first commit

Dockerfile

@@ -0,0 +1,16 @@
+# Read the doc: https://huggingface.co/docs/hub/spaces-sdks-docker
+# you will also find guides on how best to write your Dockerfile
+
+FROM python:3.9
+
+RUN useradd -m -u 1000 user
+USER user
+ENV PATH="/home/user/.local/bin:$PATH"
+
+WORKDIR /app
+
+COPY --chown=user ./requirements.txt requirements.txt
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
+
+COPY --chown=user . /app
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

app.py

@@ -0,0 +1,130 @@
+from fastapi import FastAPI, UploadFile, File
+import cv2
+import torch
+import pandas as pd
+from PIL import Image
+from transformers import AutoImageProcessor, AutoModelForImageClassification
+from tqdm import tqdm
+import json
+import shutil
+from fastapi.middleware.cors import CORSMiddleware
+
+app = FastAPI()
+
+# Add CORS middleware to allow requests from localhost:8080 (or any origin you specify)
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["http://localhost:8080"],  # Replace with the URL of your Vue.js app
+    allow_credentials=True,
+    allow_methods=["*"],  # Allows all HTTP methods (GET, POST, etc.)
+    allow_headers=["*"],  # Allows all headers (such as Content-Type, Authorization, etc.)
+)
+
+# Charger le processor et le modèle fine-tuné depuis le chemin local
+local_model_path = r'.\vit-finetuned-ucf101'
+processor = AutoImageProcessor.from_pretrained("google/vit-base-patch16-224")
+model = AutoModelForImageClassification.from_pretrained(local_model_path)
+model.eval()
+
+# Fonction pour classifier une image
+def classifier_image(image):
+    image_pil = Image.fromarray(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))
+    inputs = processor(images=image_pil, return_tensors="pt")
+    with torch.no_grad():
+        outputs = model(**inputs)
+        logits = outputs.logits
+    predicted_class_idx = logits.argmax(-1).item()
+    predicted_class = model.config.id2label[predicted_class_idx]
+    return predicted_class
+
+# Fonction pour traiter la vidéo et identifier les séquences de "Surfing"
+def identifier_sequences_surfing(video_path, intervalle=0.5):
+    cap = cv2.VideoCapture(video_path)
+    frame_rate = cap.get(cv2.CAP_PROP_FPS)
+    total_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
+    frame_interval = int(frame_rate * intervalle)
+
+    resultats = []
+    sequences_surfing = []
+    frame_index = 0
+    in_surf_sequence = False
+    start_timestamp = None
+
+    with tqdm(total=total_frames, desc="Traitement des frames de la vidéo", unit="frame") as pbar:
+        success, frame = cap.read()
+        while success:
+            if frame_index % frame_interval == 0:
+                timestamp = round(frame_index / frame_rate, 2)  # Maintain precision to the centisecond level
+                classe = classifier_image(frame)
+                resultats.append({"Timestamp": timestamp, "Classe": classe})
+
+                if classe == "Surfing" and not in_surf_sequence:
+                    in_surf_sequence = True
+                    start_timestamp = timestamp
+
+                elif classe != "Surfing" and in_surf_sequence:
+                    # Vérifier l'image suivante pour confirmer si c'était une erreur ponctuelle
+                    success_next, frame_next = cap.read()
+                    next_timestamp = round((frame_index + frame_interval) / frame_rate, 2)
+                    classe_next = None
+
+                    if success_next:
+                        classe_next = classifier_image(frame_next)
+                        resultats.append({"Timestamp": next_timestamp, "Classe": classe_next})
+
+                    # Si l'image suivante est "Surfing", on ignore l'erreur ponctuelle
+                    if classe_next == "Surfing":
+                        success = success_next
+                        frame = frame_next
+                        frame_index += frame_interval
+                        pbar.update(frame_interval)
+                        continue
+                    else:
+                        # Sinon, terminer la séquence "Surfing"
+                        in_surf_sequence = False
+                        end_timestamp = timestamp
+                        sequences_surfing.append((start_timestamp, end_timestamp))
+
+            success, frame = cap.read()
+            frame_index += 1
+            pbar.update(1)
+
+    # Si on est toujours dans une séquence "Surfing" à la fin de la vidéo
+    if in_surf_sequence:
+        sequences_surfing.append((start_timestamp, round(frame_index / frame_rate, 2)))
+
+    cap.release()
+    dataframe_sequences = pd.DataFrame(sequences_surfing, columns=["Début", "Fin"])
+    return dataframe_sequences
+
+# Fonction pour convertir les séquences en format JSON
+def convertir_sequences_en_json(dataframe):
+    events = []
+    blocks = []
+    for idx, row in dataframe.iterrows():
+        block = {
+            "id": f"Surfing{idx + 1}",
+            "start": round(row["Début"], 2),
+            "end": round(row["Fin"], 2)
+        }
+        blocks.append(block)
+    event = {
+        "event": "Surfing",
+        "blocks": blocks
+    }
+    events.append(event)
+    return events
+
+@app.post("/analyze_video/")
+async def analyze_video(file: UploadFile = File(...)):
+    with open("uploaded_video.mp4", "wb") as buffer:
+        shutil.copyfileobj(file.file, buffer)
+
+    dataframe_sequences = identifier_sequences_surfing("uploaded_video.mp4", intervalle=1)
+    json_result = convertir_sequences_en_json(dataframe_sequences)
+    return json_result
+
+# Lancer l'application avec uvicorn (command line)
+# uvicorn main:app --reload
+# http://localhost:8000/docs#/
+# (.venv) PS C:\Users\antoi\Documents\Work_Learn\Labeling-Deploy\FastAPI> uvicorn main:app --host 0.0.0.0 --port 8000 --workers 1

requirements.txt

@@ -0,0 +1,11 @@
+fastapi==0.115.0
+uvicorn==0.31.0
+torch==2.4.1
+transformers==4.45.1
+opencv-python==4.10.0.84
+pandas==2.2.3
+Pillow==10.4.0
+tqdm==4.66.5
+fastapi-cli==0.0.5
+starlette==0.38.6
+python-multipart==0.0.12

vit-finetuned-ucf101/README.md

@@ -0,0 +1,199 @@
+---
+library_name: transformers
+tags: []
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]

vit-finetuned-ucf101/config.json

@@ -0,0 +1,229 @@
+{
+  "_name_or_path": "google/vit-base-patch16-224",
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "ApplyEyeMakeup",
+    "1": "ApplyLipstick",
+    "2": "Archery",
+    "3": "BabyCrawling",
+    "4": "BalanceBeam",
+    "5": "BandMarching",
+    "6": "BaseballPitch",
+    "7": "Basketball",
+    "8": "BasketballDunk",
+    "9": "BenchPress",
+    "10": "Biking",
+    "11": "Billiards",
+    "12": "BlowDryHair",
+    "13": "BlowingCandles",
+    "14": "BodyWeightSquats",
+    "15": "Bowling",
+    "16": "BoxingPunchingBag",
+    "17": "BoxingSpeedBag",
+    "18": "BreastStroke",
+    "19": "BrushingTeeth",
+    "20": "CleanAndJerk",
+    "21": "CliffDiving",
+    "22": "CricketBowling",
+    "23": "CricketShot",
+    "24": "CuttingInKitchen",
+    "25": "Diving",
+    "26": "Drumming",
+    "27": "Fencing",
+    "28": "FieldHockeyPenalty",
+    "29": "FloorGymnastics",
+    "30": "FrisbeeCatch",
+    "31": "FrontCrawl",
+    "32": "GolfSwing",
+    "33": "Haircut",
+    "34": "Hammering",
+    "35": "HammerThrow",
+    "36": "HandstandPushups",
+    "37": "HandstandWalking",
+    "38": "HeadMassage",
+    "39": "HighJump",
+    "40": "HorseRace",
+    "41": "HorseRiding",
+    "42": "HulaHoop",
+    "43": "IceDancing",
+    "44": "JavelinThrow",
+    "45": "JugglingBalls",
+    "46": "JumpingJack",
+    "47": "JumpRope",
+    "48": "Kayaking",
+    "49": "Knitting",
+    "50": "LongJump",
+    "51": "Lunges",
+    "52": "MilitaryParade",
+    "53": "Mixing",
+    "54": "MoppingFloor",
+    "55": "Nunchucks",
+    "56": "ParallelBars",
+    "57": "PizzaTossing",
+    "58": "PlayingCello",
+    "59": "PlayingDaf",
+    "60": "PlayingDhol",
+    "61": "PlayingFlute",
+    "62": "PlayingGuitar",
+    "63": "PlayingPiano",
+    "64": "PlayingSitar",
+    "65": "PlayingTabla",
+    "66": "PlayingViolin",
+    "67": "PoleVault",
+    "68": "PommelHorse",
+    "69": "PullUps",
+    "70": "Punch",
+    "71": "PushUps",
+    "72": "Rafting",
+    "73": "RockClimbingIndoor",
+    "74": "RopeClimbing",
+    "75": "Rowing",
+    "76": "SalsaSpin",
+    "77": "ShavingBeard",
+    "78": "Shotput",
+    "79": "SkateBoarding",
+    "80": "Skiing",
+    "81": "Skijet",
+    "82": "SkyDiving",
+    "83": "SoccerJuggling",
+    "84": "SoccerPenalty",
+    "85": "StillRings",
+    "86": "SumoWrestling",
+    "87": "Surfing",
+    "88": "Swing",
+    "89": "TableTennisShot",
+    "90": "TaiChi",
+    "91": "TennisSwing",
+    "92": "ThrowDiscus",
+    "93": "TrampolineJumping",
+    "94": "Typing",
+    "95": "UnevenBars",
+    "96": "VolleyballSpiking",
+    "97": "WalkingWithDog",
+    "98": "WallPushups",
+    "99": "WritingOnBoard",
+    "100": "YoYo"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_100": 100,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_13": 13,
+    "LABEL_14": 14,
+    "LABEL_15": 15,
+    "LABEL_16": 16,
+    "LABEL_17": 17,
+    "LABEL_18": 18,
+    "LABEL_19": 19,
+    "LABEL_2": 2,
+    "LABEL_20": 20,
+    "LABEL_21": 21,
+    "LABEL_22": 22,
+    "LABEL_23": 23,
+    "LABEL_24": 24,
+    "LABEL_25": 25,
+    "LABEL_26": 26,
+    "LABEL_27": 27,
+    "LABEL_28": 28,
+    "LABEL_29": 29,
+    "LABEL_3": 3,
+    "LABEL_30": 30,
+    "LABEL_31": 31,
+    "LABEL_32": 32,
+    "LABEL_33": 33,
+    "LABEL_34": 34,
+    "LABEL_35": 35,
+    "LABEL_36": 36,
+    "LABEL_37": 37,
+    "LABEL_38": 38,
+    "LABEL_39": 39,
+    "LABEL_4": 4,
+    "LABEL_40": 40,
+    "LABEL_41": 41,
+    "LABEL_42": 42,
+    "LABEL_43": 43,
+    "LABEL_44": 44,
+    "LABEL_45": 45,
+    "LABEL_46": 46,
+    "LABEL_47": 47,
+    "LABEL_48": 48,
+    "LABEL_49": 49,
+    "LABEL_5": 5,
+    "LABEL_50": 50,
+    "LABEL_51": 51,
+    "LABEL_52": 52,
+    "LABEL_53": 53,
+    "LABEL_54": 54,
+    "LABEL_55": 55,
+    "LABEL_56": 56,
+    "LABEL_57": 57,
+    "LABEL_58": 58,
+    "LABEL_59": 59,
+    "LABEL_6": 6,
+    "LABEL_60": 60,
+    "LABEL_61": 61,
+    "LABEL_62": 62,
+    "LABEL_63": 63,
+    "LABEL_64": 64,
+    "LABEL_65": 65,
+    "LABEL_66": 66,
+    "LABEL_67": 67,
+    "LABEL_68": 68,
+    "LABEL_69": 69,
+    "LABEL_7": 7,
+    "LABEL_70": 70,
+    "LABEL_71": 71,
+    "LABEL_72": 72,
+    "LABEL_73": 73,
+    "LABEL_74": 74,
+    "LABEL_75": 75,
+    "LABEL_76": 76,
+    "LABEL_77": 77,
+    "LABEL_78": 78,
+    "LABEL_79": 79,
+    "LABEL_8": 8,
+    "LABEL_80": 80,
+    "LABEL_81": 81,
+    "LABEL_82": 82,
+    "LABEL_83": 83,
+    "LABEL_84": 84,
+    "LABEL_85": 85,
+    "LABEL_86": 86,
+    "LABEL_87": 87,
+    "LABEL_88": 88,
+    "LABEL_89": 89,
+    "LABEL_9": 9,
+    "LABEL_90": 90,
+    "LABEL_91": 91,
+    "LABEL_92": 92,
+    "LABEL_93": 93,
+    "LABEL_94": 94,
+    "LABEL_95": 95,
+    "LABEL_96": 96,
+    "LABEL_97": 97,
+    "LABEL_98": 98,
+    "LABEL_99": 99
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.1"
+}

vit-finetuned-ucf101/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c69b3dbf5e36aa63c248131c95fd15fee40e8403ea8ee78e95bd33967041ff14
+size 343528508