Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Change EfficientNetB0 to EfficientNetB1 in the final line #259

Merged
merged 4 commits into from
Sep 24, 2020
Merged

Change EfficientNetB0 to EfficientNetB1 in the final line #259

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
d766dbe
Bump B0 to B1 in the final line
sayakpaul Sep 23, 2020
77b25e9
Update image_classification_efficientnet_fine_tuning.md
sayakpaul Sep 24, 2020
bc5343e
Bumped to B1
sayakpaul Sep 24, 2020
3de9373
Updated the lines directly on ipynb
sayakpaul Sep 24, 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
4 changes: 2 additions & 2 deletions examples/vision/image_classification_efficientnet_fine_tuning.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -491,7 +491,7 @@ def unfreeze_model(model):
!tar -xf noisy_student_efficientnet-b1.tar.gz
```

Then use the script efficientnet_weight_update_util.py to convert ckpt file to h5 file.
Then use the script [efficientnet_weight_update_util.py](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/python/keras/applications/efficientnet_weight_update_util.py) to convert ckpt file to h5 file.

```
!python efficientnet_weight_update_util.py --model b1 --notop --ckpt \
Expand All @@ -501,6 +501,6 @@ def unfreeze_model(model):
When creating model, use the following to load new weight:

```python
model = EfficientNetB0(weights="efficientnetb1_notop.h5", include_top=False)
model = EfficientNetB1(weights="efficientnetb1_notop.h5", include_top=False)
```
"""
6 changes: 3 additions & 3 deletions examples/vision/ipynb/image_classification_efficientnet_fine_tuning.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -687,7 +687,7 @@
"!tar -xf noisy_student_efficientnet-b1.tar.gz\n",
"```\n",
"\n",
"Then use the script efficientnet_weight_update_util.py to convert ckpt file to h5 file.\n",
"Then use the script [efficientnet_weight_update_util.py](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/python/keras/applications/efficientnet_weight_update_util.py) to convert ckpt file to h5 file.\n",
"\n",
"```\n",
"!python efficientnet_weight_update_util.py --model b1 --notop --ckpt \\\n",
Expand All @@ -697,7 +697,7 @@
"When creating model, use the following to load new weight:\n",
"\n",
"```python\n",
"model = EfficientNetB0(weights=\"efficientnetb1_notop.h5\", include_top=False)\n",
"model = EfficientNetB1(weights=\"efficientnetb1_notop.h5\", include_top=False)\n",
"```"
]
}
Expand Down Expand Up @@ -730,4 +730,4 @@
},
"nbformat": 4,
"nbformat_minor": 0
}
}
5 changes: 2 additions & 3 deletions examples/vision/md/image_classification_efficientnet_fine_tuning.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -720,8 +720,7 @@ download the checkpoint. As example, here we download noisy-student version of B
!tar -xf noisy_student_efficientnet-b1.tar.gz
```

Then use the script efficientnet_weight_update_util.py to convert ckpt file to h5 file.

Then use the script [efficientnet_weight_update_util.py](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/python/keras/applications/efficientnet_weight_update_util.py) to convert ckpt file to h5 file.
```
!python efficientnet_weight_update_util.py --model b1 --notop --ckpt \
efficientnet-b1/model.ckpt --o efficientnetb1_notop.h5
Expand All @@ -730,5 +729,5 @@ Then use the script efficientnet_weight_update_util.py to convert ckpt file to h
When creating model, use the following to load new weight:

```python
model = EfficientNetB0(weights="efficientnetb1_notop.h5", include_top=False)
model = EfficientNetB1(weights="efficientnetb1_notop.h5", include_top=False)
```