Focused crawls are collections of frequently-updated webcrawl data from narrow (as opposed to broad or wide) web crawls, often focused on a single domain or subdomain.
When attempting to download cityscapes_2048x1024 I got: ./download-models.sh: line 721: download_fcn_resnet18_cityscapes_2048x512: command not found
It looks like there was a typo, and line 721 needs to be changed from: download_fcn_resnet18_cityscapes_2048x512 to download_fcn_resnet18_cityscapes_2048x1024
I trained > 100k, the loss looks fine, the bounding box looks too much, but the mask looks very wrong. Is it the visualization bug or we need more training?
In file binary segmentation (camvid).ipynb, block 5, there is:
# Lets look at data we have
dataset = Dataset(x_train_dir, y_train_dir, classes=['car', 'pedestrian'])
image, mask = dataset[5] # get some sample
visualize(
image=image,
cars_mask=mask[..., 0].squeeze(),
sky_mask=mask[..., 1].squeeze(),
background_mask=mask[..., 2].squeeze(),
)
Description
In some rare cases, for example, when you need to finetune a large model on a small dataset the majoring part of training loop is waiting for saving model checkpoints to a hard drive.
Proposal
Would be logically to add a CheckpointCallback with parameter save_n_best=0 to a configuration and do not store best checkpoints and instead use the latest state of the model.
In 'pointnet2/scannet/preprocessing/collect_scannet_scenes.py' line #17, we refer to 'scannet_all.txt' file. It would be helpful if you guide where to get or how to generate this file?
This is an official implementation of semantic segmentation for our TPAMI paper "Deep High-Resolution Representation Learning for Visual Recognition". https://arxiv.org/abs/1908.07919
