我想在 Image Classification with Transfer Learning in PyTorch 中显示每张图片输出下的准确性

Question

我关注这个 link : https://stackabuse.com/image-classification-with-transfer-learning-and-pytorch/#settingupapretrainedmodel

但我是编码技能的新手。请告诉我如何在图像下显示精度值。

Answer 1

该示例中使用的模型 returns 形状的对数张量（批量大小，classes）。假设你所说的 "accuracy value" 是 class 的预测概率最大的概率，你需要做的是首先通过从模型中获取输出的 SoftMax 来计算你的概率，这给出了批次中每个图像的预测概率。他们的 visualize_model 函数看起来像下面这样，但我还没有测试过。

def visualize_model(model, num_images=6):
    was_training = model.training
    model.eval()
    images_handeled = 0
    fig = plt.figure()

    with torch.no_grad():
        for i, (inputs, labels) in enumerate(dataloaders['val']):
            inputs = inputs.to(device)
            labels = labels.to(device)

            outputs = model(inputs)
            probabilities = nn.functional.softmax(outputs, dim=-1) # compute probabilities
            _, preds = torch.max(outputs, 1)

            for j in range(inputs.size()[0]):
                images_handeled += 1
                ax = plt.subplot(num_images//2, 2, images_handeled)
                ax.axis('off')
                ax.set_title('predicted: {}, probability: {}'.format(class_names[preds[j]], probabilities[preds[j]])) # add predicted class probability
                imshow(inputs.cpu().data[j])

                if images_handeled == num_images:
                    model.train(mode=was_training)
                    return
        model.train(mode=was_training)

或者您的意思是总体 class化准确率？

我想在 Image Classification with Transfer Learning in PyTorch 中显示每张图片输出下的准确性

I want to show accuracy under each picture output shown in Image Classification with Transfer Learning in PyTorch

python

data-visualization

image

classification

pytorch