Skip to content
This repository has been archived by the owner on Mar 19, 2024. It is now read-only.

Add registry for the model heads #75

Closed
wants to merge 18 commits into from
Closed
Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
18 commits
Select commit Hold shift + click to select a range
af844b3
Experiment with Blur data augmentation in swav training
prigoyal Aug 10, 2020
33628bc
Add cosine warm restart scheduler for full wave and half wave
prigoyal Aug 10, 2020
bb3ace8
Close stream and file loggers at the end of training
prigoyal Aug 10, 2020
5899157
Rewrite attrdict to have getattr and setattr for seamless attribute a…
prigoyal Aug 10, 2020
bbd8bcd
Rename engine to engines to make it clearer that there are multiple
prigoyal Aug 10, 2020
29af593
Rename distributed_train to run_distributed_engines for clarity
prigoyal Aug 10, 2020
8eac7db
Tensor input to loss functions to they follow the pytorch definitions
prigoyal Aug 10, 2020
f3bcae3
Make trainer as the main entry point and refactor task, trainer, step…
prigoyal Aug 10, 2020
7522060
Add a registry for the train steps in vissl
prigoyal Aug 10, 2020
3ac425b
Update model zoo and add more crops settings for swav trainings
prigoyal Aug 10, 2020
9bd7efe
Add a registry for data collators in vissl
prigoyal Aug 10, 2020
93b5c88
Rename PARAMS_FILE to WEIGHTS_INIT and PATH to PARAMS_FILE
prigoyal Aug 10, 2020
ba52eab
Rename ssl_hooks to hooks simply
prigoyal Aug 10, 2020
49b37bc
Rename ssl_losses to losses simply
prigoyal Aug 10, 2020
0bc77ba
Rename ssl_optimizers to optimizers for simplicity
prigoyal Aug 10, 2020
42dad13
Hard fail if specified model weights_init file does not exist
prigoyal Aug 10, 2020
9b005d4
Rename accuracy list meter parameters and also print meter names in c…
prigoyal Aug 10, 2020
8c7271e
Add registry for the model heads (#75)
prigoyal Aug 10, 2020
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Next Next commit
Experiment with Blur data augmentation in swav training
Differential Revision: D22842068

fbshipit-source-id: f73a2d4739a097afb29b38332dccf365b77fd4b8
  • Loading branch information
prigoyal authored and facebook-github-bot committed Aug 10, 2020
commit af844b31e0f71775fbc806891e51b583a6b27753
4 changes: 2 additions & 2 deletions MODEL_ZOO.md
Original file line number Diff line number Diff line change
Expand Up @@ -105,13 +105,13 @@ VISSL is 100% compatible with TorchVision ResNet models. You can benchmark these
- rn50w2 - in1k - 1000ep /mnt/vol/gfsai-bistro2-east/ai-group/bistro/gpu/prigoyal/ssl_framework/simclr_rn50w2_1000ep_simclr_8node_resnet_16_07_20.e1e3bbf0/model_final_checkpoint_phase999.torch
- rn50w4 - in1k - 1000ep
- rn101 - in1k - 100ep /mnt/vol/gfsai-bistro2-east/ai-group/bistro/gpu/prigoyal/ssl_framework/simclr_rn101_100ep_simclr_8node_resnet_16_07_20.1ff6cb4b/model_final_checkpoint_phase99.torch
- rn101 - in1k - 1000ep
- rn101 - in1k - 1000ep /mnt/vol/gfsai-bistro2-east/ai-group/bistro/gpu/prigoyal/ssl_framework/simclr_rn101_1000ep_simclr_8node_resnet_16_07_20.35063cea/model_final_checkpoint_phase999.torch

### SwAV
<!-- swav -->
- rn50 - 2x224 + 6x96 - 100ep - 8node: /mnt/vol/gfsai-bistro2-east/ai-group/bistro/gpu/prigoyal/ssl_framework/swav_in1k_rn50_100ep_swav_8node_resnet_27_07_20.7e6fc6bf/model_final_checkpoint_phase99.torch
- rn50 - 2x224 + 6x96 - 200ep - 8node: /mnt/vol/gfsai-bistro2-east/ai-group/bistro/gpu/prigoyal/ssl_framework/swav_in1k_rn50_200ep_swav_8node_resnet_27_07_20.bd595bb0/model_final_checkpoint_phase199.torch
- rn50 - 2x224 + 6x96 - 400ep - 8node:
- rn50 - 2x224 + 6x96 - 400ep - 8node: /mnt/vol/gfsai-bistro2-east/ai-group/bistro/gpu/prigoyal/ssl_framework/swav_in1k_rn50_400ep_swav_8node_resnet_27_07_20.a5990fc9/model_final_checkpoint_phase399.torch
- rn50 - 2x224 + 6x96 - 800ep - 8node:
- rn50 - 2x224 + 6x96 - 200ep - 1node - use queue:
- rn50 - 2x224 + 6x96 - 400ep - 1node - use queue:
Expand Down
10 changes: 4 additions & 6 deletions configs/config/pretrain/swav/swav_8node_resnet.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -85,10 +85,8 @@ config:
nesterov: False
# num_epochs: 100
# num_epochs: 200
# num_epochs: 400
# num_epochs: 500
# num_epochs: 600
num_epochs: 800
num_epochs: 400
# num_epochs: 800
# num_epochs: 1
# num_epochs: 2
# num_epochs: 5
Expand All @@ -112,8 +110,8 @@ config:
interval_scaling: [rescaled, fixed]
# lengths: [0.1, 0.9] # 100ep
# lengths: [0.05, 0.95] # 200ep
# lengths: [0.025, 0.975] # 400ep
lengths: [0.0125, 0.9875] # 800ep
lengths: [0.025, 0.975] # 400ep
# lengths: [0.0125, 0.9875] # 800ep
# lengths: [0.0128, 0.9872] # 1ep IG-1B
# lengths: [0.00641, 0.99359] # 2ep IG-1B
# lengths: [0.002563, 0.997437] # 5ep IG-1B = 50 ep IG-100M
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@ config:
total_num_crops: 2
size_crops: [224]
num_crops: [2]
crop_scales: [[0.14, 1]]
crop_scales: [[0.08, 1]]
- name: RandomHorizontalFlip
p: 0.5
- name: ImgPilColorDistortion
Expand Down