Age | Commit message (Collapse) | Author |
|
# Conflicts:
# models/hpm.py
# models/model.py
# models/rgb_part_net.py
# utils/configuration.py
# utils/triplet_loss.py
|
|
1. Separate FCs and triplet losses for HPM and PartNet
2. Remove FC-equivalent 1x1 conv layers in HPM
3. Support adjustable learning rate schedulers
|
|
# Conflicts:
# models/part_net.py
# models/rgb_part_net.py
|
|
|
|
# Conflicts:
# models/rgb_part_net.py
|
|
This is a HUGE performance optimization, up to 2x faster than before. Mainly because of the replacement of randomized for-loop with randomized tensor.
|
|
|
|
1. Triplet loss function and weight init function haven't been implement yet
2. Tuplize features returned by auto-encoder for later unpack
3. Correct comment error in auto-encoder
4. Swap batch_size dim and time dim in HPM and PartNet in case of redundant transpose
5. Find backbone problems in HPM and disable it temporarily
6. Make feature structure by HPM consistent to that by PartNet
7. Fix average pooling dimension issue and incorrect view change in HP
|
|
1. Register list of torch.nn.Module to the network using torch.nn.ModuleList
2. Fix operation error in squeeze list of tensor
3. Replace squeeze with view in HP in case batch size is 1
|
|
1. Let FocalConv block capable of processing frames in all batches
2. Correct input dims of TFA and output dims of HP
3. Change torch.unsqueeze and torch.cat to torch.stack
|
|
|
|
|