TFModel improvements #475
TFModel improvements #475
Conversation
Codecov Report
@@ Coverage Diff @@
## master #475 +/- ##
=========================================
Coverage ? 40.75%
=========================================
Files ? 139
Lines ? 14024
Branches ? 0
=========================================
Hits ? 5715
Misses ? 8309
Partials ? 0
Continue to review full report at Codecov.
|
| get_indices = np.vectorize(lambda c, arr=classes: np.where(c == arr)[0]) | ||
| value = get_indices(value) | ||
| classes = self.get_tensor_config(placeholder).get('classes') | ||
| if not isinstance(classes, int): |
There was a problem hiding this comment.
I don't understand it well but what if classes is int? Why can't be?
There was a problem hiding this comment.
Currently, TFModel is capable of working with custom class labels: [cats, dogs] for example. In this case, we need to manually transform such labels into int-classes, and this transform takes a lot of time. We don't need to do this in the case of integer classes.
| batch_size = get_batch_size(inputs, dynamic=True) | ||
| shape = get_shape(inputs) | ||
| ones = [1] * self.dim | ||
| if self.insert: |
There was a problem hiding this comment.
probably insert can be renamed to something related to add_last, add_first or something?
This PR proposes to:
Make
ConvBlockable to chain multiple layers, just likeTorchversion canSimplify logic of letter parsing, as well as adding capability of using
Rletter as separateBranchwith complex parametersSwap all arguments inside calls to
conv_blockto keyword onesAdd
squeeze-and-excitationversions ofResNetRe-check all the tests of model compilation
Add various attention modules: some of them are available through
S(stands for self-attention) letter, some of them are mods ofCombine