单个文件直接画图:
import torch
import matplotlib.pyplot as plt
data = torch.load('../Loss.pt')
print("Loss:")
print(data)
data = data.numpy()
plt.plot(data)
plt.title('Loss Plot')
plt.xlabel('X-axis')
plt.ylabel('Y-axis')
plt.show()
多个文件一起画图
import torch
import matplotlib.pyplot as plt
Loss = torch.load('../experiments/24_03_2023__10_06_20ECGCNN_S_physio_net_dataset_challange_two_classes/metrics/Loss.pt')
Accuracy = torch.load('../experiments/24_03_2023__10_06_20ECGCNN_S_physio_net_dataset_challange_two_classes/metrics/Accuracy.pt')
F1 = torch.load('../experiments/24_03_2023__10_06_20ECGCNN_S_physio_net_dataset_challange_two_classes/metrics/F1.pt')
print("Loss:")
print(Loss)
print("Accuracy:")
print(Accuracy)
print("F1:")
print(F1)
Loss = Loss.numpy()
Accuracy = Accuracy.numpy()
F1 = F1.numpy()
plt.plot(Loss, label='Loss')
plt.plot(Accuracy, label='Accuracy')
plt.plot(F1, label='F1')
plt.title('ECGCNNBiLSTM_B_S Plot')
plt.xlabel('X-axis')
plt.ylabel('Y-axis')
plt.show()
多个文件分别画图:
import torch
import matplotlib.pyplot as plt
Loss = torch.load('../experiments/24_03_2023__21_46_47ECGCNN_S_physio_net_dataset_challange_two_classes/metrics/Loss.pt')
Accuracy = torch.load('../experiments/24_03_2023__21_46_47ECGCNN_S_physio_net_dataset_challange_two_classes/metrics/Accuracy.pt')
F1 = torch.load('../experiments/24_03_2023__21_46_47ECGCNN_S_physio_net_dataset_challange_two_classes/metrics/F1.pt')
print("Loss:")
print(Loss)
print("Accuracy:")
print(Accuracy)
print("F1:")
print(F1)
Loss = Loss.numpy()
Accuracy = Accuracy.numpy()
F1 = F1.numpy()
arr = {
'Loss': Loss,
'Accuracy': Accuracy,
'F1': F1
}
for a in arr:
plt.plot(arr[a])
plt.title('ECGBiCLSTM_B_S' + a + 'Plot')
plt.xlabel('X-axis')
plt.ylabel('Y-axis')
plt.show()