include evaluation table (d8ae1a2e) · Commits · Softwareprojekt 2018 - Jason Marinco Rudolf Samuel / O Caption My Caption

README.md

+33 −5

Original line number	Diff line number	Diff line
		@@ -21,17 +21,33 @@ python setup.py install
		#### Retraining

		##### Singlelabel Model
		How to retrain Singlelabel
		* How to retrain Singlelabel:
		TODO

		* Results:
		[Trained model (default)](/models/singlelabel_default/)
		[Trained model (+Hyperparameters)](/models/singlelabel_hp/)


		##### ResNet Model
		How to retrain ResNet
		* How to retrain ResNet:

		* Results:
		[Trained model (default)](/models/resnet_default/)
		[Trained model (+Hyperparameters)](/models/resnet_hp/)

		##### Multilabel Model
		How to retrain multilabel
		* How to retrain multilabel:

		* Results:
		[Trained model (default)](/models/multilabel_default/)
		[Trained model (+Hyperparameters)](/models/multilabel_hp/)


		#### Visualization (Lucid)
		We used [https://github.com/tensorflow/lucid](https://github.com/tensorflow/lucid) (for creating own model have a look at this [colab-notebook](https://colab.research.google.com/drive/1PPzeZi5sBN2YRlBmKsdvZPbfYtZI-pHl#scrollTo=06q00d8zvwqc))
		Chosen Visualization style [Activation Grid](https://colab.research.google.com/github/tensorflow/lucid/blob/master/notebooks/building-blocks/ActivationGrid.ipynb)
		* We used [https://github.com/tensorflow/lucid](https://github.com/tensorflow/lucid) (for creating own model have a look at this [colab-notebook](https://colab.research.google.com/drive/1PPzeZi5sBN2YRlBmKsdvZPbfYtZI-pHl#scrollTo=06q00d8zvwqc))

		* Chosen Visualization style [Activation Grid](https://colab.research.google.com/github/tensorflow/lucid/blob/master/notebooks/building-blocks/ActivationGrid.ipynb)
		![ActivationGrid](https://storage.googleapis.com/lucid-static/building-blocks/notebook_heroes/activation-grid.jpeg)

		* Workflow:
		@@ -43,6 +59,18 @@ See [example notebook](/lucid/Visualization - singlelabel.ipynb)
		### LSTM


		### Evaluation
		\| Measure \| Singlelabel \| Multilabel \| Show & Tell (2015) \| SOTA (2017) \|
		\| -------------:\|:-------------:\|:-----------:\|:------------------:\|:-----------:\|
		\| CIDEr \| 0.366 \| 0.375 \| 0.943 \| 1.179 \|
		\| Meteor \| 0.141 \| 0.140 \| 0.254 \| 0.277 \|
		\| Rouge-L \| 0.402 \| 0.407 \| 0.530 \| 0.573 \|
		\| Bleu-1 \| 0.514 \| 0.511 \| 0.713 \| 0.795 \|
		\| Bleu-2 \| 0.338 \| 0.336 \| 0.542 \| 0.635 \|
		\| Bleu-3 \| 0.217 \| 0.217 \| 0.407 \| 0.485 \|
		\| Bleu-4 \| 0.141 \| 0.140 \| 0.309 \| 0.363 \|
		\| SPICE \| 0.092 \| 0.089 \| 0.182 \| 0.213 \|

		## Demo

		### CNN

Admin message