Hvt #146
Merged
Hvt #146
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Closed
|
The code of HVT is released and models are in the 'models' folder. |
xperzy
reviewed
Dec 27, 2021
image_classification/HVT/README.md
Outdated
|
|
||
| The official pytorch implementation is [here](). | ||
|
|
||
| This implementation is developed by [PaddleViT](https://github.com/zhuang-group/HVT). |
There was a problem hiding this comment.
Use the correct PaddleViT link and official implementation link
image_classification/HVT/hvt.py
Outdated
| droppath=config.MODEL.DROPPATH) | ||
| return model | ||
|
|
||
| # from config import get_config |
There was a problem hiding this comment.
Please remove unrelated code
image_classification/HVT/hvt.py
Outdated
| def build_hvt(config): | ||
| """build deit model using config""" | ||
| model = HVT(image_size=config.DATA.IMAGE_SIZE, | ||
| in_channels=config.MODEL.TRANS.IN_CHANNELS, |
There was a problem hiding this comment.
Please use correct code indent
image_classification/HVT/hvt.py
Outdated
| from droppath import DropPath | ||
|
|
||
|
|
||
| def print_model_named_params(model): |
There was a problem hiding this comment.
Please remove unrelated/debug code
| criterion_val = nn.CrossEntropyLoss() | ||
|
|
||
|
|
||
| # 5. Create Teacher model |
|
|
||
| # STEP 5: Define optimizer and lr_scheduler | ||
| # set lr according to batch size and world size (hacked from Swin official code and modified for CSwin) | ||
| if config.TRAIN.LINEAR_SCALED_LR is not None: |
There was a problem hiding this comment.
There is no LINEAR_SCALED_LR in config.py, please add this keyword in config.py
| # See the License for the specific language governing permissions and | ||
| # limitations under the License. | ||
|
|
||
| """DeiT training/validation using single GPU """ |
| parser.add_argument('-pretrained', type=str, default=None) | ||
| parser.add_argument('-resume', type=str, default=None) | ||
| parser.add_argument('-last_epoch', type=int, default=None) | ||
| parser.add_argument('-teacher_model', type=str, default=None) |
| # STEP 5: Create Teacher model | ||
| teacher_model = None | ||
|
|
||
| # STEP 6: Define optimizer and lr_scheduler |
There was a problem hiding this comment.
Use similar "if condition " as main_multi_gpu.py
add argument -output for image_classification(close #142)
add missing world size for lr linear scale in main_multi_gpu
xperzy
reviewed
Dec 27, 2021
xperzy
approved these changes
Dec 28, 2021
|
LGTM |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Code of HVT is released