maxmustermann/DeepLearningExamples
1
0
Fork 0
Code Issues Pull requests Projects Releases Wiki Activity

[UNet medical/TF] Loss update

Browse source
This commit is contained in:
kkudrynski 2021-02-02 15:50:38 +01:00
parent 8eca836a2e
commit 32e921cd99
3 changed files with 3 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1
TensorFlow2/Segmentation/UNet_Medical/README.md
View file

@ -634,6 +634,5 @@ February 2020
### Known issues
* Some set-ups suffer from a `ncclCommInitRank failed: unhandled system error`. This is a known issue with NCCL 2.7.5. The issue is solved in NCCL 2.7.8, which can be applied by changing the first line the Dockerfile from `ARG FROM_IMAGE_NAME=nvcr.io/nvidia/tensorflow:20.06-tf2-py3` to `ARG FROM_IMAGE_NAME=nvcr.io/nvidia/tensorflow:20.08-tf2-py3` and rebuilding the docker image.
* For TensorFlow 2.0 the training performance using AMP and XLA is around 30% lower than reported here. The issue was solved in TensorFlow 2.1.

2
TensorFlow2/Segmentation/UNet_Medical/requirements.txt
View file

@ -1,3 +1,3 @@
Pillow
tf2onnx
munch
munch

4
TensorFlow2/Segmentation/UNet_Medical/runtime/losses.py
View file

@ -32,8 +32,8 @@ def partial_losses(predict, target):
flat_labels = tf.reshape(target,
[tf.shape(input=predict)[0], -1, n_classes])
crossentropy_loss = tf.reduce_mean(input_tensor=tf.keras.backend.binary_crossentropy(output=flat_logits,
target=flat_labels),
crossentropy_loss = tf.reduce_mean(input_tensor=tf.nn.softmax_cross_entropy_with_logits(logits=flat_logits,
labels=flat_labels),
name='cross_loss_ref')
dice_loss = tf.reduce_mean(input_tensor=1 - dice_coef(tf.keras.activations.softmax(flat_logits, axis=-1),