Kartik sachdevkartik

## validation_accuracy.csv

          
            Architecture
             Model_I
             Model_II
             Model_III

            
              Convolutional Vision Transformer
               91.54%
               99.41%
               99.04%

            
              CrossFormer
               91.20%
               97.42%
               98.13%

            
              LeViT
               91.64%
               97.12%
               97.97%

            
              TwinsSVT
               91.08%
               97.44%
               98.48%

            
              CCT
               89.71%
               69.68%
               99.48%

            
              CrossViT
               84.20%
               91.33%
               81.29%

            
              CaiT
               67.93%
               62.97%
               69.38%

            
              T2TViT
               88.12%
               94.33%
               77.29%

            
              PiT
               40.63%
               33.60%
               34.18%

## twinssvt_config.py
TWINSSVT_CONFIG = {
    "network_type": "TwinsSVT",
    "pretrained": False,
    "image_size": 224,
    "batch_size": 64,
    "num_epochs": 15,
    "optimizer_config": {
        "name": "AdamW",
        "weight_decay": 0.01,
        "lr": 0.001,

## hyperparameters.csv

          
            Hyperparameter
             Value

            
              Batch size
               64

            
              Epochs
               15

            
              Image channels
               1

            
              Optimizer
               AdamW

            
              Weight decay
               0.01

            
              Learning rate schedule
               Cosine schedule with warmup

            
              Initial learning rate
               0.01

## augmentation.py
from typing import Optional
from torchvision import transforms
from PIL import Image
import albumentations as A
from albumentations.pytorch import ToTensorV2
from torch.utils.data import DataLoader, Dataset


def get_transform_train(
    upsample_size: int, final_size: int, channels: Optional[int] = 1
Architecture	Model_I	Model_II	Model_III
Convolutional Vision Transformer	91.54%	99.41%	99.04%
CrossFormer	91.20%	97.42%	98.13%
LeViT	91.64%	97.12%	97.97%
TwinsSVT	91.08%	97.44%	98.48%
CCT	89.71%	69.68%	99.48%
CrossViT	84.20%	91.33%	81.29%
CaiT	67.93%	62.97%	69.38%
T2TViT	88.12%	94.33%	77.29%
PiT	40.63%	33.60%	34.18%
	TWINSSVT_CONFIG = {
	"network_type": "TwinsSVT",
	"pretrained": False,
	"image_size": 224,
	"batch_size": 64,
	"num_epochs": 15,
	"optimizer_config": {
	"name": "AdamW",
	"weight_decay": 0.01,
	"lr": 0.001,
	Hyperparameter	Value
	Batch size	64
	Epochs	15
	Image channels	1
	Optimizer	AdamW
	Weight decay	0.01
	Learning rate schedule	Cosine schedule with warmup
	Initial learning rate	0.01
	from typing import Optional
	from torchvision import transforms
	from PIL import Image
	import albumentations as A
	from albumentations.pytorch import ToTensorV2
	from torch.utils.data import DataLoader, Dataset


	def get_transform_train(
	upsample_size: int, final_size: int, channels: Optional[int] = 1