텍스트 비교

두 텍스트 파일의 차이점을 찾아보세요

실시간 편집

변경 없는 행 숨기기

줄바꿈 비활성화

레이아웃

비교 단위

구문 강조

Diffchecker Desktop 가장 안전하게 Diffchecker를 사용하는 방법. 데스크톱 앱을 사용하면 비교 데이터가 외부로 전송되지 않습니다!데스크톱 앱 받기

model_diff_help1

생성일 2년 전비교 결과 만료 없음

3 삭제

행
총
삭제

글자
총
삭제

이 기능을 계속 사용하려면 업그레이드해 주세요 Diffchecker Pro 요금제 보기

26 행

9 추가

행
총
추가

글자
총
추가

이 기능을 계속 사용하려면 업그레이드해 주세요 Diffchecker Pro 요금제 보기

31 행

class Model(nn.Module):

def forward(self, img1, img2):

# Calculate the mean of the two input tensors

mean1 = torch.mean(img1, dim=0)

mean1 = torch.mean(img1, dim=1, keepdim=True)

mean2 = torch.mean(img2, dim=0)

mean2 = torch.mean(img2, dim=1, keepdim=True)

# Calculate the absolute difference between the two mean tensors

diff = torch.sqrt(torch.pow(mean1 - mean2, 2)).float()

print(diff.shape)

threshold = 30.0

# Create a binary mask where differences are higher than the threshold

mask = torch.where(diff > threshold, torch.tensor(1.0), torch.tensor(0.0))

print(mask.shape)

# Count the number of moving pixels

movingPx = torch.sum(mask)

movingPx = torch.sum(mask).view(1,1,1,1)

print(movingPx)

# Calculate the total number of pixels

totalPx = torch.tensor(mask.shape[0] * mask.shape[1], dtype=torch.float32)

# Calculate the ratio of moving pixels to the total number of pixels

movingRatio = movingPx / totalPx

return movingRatio.unsqueeze(0) # Ensure the output is a tensor with an added dimension

return movingRatio # Ensure the output is a tensor with an added dimension

model = Model()

torch.onnx.export(model, (torch.randn(1,3,720,720), torch.randn(1,3,720,720)), "model_diff.onnx", opset_version=16)

저장된 비교 결과

원본

파일 열기

class Model(nn.Module):
    def forward(self, img1, img2):
        # Calculate the mean of the two input tensors
        mean1 = torch.mean(img1, dim=0)
        mean2 = torch.mean(img2, dim=0)

# Calculate the absolute difference between the two mean tensors
        diff = torch.sqrt(torch.pow(mean1 - mean2, 2)).float()
        print(diff.shape)

threshold = 30.0

# Create a binary mask where differences are higher than the threshold
        mask = torch.where(diff > threshold, torch.tensor(1.0), torch.tensor(0.0))
        print(mask.shape)

# Count the number of moving pixels
        movingPx = torch.sum(mask)
        print(movingPx)

# Calculate the total number of pixels
        totalPx = torch.tensor(mask.shape[0] * mask.shape[1], dtype=torch.float32)

# Calculate the ratio of moving pixels to the total number of pixels
        movingRatio = movingPx / totalPx
        return movingRatio.unsqueeze(0)  # Ensure the output is a tensor with an added dimension

수정본

파일 열기

class Model(nn.Module):
    def forward(self, img1, img2):
        # Calculate the mean of the two input tensors
        mean1 = torch.mean(img1, dim=1, keepdim=True)
        mean2 = torch.mean(img2, dim=1, keepdim=True)

# Calculate the absolute difference between the two mean tensors
        diff = torch.sqrt(torch.pow(mean1 - mean2, 2)).float()
        print(diff.shape)

threshold = 30.0

# Create a binary mask where differences are higher than the threshold
        mask = torch.where(diff > threshold, torch.tensor(1.0), torch.tensor(0.0))
        print(mask.shape)

# Count the number of moving pixels
        movingPx = torch.sum(mask).view(1,1,1,1)
        print(movingPx)

# Calculate the total number of pixels
        totalPx = torch.tensor(mask.shape[0] * mask.shape[1], dtype=torch.float32)

# Calculate the ratio of moving pixels to the total number of pixels
        movingRatio = movingPx / totalPx
        return movingRatio  # Ensure the output is a tensor with an added dimension

model = Model()
torch.onnx.export(model, (torch.randn(1,3,720,720), torch.randn(1,3,720,720)), "model_diff.onnx", opset_version=16)