File size: 1,479 Bytes
71ec175 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 | import torch
import numpy as np
from sklearn.metrics import accuracy_score, precision_recall_fscore_support, confusion_matrix, roc_auc_score
def evaluate_model(model, dataloader, device="cpu"):
"""
Standard comprehensive evaluation calculating Accuracy, Precision, Recall, Specificity, F1, and AUC.
"""
model.eval()
all_preds = []
all_targets = []
all_probs = []
with torch.no_grad():
for inputs, targets in dataloader:
inputs = inputs.to(device)
outputs, _ = model(inputs)
probs = torch.softmax(outputs, dim=1)[:, 1]
preds = torch.argmax(outputs, dim=1)
all_preds.extend(preds.cpu().numpy())
all_targets.extend(targets.numpy())
all_probs.extend(probs.cpu().numpy())
all_preds = np.array(all_preds)
all_targets = np.array(all_targets)
all_probs = np.array(all_probs)
acc = accuracy_score(all_targets, all_preds)
prec, rec, f1, _ = precision_recall_fscore_support(all_targets, all_preds, average='binary')
tn, fp, fn, tp = confusion_matrix(all_targets, all_preds).ravel()
spec = tn / (tn + fp)
auc_val = roc_auc_score(all_targets, all_probs)
return {
"accuracy": acc,
"precision": prec,
"recall_sensitivity": rec,
"specificity": spec,
"f1_score": f1,
"roc_auc": auc_val,
"confusion_matrix": {"TP": int(tp), "TN": int(tn), "FP": int(fp), "FN": int(fn)}
}
|