kingabzpro

pred_final = np.round(0.3*pred_1 + 0.6*pred_2 + 0.1*pred_3)

# evalution
accuracy = round(accuracy_score(y_test, pred_final) * 100, 3)
auc = round(roc_auc_score(y_test, pred_final), 3)

print(f" Accuracy: {accuracy}%")
print(f" AUC score: {auc}")

kingabzpro

# Utility
import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.metrics import roc_auc_score,accuracy_score
from sklearn.preprocessing import StandardScaler

# machine learning
from sklearn.ensemble import RandomForestClassifier
from sklearn.linear_model import LogisticRegression, SGDClassifier

kingabzpro

from tqdm.notebook import tqdm

colors = ["Blue","Green","Yellow","White","Gray","Black"]
for x in tqdm(colors):
    sleep(1)
    print(x)

kingabzpro

from tqdm.notebook import trange

for i in trange(10, desc='Traning Model on 10 Epochs'):
    sleep(0.01)
    for x in trange(10000, desc=f'Epoch {i}'):
        sleep(0.001)

kingabzpro

HF_TOKEN = os.getenv("HF_TOKEN")
hf_writer = gr.HuggingFaceDatasetSaver(HF_TOKEN, "savtadepth-flags")

iface = gr.Interface(
        gen,
        gr.inputs.Image(shape=(640, 480), type="numpy"),
        "image",
        title=title,
        description=description,
        article=article,

kingabzpro

git add .
git commit -m "first commit to HF Spaces"
git push gradio master:main -f

kingabzpro

-f https://download.pytorch.org/whl/cpu/torch_stable.html
dvc==2.9.5
fastai==2.5.3
torch==1.10.2+cpu
gradio==2.8.1

kingabzpro

---
title: Monocular Depth Estimation
emoji: 🛋
colorFrom: gray
colorTo: yellow
sdk: gradio
app_file: app/app_savta.py
pinned: false
license: mit
---

kingabzpro

git remote add gradio https://huggingface.co/spaces/kingabzpro/savtadepth

kingabzpro

import os

PROD_MODEL_PATH = "src/models"
TRAIN_PATH = "src/data/processed/train/bathroom"
TEST_PATH = "src/data/processed/test/bathroom"

if os.path.isdir(".dvc"):
    print("Running DVC")
    os.system("dvc config cache.type copy")
    os.system("dvc config core.no_scm true")