def _draw_batch_preds(harn, batch, outputs, lim=16):
"""
Example:
>>> # xdoctest: +REQUIRES(--slow)
>>> kw = {'workers': 0, 'xpu': 'cpu', 'batch_size': 8}
>>> harn = setup_harn(cmdline=False, **kw).initialize()
>>> batch = harn._demo_batch(tag='train')
>>> outputs, loss_parts = harn.run_batch(batch)
>>> toshow = harn._draw_batch_preds(batch, outputs)
>>> # xdoctest: +REQUIRES(--show)
>>> import kwplot
>>> kwplot.autompl()
>>> kwplot.imshow(toshow)
"""
import cv2
im = batch['im'].data.cpu().numpy()
class_true = batch['class_idxs'].data.cpu().numpy()
class_pred = outputs['class_probs'].data.cpu().numpy().argmax(axis=1)
batch_imgs = []
for bx in range(min(len(class_true), lim)):
orig_img = im[bx].transpose(1, 2, 0)
out_size = class_pred[bx].shape[::-1]
orig_img = cv2.resize(orig_img, tuple(map(int, out_size)))
orig_img = kwimage.ensure_alpha_channel(orig_img)
pred_heatmap = kwimage.Heatmap(
class_idx=class_pred[bx],
classes=harn.classes
)
true_heatmap = kwimage.Heatmap(
class_idx=class_true[bx],
classes=harn.classes
)
# TODO: scale up to original image size
pred_img = pred_heatmap.draw_on(orig_img, channel='idx', with_alpha=.5)
true_img = true_heatmap.draw_on(orig_img, channel='idx', with_alpha=.5)
true_img = kwimage.ensure_uint255(true_img)
pred_img = kwimage.ensure_uint255(pred_img)
true_img = kwimage.draw_text_on_image(
true_img, 'true', org=(0, 0), valign='top', color='blue')
pred_img = kwimage.draw_text_on_image(
pred_img, 'pred', org=(0, 0), valign='top', color='blue')
item_img = kwimage.stack_images([pred_img, true_img], axis=1)
batch_imgs.append(item_img)
toshow = kwimage.stack_images_grid(batch_imgs, chunksize=2, overlap=-32)
return toshow
def __getitem__(self, index):
import kwimage
# Load sample image and category
sample = self.sampler.load_positive(index, with_annots=False)
image = kwimage.atleast_3channels(sample['im'])[:, :, 0:3]
target = sample['tr']
image = kwimage.ensure_uint255(image)
if self.augmenter is not None:
det = self.augmenter.to_deterministic()
image = det.augment_image(image)
# Resize to input dimensinos
if self.input_dims is not None:
dsize = tuple(self.input_dims[::-1])
image = kwimage.imresize(image, dsize=dsize, letterbox=True)
class_id_to_idx = self.sampler.classes.id_to_idx
cid = target['category_id']
cidx = class_id_to_idx[cid]
im_chw = image.transpose(2, 0, 1) / 255.0
inputs = {
'rgb': torch.FloatTensor(im_chw),
}
labels = {
'class_idxs': cidx,
}
batch = {
'inputs': inputs,
'labels': labels,
}
return batch
fpath = ub.grabdata('https://i.redd.it/ywip9sbwysy71.jpg')
data = kwimage.imread(fpath)
subdata = data[242:-22, 22:300]
img = subdata
inty = integrate.cumtrapz(img, axis=0)
intx = integrate.cumtrapz(img, axis=1)
dery = np.gradient(img, axis=0)
derx = np.gradient(img, axis=1)
der_canvas = kwarray.normalize(kwimage.stack_images([dery, derx], axis=0))
int_canvas = kwarray.normalize(kwimage.stack_images([inty, intx], axis=0))
der_canvas = kwimage.ensure_uint255(der_canvas)
int_canvas = kwimage.ensure_uint255(int_canvas)
der_canvas = kwimage.draw_header_text(der_canvas, 'derivative', color='white')
int_canvas = kwimage.draw_header_text(int_canvas,
'antiderivative',
color='white')
canvas = kwimage.stack_images([der_canvas, int_canvas], axis=1)
# kwimage.imwrite('ftfy.jpg', canvas)
kwplot.autompl()
kwplot.imshow(canvas)