def net_process(self,
image: np.ndarray,
flip: bool = True) -> torch.Tensor:
""" Feed input through the network.
In addition to running a crop through the network, we can flip
the crop horizontally, run both crops through the network, and then
average them appropriately. Afterwards, apply softmax, then convert
the prediction to the label taxonomy.
Args:
- image:
- flip: boolean, whether to average with flipped patch output
Returns:
- output: Pytorch tensor representing network predicting in evaluation
taxonomy (not necessarily model taxonomy)
"""
input = torch.from_numpy(image.transpose((2, 0, 1))).float()
normalize_img(input, self.mean, self.std)
input = input.unsqueeze(0)
if self.use_gpu:
input = input.cuda()
if flip:
# add another example to batch dimension, that is the flipped crop
input = torch.cat([input, input.flip(3)], 0)
with torch.no_grad():
output = self.model(input)
_, _, h_i, w_i = input.shape
_, _, h_o, w_o = output.shape
if (h_o != h_i) or (w_o != w_i):
output = F.interpolate(output, (h_i, w_i),
mode='bilinear',
align_corners=True)
prediction_conversion_req = self.model_taxonomy != self.eval_taxonomy
if prediction_conversion_req:
# Either (model_taxonomy='naive', eval_taxonomy='test_dataset')
# Or (model_taxonomy='universal', eval_taxonomy='test_dataset')
output = self.tc.transform_predictions_test(
output, self.args.dataset)
else:
# model & eval tax match, so no conversion needed
assert self.model_taxonomy in ['universal', 'test_dataset']
# todo: determine when .cuda() needed here
output = self.softmax(output)
if flip:
# take back out the flipped crop, correct its orientation, and average result
output = (output[0] + output[1].flip(2)) / 2
else:
output = output[0]
# output = output.data.cpu().numpy()
# convert CHW to HWC order
# output = output.transpose(1, 2, 0)
# output = output.permute(1,2,0)
return output
def net_process(self, image: np.ndarray, flip: bool = True):
""" Feed input through the network.
In addition to running a crop through the network, we can flip
the crop horizontally, run both crops through the network, and then
average them appropriately.
Args:
- model:
- image:
- flip: boolean, whether to average with flipped patch output
Returns:
- output:
"""
input = torch.from_numpy(image.transpose((2, 0, 1))).float()
normalize_img(input, self.mean, self.std)
input = input.unsqueeze(0)
if self.use_gpu:
input = input.cuda()
if flip:
# add another example to batch dimension, that is the flipped crop
input = torch.cat([input, input.flip(3)], 0)
with torch.no_grad():
output = self.model(input)
_, _, h_i, w_i = input.shape
_, _, h_o, w_o = output.shape
if (h_o != h_i) or (w_o != w_i):
output = F.interpolate(output, (h_i, w_i),
mode='bilinear',
align_corners=True)
if self.output_taxonomy == 'universal':
output = self.softmax(output)
elif self.output_taxonomy == 'test_dataset':
output = self.convert_pred_to_label_tax_and_softmax(output)
else:
print('Unrecognized output taxonomy. Quitting....')
quit()
# print(time.time() - start1, image_scale.shape, h, w)
if flip:
# take back out the flipped crop, correct its orientation, and average result
output = (output[0] + output[1].flip(2)) / 2
else:
output = output[0]
# output = output.data.cpu().numpy()
# convert CHW to HWC order
# output = output.transpose(1, 2, 0)
# output = output.permute(1,2,0)
return output
def test_normalize_img_test_mean_only():
"""
Take image of shape HWC, i.e. (2 x 2 x 3)
"""
image = np.array([[[20, 22, 24], [26, 28, 30]],
[[32, 34, 36], [38, 40, 42]]]).astype(np.uint8)
input = torch.from_numpy(image.transpose((2, 0, 1))).float()
# tensor is now CHW, i.e. (3,2,2)
mean = [30, 30, 30]
normalize_img(input, mean)
# subtract 30 from all entries
gt_input = torch.tensor([[[-10, -8, -6], [-4, -2, 0]],
[[2, 4, 6], [8, 10, 12]]])
gt_input = gt_input.permute(2, 0, 1).float()
assert torch.allclose(input, gt_input)
assert isinstance(input, torch.Tensor)