model.norm is not None else x_l
+            cls_l = x_ln[:, 0]  # CLS token
+            logits_l = model.head(cls_l)
+            logits_list.append(logits_l.detach().cpu())
+            probs_list.append(torch.softmax(logits_l, dim=-1).detach().cpu())
+
+    logits_per_layer = torch.stack(logits_list, dim=0)  # [L,B,C]
+    probs_per_layer  = torch.stack(probs_list,  dim=0)
+    return logits_per_layer, probs_per_layer
+
+
+def round_tensor(t: torch.Tensor, decimals: int):
+    s = 10 ** decimals
+    return torch.round(t * s) / s
+
+
+MODEL_LOCK = threading.Lock()
+
+def analyze_image(pil_img: Image.Image) -> Dict[str, Any]:
+    x = preprocess(pil_img).to(DEVICE)
+
+    # Per-request storage
+    attn_maps = []
+    layer_tokens = []
+    tok_token = _tok_var.set(layer_tokens)
+    attn_token = _attn_var.set(attn_maps)
+
+    try:
+        with torch.no_grad():
+            # Lock recommended if you run multiple workers/threads with GPU,
+            # and because we use shared model + hooks
+            with MODEL_LOCK:
+                logits_final = MODEL(x)
+
+        # Final probs
+        probs_final = torch.softmax(logits_final, dim=-1)[0].detach().cpu()
+        probs_final = round_tensor(probs_final, 6)
+
+        # Logit lens
+        logits_by_layer, probs_by_layer = compute_logit_lens_from_tokens(layer_tokens, MODEL)
+
+        # Export logit lens json
+        export_logit = {
+            "model": MODEL_NAME,
+            "grid": [NEW_GRID[0], NEW_GRID[1]],
+            "num_layers": int(logits_by_layer.shape[0]),
+            "num_classes": int(logits_by_layer.shape[-1]),
+            "class_names": IMAGENET_LABELS,
+            "logits": [],
+            "final_probs": probs_final.tolist()
+        }
+        for l in range(logits_by_layer.shape[0]):
+            v = logits_by_layer[l, 0]  # [C]
+            v = round_tensor(v, 3)
+            export_logit["logits"].append(v.tolist())
+
+        # Attention json
+        # attn_maps is list length L, each: [B,H,N,N] CPU
+        attn_maps2 = [a.squeeze(0) for a in attn_maps]  # -> [H,N,N]
+        if len(attn_maps2) == 0:
+            raise RuntimeError("No attention captured. (Hook may not match this timm model/config)")
+
+        attn_serializable = []
+        for layer in attn_maps2:
+            layer_data = []
+            for head in layer:
+                head = round_tensor(head, 4)
+                layer_data.append(head.tolist())
+            attn_serializable.append(layer_data)
+
+        export_attn = {
+            "num_layers": len(attn_serializable),
+            "num_heads": len(attn_serializable[0]),
+            "num_tokens": len(attn_serializable[0][0]),
+            "grid": [NEW_GRID[0], NEW_GRID[1]],
+            "attention": attn_serializable
+        }
+
+        return {
+            "logit_lens_full": export_logit,
+            "attention_full": export_attn
+        }
+
+    finally:
+        _tok_var.reset(tok_token)
+        _attn_var.reset(attn_token)
+        layer_tokens.clear()
+        attn_maps.clear()
+
+
+# -----------------------
+# FastAPI app
+# -----------------------
+app = FastAPI(title="ViT Explainer API", version="1.0")
+
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],  # tighten in prod
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+# In-memory store for "file-like endpoints" (job-based)
+RESULTS: Dict[str, Dict[str, Any]] = {}
+
+# In-memory store for "current files" (no-regenerate on GET)
+CURRENT: Dict[str, Any] = {
+    "hash": None,
+    "attention_full": None,
+    "logit_lens_full": None,
+}
+
+def _no_store(resp: JSONResponse) -> JSONResponse:
+    resp.headers["Cache-Control"] = "no-store, no-cache, must-revalidate, max-age=0"
+    resp.headers["Pragma"] = "no-cache"
+    return resp
+
+
+@app.get("/health")
+def health():
+    return {
+        "status": "ok",
+        "model": MODEL_NAME,
+        "device": DEVICE,
+        "grid": list(NEW_GRID),
+        "has_current": CURRENT["attention_full"] is not None,
+    }
+
+
+# -----------------------
+# Legacy: returns JSON directly OR job endpoints
+# -----------------------
+@app.post("/analyze")
+async def analyze(
+    file: UploadFile = File(...),
+    store: int = Query(0, description="1 => guarda resultados y entrega endpoints /results/{id}/..."),
+):
+    if not file.content_type or not file.content_type.startswith("image/"):
+        raise HTTPException(status_code=400, detail="Please upload an image file.")
+
+    raw = await file.read()
+    try:
+        img = Image.open(io.BytesIO(raw)).convert("RGB")
+    except Exception:
+        raise HTTPException(status_code=400, detail="Could not decode image.")
+
+    try:
+        out = analyze_image(img)
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"Model inference failed: {e}")
+
+    if store == 1:
+        job_id = str(uuid.uuid4())
+        RESULTS[job_id] = out
+        return {
+            "job_id": job_id,
+            "endpoints": {
+                "attention_full": f"/results/{job_id}/attention_full.json",
+                "logit_lens_full": f"/results/{job_id}/logit_lens_full.json",
+            }
+        }
+
+    return out
+
+
+@app.get("/results/{job_id}/attention_full.json")
+def get_attention(job_id: str):
+    if job_id not in RESULTS:
+        raise HTTPException(status_code=404, detail="job_id not found")
+    return _no_store(JSONResponse(RESULTS[job_id]["attention_full"]))
+
+
+@app.get("/results/{job_id}/logit_lens_full.json")
+def get_logit(job_id: str):
+    if job_id not in RESULTS:
+        raise HTTPException(status_code=404, detail="job_id not found")
+    return _no_store(JSONResponse(RESULTS[job_id]["logit_lens_full"]))
+
+
+# -----------------------
+# Preferred: "current files" endpoints (keep frontend fetch paths stable)
+#   - POST /analyze_current only when image changes
+#   - GET /attention_full.json and /logit_lens_full.json are just readers
+# -----------------------
+@app.post("/analyze_current")
+async def analyze_current(file: UploadFile = File(...)):
+    if not file.content_type or not file.content_type.startswith("image/"):
+        raise HTTPException(status_code=400, detail="Please upload an image file.")
+
+    raw = await file.read()
+    img_hash = hashlib.sha256(raw).hexdigest()
+
+    # ✅ no regenerate if same image already processed
+    if CURRENT["hash"] == img_hash and CURRENT["attention_full"] is not None:
+        return {"status": "unchanged", "hash": img_hash}
+
+    try:
+        img = Image.open(io.BytesIO(raw)).convert("RGB")
+    except Exception:
+        raise HTTPException(status_code=400, detail="Could not decode image.")
+
+    try:
+        out = analyze_image(img)
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"Model inference failed: {e}")
+
+    CURRENT["hash"] = img_hash
+    CURRENT["attention_full"] = out["attention_full"]
+    CURRENT["logit_lens_full"] = out["logit_lens_full"]
+
+    return {"status": "updated", "hash": img_hash}
+
+
+@app.get("/attention_full.json")
+def attention_full_current():
+    if CURRENT["attention_full"] is None:
+        raise HTTPException(status_code=404, detail="No attention computed yet. Call POST /analyze_current first.")
+    return _no_store(JSONResponse(CURRENT["attention_full"]))
+
+
+@app.get("/logit_lens_full.json")
+def logit_lens_current():
+    if CURRENT["logit_lens_full"] is None:
+        raise HTTPException(status_code=404, detail="No logit lens computed yet. Call POST /analyze_current first.")
+    return _no_store(JSONResponse(CURRENT["logit_lens_full"]))

imagenet_classes.txt

@@ -0,0 +1,1000 @@
+tench
+goldfish
+great white shark
+tiger shark
+hammerhead
+electric ray
+stingray
+cock
+hen
+ostrich
+brambling
+goldfinch
+house finch
+junco
+indigo bunting
+robin
+bulbul
+jay
+magpie
+chickadee
+water ouzel
+kite
+bald eagle
+vulture
+great grey owl
+European fire salamander
+common newt
+eft
+spotted salamander
+axolotl
+bullfrog
+tree frog
+tailed frog
+loggerhead
+leatherback turtle
+mud turtle
+terrapin
+box turtle
+banded gecko
+common iguana
+American chameleon
+whiptail
+agama
+frilled lizard
+alligator lizard
+Gila monster
+green lizard
+African chameleon
+Komodo dragon
+African crocodile
+American alligator
+triceratops
+thunder snake
+ringneck snake
+hognose snake
+green snake
+king snake
+garter snake
+water snake
+vine snake
+night snake
+boa constrictor
+rock python
+Indian cobra
+green mamba
+sea snake
+horned viper
+diamondback
+sidewinder
+trilobite
+harvestman
+scorpion
+black and gold garden spider
+barn spider
+garden spider
+black widow
+tarantula
+wolf spider
+tick
+centipede
+black grouse
+ptarmigan
+ruffed grouse
+prairie chicken
+peacock
+quail
+partridge
+African grey
+macaw
+sulphur-crested cockatoo
+lorikeet
+coucal
+bee eater
+hornbill
+hummingbird
+jacamar
+toucan
+drake
+red-breasted merganser
+goose
+black swan
+tusker
+echidna
+platypus
+wallaby
+koala
+wombat
+jellyfish
+sea anemone
+brain coral
+flatworm
+nematode
+conch
+snail
+slug
+sea slug
+chiton
+chambered nautilus
+Dungeness crab
+rock crab
+fiddler crab
+king crab
+American lobster
+spiny lobster
+crayfish
+hermit crab
+isopod
+white stork
+black stork
+spoonbill
+flamingo
+little blue heron
+American egret
+bittern
+crane
+limpkin
+European gallinule
+American coot
+bustard
+ruddy turnstone
+red-backed sandpiper
+redshank
+dowitcher
+oystercatcher
+pelican
+king penguin
+albatross
+grey whale
+killer whale
+dugong
+sea lion
+Chihuahua
+Japanese spaniel
+Maltese dog
+Pekinese
+Shih-Tzu
+Blenheim spaniel
+papillon
+toy terrier
+Rhodesian ridgeback
+Afghan hound
+basset
+beagle
+bloodhound
+bluetick
+black-and-tan coonhound
+Walker hound
+English foxhound
+redbone
+borzoi
+Irish wolfhound
+Italian greyhound
+whippet
+Ibizan hound
+Norwegian elkhound
+otterhound
+Saluki
+Scottish deerhound
+Weimaraner
+Staffordshire bullterrier
+American Staffordshire terrier
+Bedlington terrier
+Border terrier
+Kerry blue terrier
+Irish terrier
+Norfolk terrier
+Norwich terrier
+Yorkshire terrier
+wire-haired fox terrier
+Lakeland terrier
+Sealyham terrier
+Airedale
+cairn
+Australian terrier
+Dandie Dinmont
+Boston bull
+miniature schnauzer
+giant schnauzer
+standard schnauzer
+Scotch terrier
+Tibetan terrier
+silky terrier
+soft-coated wheaten terrier
+West Highland white terrier
+Lhasa
+flat-coated retriever
+curly-coated retriever
+golden retriever
+Labrador retriever
+Chesapeake Bay retriever
+German short-haired pointer
+vizsla
+English setter
+Irish setter
+Gordon setter
+Brittany spaniel
+clumber
+English springer
+Welsh springer spaniel
+cocker spaniel
+Sussex spaniel
+Irish water spaniel
+kuvasz
+schipperke
+groenendael
+malinois
+briard
+kelpie
+komondor
+Old English sheepdog
+Shetland sheepdog
+collie
+Border collie
+Bouvier des Flandres
+Rottweiler
+German shepherd
+Doberman
+miniature pinscher
+Greater Swiss Mountain dog
+Bernese mountain dog
+Appenzeller
+EntleBucher
+boxer
+bull mastiff
+Tibetan mastiff
+French bulldog
+Great Dane
+Saint Bernard
+Eskimo dog
+malamute
+Siberian husky
+dalmatian
+affenpinscher
+basenji
+pug
+Leonberg
+Newfoundland
+Great Pyrenees
+Samoyed
+Pomeranian
+chow
+keeshond
+Brabancon griffon
+Pembroke
+Cardigan
+toy poodle
+miniature poodle
+standard poodle
+Mexican hairless
+timber wolf
+white wolf
+red wolf
+coyote
+dingo
+dhole
+African hunting dog
+hyena
+red fox
+kit fox
+Arctic fox
+grey fox
+tabby
+tiger cat
+Persian cat
+Siamese cat
+Egyptian cat
+cougar
+lynx
+leopard
+snow leopard
+jaguar
+lion
+tiger
+cheetah
+brown bear
+American black bear
+ice bear
+sloth bear
+mongoose
+meerkat
+tiger beetle
+ladybug
+ground beetle
+long-horned beetle
+leaf beetle
+dung beetle
+rhinoceros beetle
+weevil
+fly
+bee
+ant
+grasshopper
+cricket
+walking stick
+cockroach
+mantis
+cicada
+leafhopper
+lacewing
+dragonfly
+damselfly
+admiral
+ringlet
+monarch
+cabbage butterfly
+sulphur butterfly
+lycaenid
+starfish
+sea urchin
+sea cucumber
+wood rabbit
+hare
+Angora
+hamster
+porcupine
+fox squirrel
+marmot
+beaver
+guinea pig
+sorrel
+zebra
+hog
+wild boar
+warthog
+hippopotamus
+ox
+water buffalo
+bison
+ram
+bighorn
+ibex
+hartebeest
+impala
+gazelle
+Arabian camel
+llama
+weasel
+mink
+polecat
+black-footed ferret
+otter
+skunk
+badger
+armadillo
+three-toed sloth
+orangutan
+gorilla
+chimpanzee
+gibbon
+siamang
+guenon
+patas
+baboon
+macaque
+langur
+colobus
+proboscis monkey
+marmoset
+capuchin
+howler monkey
+titi
+spider monkey
+squirrel monkey
+Madagascar cat
+indri
+Indian elephant
+African elephant
+lesser panda
+giant panda
+barracouta
+eel
+coho
+rock beauty
+anemone fish
+sturgeon
+gar
+lionfish
+puffer
+abacus
+abaya
+academic gown
+accordion
+acoustic guitar
+aircraft carrier
+airliner
+airship
+altar
+ambulance
+amphibian
+analog clock
+apiary
+apron
+ashcan
+assault rifle
+backpack
+bakery
+balance beam
+balloon
+ballpoint
+Band Aid
+banjo
+bannister
+barbell
+barber chair
+barbershop
+barn
+barometer
+barrel
+barrow
+baseball
+basketball
+bassinet
+bassoon
+bathing cap
+bath towel
+bathtub
+beach wagon
+beacon
+beaker
+bearskin
+beer bottle
+beer glass
+bell cote
+bib
+bicycle-built-for-two
+bikini
+binder
+binoculars
+birdhouse
+boathouse
+bobsled
+bolo tie
+bonnet
+bookcase
+bookshop
+bottlecap
+bow
+bow tie
+brass
+brassiere
+breakwater
+breastplate
+broom
+bucket
+buckle
+bulletproof vest
+bullet train
+butcher shop
+cab
+caldron
+candle
+cannon
+canoe
+can opener
+cardigan
+car mirror
+carousel
+carpenter's kit
+carton
+car wheel
+cash machine
+cassette
+cassette player
+castle
+catamaran
+CD player
+cello
+cellular telephone
+chain
+chainlink fence
+chain mail
+chain saw
+chest
+chiffonier
+chime
+china cabinet
+Christmas stocking
+church
+cinema
+cleaver
+cliff dwelling
+cloak
+clog
+cocktail shaker
+coffee mug
+coffeepot
+coil
+combination lock
+computer keyboard
+confectionery
+container ship
+convertible
+corkscrew
+cornet
+cowboy boot
+cowboy hat
+cradle
+crane
+crash helmet
+crate
+crib
+Crock Pot
+croquet ball
+crutch
+cuirass
+dam
+desk
+desktop computer
+dial telephone
+diaper
+digital clock
+digital watch
+dining table
+dishrag
+dishwasher
+disk brake
+dock
+dogsled
+dome
+doormat
+drilling platform
+drum
+drumstick
+dumbbell
+Dutch oven
+electric fan
+electric guitar
+electric locomotive
+entertainment center
+envelope
+espresso maker
+face powder
+feather boa
+file
+fireboat
+fire engine
+fire screen
+flagpole
+flute
+folding chair
+football helmet
+forklift
+fountain
+fountain pen
+four-poster
+freight car
+French horn
+frying pan
+fur coat
+garbage truck
+gasmask
+gas pump
+goblet
+go-kart
+golf ball
+golfcart
+gondola
+gong
+gown
+grand piano
+greenhouse
+grille
+grocery store
+guillotine
+hair slide
+hair spray
+half track
+hammer
+hamper
+hand blower
+hand-held computer
+handkerchief
+hard disc
+harmonica
+harp
+harvester
+hatchet
+holster
+home theater
+honeycomb
+hook
+hoopskirt
+horizontal bar
+horse cart
+hourglass
+iPod
+iron
+jack-o'-lantern
+jean
+jeep
+jersey
+jigsaw puzzle
+jinrikisha
+joystick
+kimono
+knee pad
+knot
+lab coat
+ladle
+lampshade
+laptop
+lawn mower
+lens cap
+letter opener
+library
+lifeboat
+lighter
+limousine
+liner
+lipstick
+Loafer
+lotion
+loudspeaker
+loupe
+lumbermill
+magnetic compass
+mailbag
+mailbox
+maillot
+maillot
+manhole cover
+maraca
+marimba
+mask
+matchstick
+maypole
+maze
+measuring cup
+medicine chest
+megalith
+microphone
+microwave
+military uniform
+milk can
+minibus
+miniskirt
+minivan
+missile
+mitten
+mixing bowl
+mobile home
+Model T
+modem
+monastery
+monitor
+moped
+mortar
+mortarboard
+mosque
+mosquito net
+motor scooter
+mountain bike
+mountain tent
+mouse
+mousetrap
+moving van
+muzzle
+nail
+neck brace
+necklace
+nipple
+notebook
+obelisk
+oboe
+ocarina
+odometer
+oil filter
+organ
+oscilloscope
+overskirt
+oxcart
+oxygen mask
+packet
+paddle
+paddlewheel
+padlock
+paintbrush
+pajama
+palace
+panpipe
+paper towel
+parachute
+parallel bars
+park bench
+parking meter
+passenger car
+patio
+pay-phone
+pedestal
+pencil box
+pencil sharpener
+perfume
+Petri dish
+photocopier
+pick
+pickelhaube
+picket fence
+pickup
+pier
+piggy bank
+pill bottle
+pillow
+ping-pong ball
+pinwheel
+pirate
+pitcher
+plane
+planetarium
+plastic bag
+plate rack
+plow
+plunger
+Polaroid camera
+pole
+police van
+poncho
+pool table
+pop bottle
+pot
+potter's wheel
+power drill
+prayer rug
+printer
+prison
+projectile
+projector
+puck
+punching bag
+purse
+quill
+quilt
+racer
+racket
+radiator
+radio
+radio telescope
+rain barrel
+recreational vehicle
+reel
+reflex camera
+refrigerator
+remote control
+restaurant
+revolver
+rifle
+rocking chair
+rotisserie
+rubber eraser
+rugby ball
+rule
+running shoe
+safe
+safety pin
+saltshaker
+sandal
+sarong
+sax
+scabbard
+scale
+school bus
+schooner
+scoreboard
+screen
+screw
+screwdriver
+seat belt
+sewing machine
+shield
+shoe shop
+shoji
+shopping basket
+shopping cart
+shovel
+shower cap
+shower curtain
+ski
+ski mask
+sleeping bag
+slide rule
+sliding door
+slot
+snorkel
+snowmobile
+snowplow
+soap dispenser
+soccer ball
+sock
+solar dish
+sombrero
+soup bowl
+space bar
+space heater
+space shuttle
+spatula
+speedboat
+spider web
+spindle
+sports car
+spotlight
+stage
+steam locomotive
+steel arch bridge
+steel drum
+stethoscope
+stole
+stone wall
+stopwatch
+stove
+strainer
+streetcar
+stretcher
+studio couch
+stupa
+submarine
+suit
+sundial
+sunglass
+sunglasses
+sunscreen
+suspension bridge
+swab
+sweatshirt
+swimming trunks
+swing
+switch
+syringe
+table lamp
+tank
+tape player
+teapot
+teddy
+television
+tennis ball
+thatch
+theater curtain
+thimble
+thresher
+throne
+tile roof
+toaster
+tobacco shop
+toilet seat
+torch
+totem pole
+tow truck
+toyshop
+tractor
+trailer truck
+tray
+trench coat
+tricycle
+trimaran
+tripod
+triumphal arch
+trolleybus
+trombone
+tub
+turnstile
+typewriter keyboard
+umbrella
+unicycle
+upright
+vacuum
+vase
+vault
+velvet
+vending machine
+vestment
+viaduct
+violin
+volleyball
+waffle iron
+wall clock
+wallet
+wardrobe
+warplane
+washbasin
+washer
+water bottle
+water jug
+water tower
+whiskey jug
+whistle
+wig
+window screen
+window shade
+Windsor tie
+wine bottle
+wing
+wok
+wooden spoon
+wool
+worm fence
+wreck
+yawl
+yurt
+web site
+comic book
+crossword puzzle
+street sign
+traffic light
+book jacket
+menu
+plate
+guacamole
+consomme
+hot pot
+trifle
+ice cream
+ice lolly
+French loaf
+bagel
+pretzel
+cheeseburger
+hotdog
+mashed potato
+head cabbage
+broccoli
+cauliflower
+zucchini
+spaghetti squash
+acorn squash
+butternut squash
+cucumber
+artichoke
+bell pepper
+cardoon
+mushroom
+Granny Smith
+strawberry
+orange
+lemon
+fig
+pineapple
+banana
+jackfruit
+custard apple
+pomegranate
+hay
+carbonara
+chocolate sauce
+dough
+meat loaf
+pizza
+potpie
+burrito
+red wine
+espresso
+cup
+eggnog
+alp
+bubble
+cliff
+coral reef
+geyser
+lakeside
+promontory
+sandbar
+seashore
+valley
+volcano
+ballplayer
+groom
+scuba diver
+rapeseed
+daisy
+yellow lady's slipper
+corn
+acorn
+hip
+buckeye
+coral fungus
+agaric
+gyromitra
+stinkhorn
+earthstar
+hen-of-the-woods
+bolete
+ear
+toilet tissue

requirements.txt

@@ -0,0 +1,14 @@
+--extra-index-url https://download.pytorch.org/whl/cpu
+
+fastapi==0.115.6
+uvicorn[standard]==0.30.6
+python-multipart==0.0.9
+
+torch==2.5.1
+torchvision==0.20.1
+timm==0.9.16
+
+pillow==10.4.0
+numpy==2.1.3
+huggingface-hub==0.24.7
+safetensors==0.4.5