Downloading data from https://mindspore-website.obs.cn-north-4.myhuaweicloud.com/notebook/datasets/MNIST_Data.zip (10.3 MB)

file_sizes: 100%|██████████████████████████| 10.8M/10.8M [00:00<00:00, 95.0MB/s]
Extracting zip file...
Successfully downloaded / unzipped to ./
Epoch 1
-------------------------------
loss: 2.303327  [  0/938]
2.0164787769317627
loss: 2.285390  [100/938]
4.2119457721710205
loss: 2.258592  [200/938]
6.720204591751099
loss: 2.186386  [300/938]
10.521805047988892
loss: 1.879479  [400/938]
14.198472023010254
loss: 1.388701  [500/938]
17.38415837287903
loss: 0.997088  [600/938]
21.71060013771057
loss: 0.723973  [700/938]
25.301536321640015
loss: 0.660443  [800/938]
25.50191068649292
loss: 0.592801  [900/938]
29.894129037857056
Test:
 Accuracy: 84.5%, Avg loss: 0.539146

st = time.time()
for batch, (data, label) in enumerate(dataset.create_tuple_iterator()):
    loss = train_step(data, label)
    if batch % 100 == 0:
        loss, current = loss.asnumpy(), batch
        print(f"loss: {loss:>7f}  [{current:>3d}/{size:>3d}]")
        print(time.time() - st)
        st = time.time()