- 01 12月, 2020 1 次提交
-
-
由 jrzaurin 提交于
-
- 28 11月, 2020 1 次提交
-
-
由 jrzaurin 提交于
all started by trying to add a line so that the builder accepted 2D images (or in general images of dim different than 3. But it ended up by adding functionalities so that each individual component (wide, deepdense, deeptext and deepimage) can be used individually
-
- 28 9月, 2020 1 次提交
-
-
由 jrzaurin 提交于
Added a condition to account for 2D images (images with no color channels). This way we replicate exactly what ToTensor does within the WideDeepDataset class
-
- 13 9月, 2020 1 次提交
-
-
由 jrzaurin 提交于
-
- 12 9月, 2020 1 次提交
-
-
由 jrzaurin 提交于
Modified documentation and added doc test. Also changed some of the code in the main WideDeep class to increase test coverage
-
- 06 9月, 2020 1 次提交
-
-
由 jrzaurin 提交于
-
- 31 8月, 2020 1 次提交
-
-
由 jrzaurin 提交于
Finished implementation of DeepDenseResnet. Adapated DeepDense code for consistency (simply renamed 'embed_p' to 'embed_dropout'). Adapted docs and README. Included unit test for DeepDenseResnet.
-
- 30 8月, 2020 3 次提交
- 08 8月, 2020 3 次提交
-
-
由 jrzaurin 提交于
-
由 jrzaurin 提交于
Changed loss value printed on the screen for regression. From RMSE to MSE. Adjusted documentation. Also changed unit test for callbacks to the new Linear-Embedding implementation, which implied incresing delta for early stopping
-
由 jrzaurin 提交于
#18 Implementation of the Linear model that is the wide component via an Embedding layer. This helps optimize speed and memory usage. Adapted all the submodules accordingly
-
- 19 7月, 2020 1 次提交
-
-
由 jrzaurin 提交于
Changed README, wide_deep.py, docs, and examples according to the new metrics. Only thing left is adjust the notebooks
-
- 12 7月, 2020 1 次提交
-
-
由 jrzaurin 提交于
fixed a bug related to the focal loss. Remove activations before the losses in the fit method in WideDeep. Sigmoid and logSoftmax happen within the loss. Added activations in the train and eval step and in the predict method
-
- 11 7月, 2020 1 次提交
-
-
由 jrzaurin 提交于
Adapted the examples to the small code changes. Replace add_ with add in WideDeep to avoid annoying warnings. Replace output_dim with pred_dim in Wide for consistentcy
-
- 10 7月, 2020 2 次提交
- 07 7月, 2020 1 次提交
-
-
由 jrzaurin 提交于
-
- 04 7月, 2020 1 次提交
-
-
由 jrzaurin 提交于
-
- 27 6月, 2020 2 次提交
- 03 5月, 2020 1 次提交
-
-
由 jrzaurin 提交于
-
- 28 4月, 2020 1 次提交
-
-
由 Minjin Choi 提交于
Deal with when either deeptext or deepimage does not exist.
-
- 03 2月, 2020 2 次提交
- 19 12月, 2019 1 次提交
-
-
由 jrzaurin 提交于
-
- 17 12月, 2019 1 次提交
-
-
由 jrzaurin 提交于
fixed bug related to the activation function in the case of multiclass classification. F.cross_entropy already applies logSoftmax
-
- 02 12月, 2019 1 次提交
-
-
由 jrzaurin 提交于
-
- 01 12月, 2019 2 次提交
- 30 11月, 2019 1 次提交
-
-
由 jrzaurin 提交于
-
- 26 11月, 2019 3 次提交
- 25 11月, 2019 1 次提交
-
-
由 jrzaurin 提交于
-
- 01 11月, 2019 2 次提交
- 30 10月, 2019 1 次提交
-
-
由 jrzaurin 提交于
-
- 28 10月, 2019 1 次提交
-
-
由 jrzaurin 提交于
-