big_transfer

big_transfer copied to clipboard

Bumps [numpy](https://github.com/numpy/numpy) from 1.18.4 to 1.22.0. Release notes Sourced from numpy's releases. v1.22.0 NumPy 1.22.0 Release Notes NumPy 1.22.0 is a big release featuring the work of 153 contributors spread...

dependabot[bot]

Bumps [tensorflow](https://github.com/tensorflow/tensorflow) from 2.2.0 to 2.7.2. Release notes Sourced from tensorflow's releases. TensorFlow 2.7.2 Release 2.7.2 This releases introduces several vulnerability fixes: Fixes a code injection in saved_model_cli (CVE-2022-29216) Fixes...

dependabot[bot]

Bumps [tensorflow-cpu](https://github.com/tensorflow/tensorflow) from 2.2.0 to 2.7.2. Release notes Sourced from tensorflow-cpu's releases. TensorFlow 2.7.2 Release 2.7.2 This releases introduces several vulnerability fixes: Fixes a code injection in saved_model_cli (CVE-2022-29216) Fixes...

dependabot[bot]

GRAD CAM

2

Hi! I would like to apply grad cam from here: https://keras.io/examples/vision/grad_cam/. The problem is that if I apply tfhub y just see one layer, what could I do?

movaldivia

In [Line 103 of input_pipeline_tf2_or_jax.py](https://github.com/google-research/big_transfer/blob/49afe42338b62af9fbe18f0258197a33ee578a6b/input_pipeline_tf2_or_jax.py#L103), why use `tf.image.flip_left_right` instead of `tf.image.random_flip_left_right`? From [tensorflow's doc](https://www.tensorflow.org/api_docs/python/tf/image/flip_left_right), `tf.image.flip_left_right` will always flip the image, without any randomness. It makes more sense to use `tf.image.random_flip_left_right`...

exiarepairii

I tried to finetune big transfer code for cifar 10 dataset using the colab provided in [TF Blog](https://blog.tensorflow.org/2020/05/bigtransfer-bit-state-of-art-transfer-learning-computer-vision.html) The dataset was split on 90% training and 10% validation. The steps...

abdul53saifee

Hi there In the function ```get_lr()``` in ```bit_hyperrule.py```, when step == 0, the returned learning rate is 0.0. I wanted to check if this is a bug or intentional?

danielamassiceti

TF2 weights shape wrong for 2 architectures

2

I've tried to load all provided TF2 model weights and found that 2 of them could not be loaded: - BiT-S-R50x3.h5 : `ValueError: Cannot assign to variable standardized_conv2d/kernel:0 due to...

shkarupa-alex

what's the meaning of Ex/cls

1

what's the meaning of Ex/cls

GuoQuanhao

Is there a way where we can specify a specific layer number and start training specific layers with BIT using tensorflow. Currently number of layers it shows 2 and when...

sumedhvdatar