def main():
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model_path = "captcha-breaker-v%d.pth" % CaptchaNN.version()
data_path = "./fetched"
getImageUrl = "http://captcha.qq.com/getimage"
downloadNum = 500
net = CaptchaNN()
net = net.to(device)
net.load_state_dict(torch.load(model_path))
net.eval()
transform = CaptchaDataset.get_transform(224, 224)
for i in range(0, downloadNum):
file = "!unclassified.jpg"
url = getImageUrl
localPath = os.path.join(data_path, file)
urllib.request.urlretrieve(url, localPath)
pilImg = Image.open(localPath)
img = transform(pilImg)
img = CaptchaDataset.to_var(img)
X = img.to(device)
pred = CaptchaDataset.decode_label(net.predict(X))
os.rename(localPath, os.path.join(data_path, pred + ".jpg"))
print("Downloaded and recognized as ", pred)
pass
def main():
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model_path = "captcha-breaker-v%d.pth" % CaptchaNN.version()
data_path = "./datav2/test"
net = CaptchaNN()
net = net.to(device)
net.load_state_dict(torch.load(model_path))
net.eval()
#transform = dataset.CaptchaDataset.get_transform(224, 224)
train_dataset = CaptchaDataset(data_path, 224, 224)
trainIter = DataLoader(train_dataset,
batch_size=1,
num_workers=0,
shuffle=True,
drop_last=False)
rightNum = 0
for i, (X, label) in enumerate(trainIter):
X = X.to(device)
label = label.to(device)
label = label.long()
label1 = label[:, 0]
label2 = label[:, 1]
label3 = label[:, 2]
label4 = label[:, 3]
y1, y2, y3, y4 = net(X)
_, y1_pred = torch.max(y1.data, dim=1)
_, y2_pred = torch.max(y2.data, dim=1)
_, y3_pred = torch.max(y3.data, dim=1)
_, y4_pred = torch.max(y4.data, dim=1)
print(
CaptchaDataset.decode_label((label1, label2, label3, label4)),
CaptchaDataset.decode_label((y1_pred.item(), y2_pred.item(),
y3_pred.item(), y4_pred.item())))
if label1 == y1_pred.item() and label2 == y2_pred.item(
) and label3 == y3_pred.item() and label4 == y4_pred.item():
rightNum += 1
print("RIGHT: %d/%d %f" % (rightNum, i, rightNum / i))
result = []
total_pred, total_given = [], []
for i, (images, labels) in enumerate(data_loader):
t0 = time.time()
with torch.no_grad():
inputs, targets = images.to(device), labels.to(device)
logits = model(inputs)
loss = F.cross_entropy(logits, targets)
dist = F.log_softmax(logits, dim=1)
pred = dist.max(1)[1]
pred_label = "".join(dataset.decode_label(pred[0]))
total_pred.extend(pred[0].cpu().numpy())
total_given.extend(labels[0].cpu().numpy())
result.append((loss.data.cpu(), dataset.image_names[i], pred_label))
for loss, name, label in sorted(result, key=lambda x: -x[0]):
err = ' ' if label == name[:-4] else '*'
print("{}\t{}\t{}\t{:.8f}".format(name, label, err, loss))
pr, gv = np.array(total_pred), np.array(total_given)
car = np.mean(pr == gv)
sar = np.mean(np.prod(pr.reshape(-1, 5), axis=1) == \
np.prod(gv.reshape(-1,5), axis=1))
