it's implimentation of multiple loss
Project description
In multiple loss package you get two loass functions.
- multilabelloss.
- contrastiveloss.
multilabelloss
Create a multilabelloss which can help as when we working on multilabel classification model. meaning of multilabel classification is that:-
-
develop a single model that will provide binary classification predictions for each of the num_class
-
In other words it will predict 'positive' or 'negative' for all class.
how to use tf-multilabelloss
from multiple_loss.multilabelloss import MultilabelLoss
predictions = Dense(len(num_class), activation="sigmoid")(x)
model = Model(inputs=base_model.input, outputs=predictions)
model.compile(optimizer='adam', loss=MultilabelLoss(num_class),metrics=['binary_accuracy'])
contrastiveloss
contrastive loss function use when we are working on Siamese networks.
Siamese networks :- A Siamese networks consists of two identical neural networks, each taking one of the two input images. The last layers of the two networks are then fed to a contrastive loss function , which calculates the similarity between the two images. Each image in the image pair is fed to one of these networks.
if you want to know more about contrastive
from multiple_loss.contrastive_loss import contrastive_loss_with_margin
rms = RMSprop()
model.compile(loss=contrastive_loss_with_margin(margin=1), optimizer=rms)
history = model.fit([tr_pairs[:,0], tr_pairs[:,1]], tr_y, epochs=20, batch_size=128, validation_data=([ts_pairs[:,0], ts_pairs[:,1]], ts_y))
installation
pip install multiple-loss==0.0.7
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
File details
Details for the file multiple_loss-0.0.7.tar.gz
.
File metadata
- Download URL: multiple_loss-0.0.7.tar.gz
- Upload date:
- Size: 14.7 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.4.2 importlib_metadata/4.8.1 pkginfo/1.7.1 requests/2.26.0 requests-toolbelt/0.9.1 tqdm/4.62.3 CPython/3.9.7
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 71e315fbcdb57bfaf905d10d76e9d099c31f53d1837edac7e1d684282a91daa8 |
|
MD5 | 628b33534f0ddf1ed9848011e34359f9 |
|
BLAKE2b-256 | e5c5ae08f66527bcb1fcfdd259e3a2444b2357ad7dc617e244fca802701795b4 |
Provenance
File details
Details for the file multiple_loss-0.0.7-py3-none-any.whl
.
File metadata
- Download URL: multiple_loss-0.0.7-py3-none-any.whl
- Upload date:
- Size: 15.4 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.4.2 importlib_metadata/4.8.1 pkginfo/1.7.1 requests/2.26.0 requests-toolbelt/0.9.1 tqdm/4.62.3 CPython/3.9.7
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | db19b8b311ba0d48e1a3e1c9420f821287538cc69926b6a6d6520c7c989a81a0 |
|
MD5 | a8785ee6471427bb34a7e93e3c386fee |
|
BLAKE2b-256 | 3e140d7f0336fa5574909eed723cbe45337fd441409ccf3691e8c41063a9169d |