e96031413

from backtesting import Backtest, Strategy
from backtesting.lib import crossover

from FinMind.data import DataLoader
import pandas as pd

import talib
from talib import abstract

## 取得資料

e96031413

import pandas as pd
from twstock import Stock
import argparse


def parse():
    parser = argparse.ArgumentParser()
    parser.add_argument(
        "--etf_code", type=str, default="00733",
    )

e96031413

"""
RetinaNet model with the MobileNetV3 backbone from 
Torchvision classification models.

Reference: https://github.com/pytorch/vision/blob/main/torchvision/models/detection/retinanet.py#L377-L405
"""

import torchvision
import torch
from torchvision.models.detection import RetinaNet

e96031413

import matplotlib.pyplot as plt
import numpy as np
import rawpy

def pack_raw(raw):
        im = raw.raw_image_visible.astype(np.float32)
        im = np.expand_dims(im, axis=2)
        img_shape = im.shape
        H = img_shape[0]
        W = img_shape[1]

e96031413

import numpy as np
import cv2
import matplotlib.image

def gamma_compression(image):
    """Converts from linear to gamma space."""
    return np.maximum(image, 1e-8) ** (1.0 / 2.2)

def tonemap(image):
    """Simple S-curved global tonemap"""

e96031413

"""
有时我们需要载入之前训练好的模型来训练当前网络，但之前模型和现在网络结构又存在一些不同（相同就更简单了，直接载入就行）
可使用如下代码来迁移模型参数：
https://zhuanlan.zhihu.com/p/393586665
"""

def transfer_model(pretrain_file, model):
    pretrain_dict = torch.load(pretrain_file)
    model_dict = model.state_dict()
    pretrain_dict = transfer_state_dict(pretrain_dict, model_dict)

e96031413

import tensorflow as tf
from tensorboard.backend.event_processing import event_accumulator

# Specify the path to the existing event file
original_event_file = "old_events.out.tfevents.1686288913.51ec3d9beacb.141764.0"

# Specify the path for the new event file
new_event_file = "new_events.out.tfevents.1686288913.51ec3d9beacb.141764.0"
# Load the existing event file using EventAccumulator
event_acc = event_accumulator.EventAccumulator(original_event_file)

e96031413

# https://github.com/mv-lab/AISP/blob/main/mai22-learnedisp/mai-learned-isp-dev.ipynb
import numpy as np
import pandas as pd
import gc
import time
from glob import glob
from tqdm import tqdm
from matplotlib import pyplot as plt
import pickle
import imageio

e96031413

# init git
cd existing_folder
git init --initial-branch=main
git remote add origin git@gitlab-XXXX.com:yanwei.liu/XXXX-XXXX.git

# git commit
git add .
git commit -m "Initial commit"
git push -u origin main

e96031413

import torch
import torch.nn.functional as F

def pad_image_to_nearest_multiple(image, multiple=32):
    image = torch.from_numpy(image.astype(np.float32)).unsqueeze(0)

    channels, height, width = image.shape
    padded_height = ((height + multiple - 1) // multiple) * multiple
    padded_width = ((width + multiple - 1) // multiple) * multiple