"e2e_dump_settings": {
"enable": True,
"trans_flag": False
}
}
with open("./data_dump.json", "w", encoding="GBK") as f:
json.dump(data_dump, f)
os.environ['MINDSPORE_DUMP_CONFIG'] = abspath + "/data_dump.json"
def set_log_info():
os.environ['GLOG_v'] = '1'
os.environ['GLOG_logtostderr'] = '1'
os.environ['logger_maxBytes'] = '5242880'
os.environ['GLOG_log_dir'] = 'D:/' if os.name == "nt" else '/var/log/mindspore'
os.environ['logger_backupCount'] = '10'
print(logger.get_log_config())
if __name__ == "__main__":
set_dump_info()
set_log_info()
context.set_context(mode=context.GRAPH_MODE)
train_dataset = create_train_dataset()
eval_dataset = create_eval_dataset()
net = Net()
net_opt = Momentum(net.trainable_params(), 0.01, 0.9)
net_loss = SoftmaxCrossEntropyWithLogits(reduction='mean')
model = Model(network=net, loss_fn=net_loss, optimizer=net_opt, metrics={'Accuracy': nn.Accuracy()})
model.train(epoch=100,
train_dataset=train_dataset,
callbacks=[LossMonitor(), StopAtTime(3), SaveCallback(model, eval_dataset)])
help="set the eps of fgsm")
args, _ = parser.parse_known_args()
images = []
labels = []
test_images = []
test_labels = []
predict_labels = []
net = LeNet5()
mnist_path = "./datasets/MNIST_Data/"
param_dict = load_checkpoint("checkpoint_lenet-1_1875.ckpt")
load_param_into_net(net, param_dict)
net_loss = nn.SoftmaxCrossEntropyWithLogits(sparse=True, reduction='mean')
net_opt = nn.Momentum(net.trainable_params(), learning_rate=0.01, momentum=0.9)
model = Model(net, net_loss, net_opt, metrics={"Accuracy": nn.Accuracy()})
ds_test = create_dataset(os.path.join(mnist_path, "test"),
batch_size=32).create_dict_iterator(output_numpy=True)
for data in ds_test:
images = data['image'].astype(np.float32)
labels = data['label']
test_images.append(images)
test_labels.append(labels)
pred_labels = np.argmax(model.predict(Tensor(images)).asnumpy(), axis=1)
predict_labels.append(pred_labels)
test_images = np.concatenate(test_images)
predict_labels = np.concatenate(predict_labels)
true_labels = np.concatenate(test_labels)
def set_log_info():
os.environ['GLOG_v'] = '1'
os.environ['GLOG_logtostderr'] = '1'
os.environ['logger_maxBytes'] = '5242880'
os.environ[
'GLOG_log_dir'] = 'D:/' if os.name == "nt" else '/var/log/mindspore'
os.environ['logger_backupCount'] = '10'
print(logger.get_log_config())
if __name__ == "__main__":
set_dump_info()
set_log_info()
context.set_context(mode=context.GRAPH_MODE)
train_dataset = create_train_dataset()
eval_dataset = create_eval_dataset()
net = Net()
net_opt = Momentum(net.trainable_params(), 0.01, 0.9)
net_loss = SoftmaxCrossEntropyWithLogits(reduction='mean')
model = Model(network=net,
loss_fn=net_loss,
optimizer=net_opt,
metrics={'Accuracy': nn.Accuracy()})
model.train(epoch=100,
train_dataset=train_dataset,
callbacks=[
LossMonitor(),
StopAtTime(3),
SaveCallback(model, eval_dataset)
])
"""
import mindspore.nn as nn
from mindspore.nn import Momentum, SoftmaxCrossEntropyWithLogits
from mindspore import Model, context
from mindspore.train.callback import ModelCheckpoint, CheckpointConfig, LossMonitor
from src.dataset import create_train_dataset, create_eval_dataset
from src.net import Net
if __name__ == "__main__":
context.set_context(mode=context.GRAPH_MODE)
ds_train = create_train_dataset()
ds_eval = create_eval_dataset()
net = Net()
net_opt = Momentum(net.trainable_params(), 0.01, 0.9)
net_loss = SoftmaxCrossEntropyWithLogits(reduction='mean')
metrics = {
'Accuracy': nn.Accuracy(),
'Loss': nn.Loss(),
'Precision': nn.Precision(),
'Recall': nn.Recall(),
'F1_score': nn.F1()
}
config_ck = CheckpointConfig(save_checkpoint_steps=1000, keep_checkpoint_max=10)
ckpoint = ModelCheckpoint(prefix="CKPT", config=config_ck)
model = Model(network=net, loss_fn=net_loss, optimizer=net_opt, metrics=metrics)
model.train(epoch=2, train_dataset=ds_train, callbacks=[ckpoint, LossMonitor()])
result = model.eval(ds_eval)
print(result)