Remove unwanted loss function in depth_estimation.py #1506
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
The depth_estimation.py example implements custom_loss function (i.e. calculate_loss) using 1. Structural similarity index(SSIM), 2. L1-loss, or Point-wise depth in our case and 3. Depth smoothness loss. The same loss function used in train_step also. But still model.compile() was given another loss function `cross_entropy = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True, reduction="none")` which has to be removed as it has no effect and also creates unwanted confusion. Hence deleted the unwanted loss defined in model.compile()
The depth_estimation.py example implements custom_loss function (i.e. calculate_loss) using 1. Structural similarity index(SSIM), 2. L1-loss, or Point-wise depth in our case and 3. Depth smoothness loss. The same loss function used in train_step also. But still model.compile() was given another loss function cross_entropy = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True, reduction="none") which has to be removed as it has no effect and also creates unwanted confusion. Hence deleted the unwanted loss defined in model.compile()
The depth_estimation.py example implements custom_loss function (i.e. calculate_loss) using 1. Structural similarity index(SSIM), 2. L1-loss, or Point-wise depth in our case and 3. Depth smoothness loss. The same loss function used in train_step also. But still model.compile() was given another loss function cross_entropy = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True, reduction="none") which has to be removed as it has no effect and also creates unwanted confusion. Hence deleted the unwanted loss defined in model.compile()
pcoet
approved these changes
Sep 6, 2023
|
@SuryanarayanaY Do you know how to resolve the docker-image failure? Then we can merge this... |
|
@sachinprasadhs mentioned that this issue should be fixed, so I'll go ahead and merge the PR. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
The depth_estimation.py example implements
custom_lossfunction (i.e. calculate_loss) using 1. Structural similarity index(SSIM), 2. L1-loss, or Point-wise depth in our case and 3. Depth smoothness loss. The same loss function used intrain_stepalso. But stillmodel.compile()was given another loss functioncross_entropy = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True, reduction="none")which has to be removed as it has no effect and also creates unwanted confusion.Hence deleted the unwanted loss defined in
model.compile()Fixes #969