def on_batch_end(self, state: State):
names = state.batch_in[self.outpath_key]
images = state.batch_in[self.input_key]
images = utils.tensor_to_ndimage(images.detach().cpu(), dtype=np.uint8)
for image, name in zip(images, names):
fname = self.get_image_path(state, name, self.filename_suffix)
imageio.imwrite(fname, image)
def on_batch_end(self, state: State):
names = state.batch_in[self.outpath_key]
images = state.batch_in[self.input_key]
masks = state.batch_out[self.output_key]
images = utils.tensor_to_ndimage(images.detach().cpu())
for name, image, mask in zip(names, images, masks):
image = mask_to_overlay_image(image, mask, self.mask_strength)
fname = self.get_image_path(state, name, self.filename_suffix)
imageio.imwrite(fname, image)
def on_batch_end(self, runner: IRunner):
"""Save batch of images.
Args:
runner (IRunner): current runner
"""
names = runner.input[self.outpath_key]
images = runner.input[self.input_key]
images = utils.tensor_to_ndimage(images.detach().cpu(), dtype=np.uint8)
for image, name in zip(images, names):
fname = self._get_image_path(runner.logdir, name)
imageio.imwrite(fname, image)
def on_batch_end(self, runner: IRunner):
"""Save batch of images with overlay.
Args:
runner (IRunner): current runner
"""
names = runner.input[self.outpath_key]
images = runner.input[self.input_key]
masks = runner.output[self.output_key]
images = utils.tensor_to_ndimage(images.detach().cpu())
for name, image, mask in zip(names, images, masks):
image = mask_to_overlay_image(image, mask, self.mask_strength)
fname = self._get_image_path(runner.logdir, name)
imageio.imwrite(fname, image)
def on_batch_end(self, runner: IRunner):
"""Batch end hook.
Args:
runner (IRunner): current runner
"""
lm = runner.loader_name
names = runner.input.get(self.name_key, [])
features = runner.input[self.input_key].detach().cpu()
images = utils.tensor_to_ndimage(features)
logits = runner.output[self.output_key]
logits = (
torch.unsqueeze_(logits, dim=1)
if len(logits.shape) < 4
else logits
)
if self.mask_type == "soft":
probabilities = torch.sigmoid(logits)
else:
probabilities = F.softmax(logits, dim=1)
probabilities = probabilities.detach().cpu().numpy()
masks = []
for probability in probabilities:
mask = np.zeros_like(probability[0], dtype=np.int32)
for i, ch in enumerate(probability):
mask[ch >= self.threshold] = i + 1
masks.append(mask)
for index, (image, mask) in enumerate(zip(images, masks)):
try:
suffix = names[index]
except IndexError:
suffix = f"{self.counter:06d}"
self.counter += 1
mask = label2rgb(mask, bg_label=0)
image = (
image * (1 - self.mask_strength) + mask * self.mask_strength
)
image = (image * 255).clip(0, 255).round().astype(np.uint8)
filename = f"{self.out_prefix}/{lm}/{suffix}.jpg"
imageio.imwrite(filename, image)
def on_batch_end(self, state: State):
names = state.batch_in[self.outpath_key]
images = state.batch_in[self.input_key]
gtmasks = state.batch_in[self.input_target_key]
images = utils.tensor_to_ndimage(images.detach().cpu())
gtmasks = gtmasks.detach().cpu().squeeze(1).numpy()
predmasks = state.batch_out[self.output_key]
# print('img %s, gt %s, pred %s' %(images.shape, gtmasks.shape, predmasks.shape))
for name, image, gtmask, predmask in zip(names, images, gtmasks,
predmasks):
# image = mask_to_overlay_image(image, mask, self.mask_strength)
dice = dice_score(gtmask, predmask)
self.dice_list.append(dice)
plot_obj = PlotSeg2Image(image[..., 1])
plot_obj.put_on_mask(gtmask, color='r', is_bbox_on=False)
plot_obj.put_on_mask(predmask, color='g', is_bbox_on=False)
fname = self.get_image_path(state, name, '%0.4f' % dice)
# print('check2:', str(fname))
plot_obj.save_fig(fname)
model=model,
loader=infer_loader,
resume=f"{logdir}/checkpoints/best.pth",
verbose=False,
)
print(type(predictions))
print(predictions.shape)
# In[22]:
threshold = 0.5
max_count = 5
for i, (features, logits) in enumerate(zip(test_dataset, predictions)):
image = utils.tensor_to_ndimage(features["image"])
mask_ = torch.from_numpy(logits[0]).sigmoid()
mask = utils.detach(mask_ > threshold).astype("float")
show_examples(name="", image=image, mask=mask)
if i >= max_count:
break
# ## Model tracing
#
# Catalyst allows you to use Runner to make [tracing](https://pytorch.org/docs/stable/jit.html) models.
#
# > How to do this in the Config API, we wrote in [our blog (issue \#2)](https://github.com/catalyst-team/catalyst-info#catalyst-info-2-tracing-with-torchjit)
#
