Skip to content

v0.4.7: individual components can run independently and image treatment replicates that of Pytorch

Compare
Choose a tag to compare
@jrzaurin jrzaurin released this 04 Dec 16:50
· 577 commits to master since this release
v0.4.7
2fe4b49
This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
GPG key ID: 4AEE18F83AFDEB23
Expired
Learn about vigilant mode.

The treatment of the image datasets in WideDeepDataset replicates that of Pytorch. In particular this source code:

if isinstance(pic, np.ndarray):
    # handle numpy array
    if pic.ndim == 2:
        pic = pic[:, :, None]

In addition, I have added the possibility of using each of the model components in isolation and independently. This is, one could now use the wide, deepdense (either DeepDense or DeepDenseResnet), deeptext and deepimage independently.

Assets 2
Loading