EckoTan0804

class UnNormalize(object):
    def __init__(self, mean, std):
        self.mean = mean
        self.std = std

    def __call__(self, tensor):
        """
        Args:
            tensor (Tensor): Tensor image of size (C, H, W) to be normalized.
        Returns:

EckoTan0804

# Place this file to the root of the project
# Adjust based on your needs

repos:
  - repo: https://github.com/pre-commit/pre-commit-hooks
    rev: v4.3.0
    hooks:
      - id: check-added-large-files # Prevent giant files from being committed.
      - id: check-ast # Simply check whether files parse as valid python.
      - id: fix-byte-order-marker # Removes UTF-8 byte order marker.

EckoTan0804

from PIL import Image

images = [Image.open(x) for x in ['Test1.jpg', 'Test2.jpg', 'Test3.jpg']]
widths, heights = zip(*(i.size for i in images))

total_width = sum(widths)
max_height = max(heights)

new_im = Image.new('RGB', (total_width, max_height))

EckoTan0804

from prettytable import PrettyTable

def count_parameters(model):
    table = PrettyTable(["Module", "Parameters"])
    
    # Assume the model consists of three main components: backbone, transformer, head
    module_param_dict = {
        "backbone": 0,
        "transformer": 0,
        "head": 0

EckoTan0804

import math
import torch
import numpy as np
from torchvision.models import resnet18, ResNet18_Weights # TODO: Import your model 
from tqdm import tqdm
from rich import print

# ========== TODO: Adjust based on your needs ==========
MODEL = resnet18(weights=ResNet18_Weights.IMAGENET1K_V1) 

EckoTan0804

import argparse
import torch
import torch.nn as nn
from torch.autograd import Variable
from torch.utils.data import DataLoader

import torchvision
import torchvision.transforms as T
from torchvision.datasets import ImageFolder

EckoTan0804

"""
This is a batched LSTM forward and backward pass
"""
import numpy as np
import code

class LSTM:
  
  @staticmethod
  def init(input_size, hidden_size, fancy_forget_bias_init = 3):

EckoTan0804

import os
import matplotlib.pyplot as plt

def save_fig(
    fig, fig_name, fig_dir, tight_layout=True, padding=False, fig_extension="png", resolution=300, transparent=True
):
    """
    Save figure
    Parameters
    ----------