def view_classify(img: NDArray, ps: NDArray, version="MNIST"):
''' Function for viewing an image and it's predicted classes.
'''
ps = ps.asnumpy().squeeze()
fig, (ax1, ax2) = plt.subplots(figsize=(6, 9), ncols=2)
ax1.imshow(img.asnumpy().squeeze())
ax1.axis('off')
ax2.barh(np.arange(10), ps)
ax2.set_aspect(0.1)
ax2.set_yticks(np.arange(10))
if version == "MNIST":
ax2.set_yticklabels(np.arange(10))
ax2.set_title('Class Probability')
ax2.set_xlim(0, 1.1)
plt.tight_layout()
def view_recon(img: NDArray, recon):
''' Function for displaying an image (as a PyTorch Tensor) and its
reconstruction also a PyTorch Tensor
'''
fig, axes = plt.subplots(ncols=2, sharex=True, sharey=True)
axes[0].imshow(img.asnumpy().squeeze())
axes[1].imshow(recon.asnumpy().squeeze())
for ax in axes:
ax.axis('off')
ax.set_adjustable('box-forced')
def stat_helper(name, array):
"""wrapper for executor callback"""
import ctypes
from mxnet.ndarray import NDArray
from mxnet.base import NDArrayHandle, py_str
array = ctypes.cast(array, NDArrayHandle)
array = NDArray(array, writable=False)
array.wait_to_read()
elapsed = float(time.time()-stat_helper.start_time)*1000
# if elapsed>0.:
# print (name, array.shape, ('%.1fms' % (elapsed,)))
# stat_helper.start_time=time.time()
array = array.asnumpy()
print(name, array.shape, np.average(array), np.std(array), ('%.1fms' % (float(time.time()-stat_helper.start_time)*1000)))
stat_helper.internal_shapes.append((name,array.shape))