simclr

simclr copied to clipboard

I think that in case when we are using only contrastive loss, dividing it by the number of replicas isn't doing what it is supposed to do. For every replica,...

piotrmwojcik

Data augument for supervised models

2

Hello, does the supervised comparison model you provided here use the same data enhancement method（random crop (with resize and random flip), random color distortion, and random Gaussian blur）? 

Dashi-1997

'_UserObject' object has no attribute 'summary'

4

Hello, I'm trying to load a r50_1x_sk0/saved_model of pretrained checkpoint-tf2 of simCLRv2, to just fine tuned but I'm coming across this error: '_UserObject' object has no attribute 'summary' I would...

aynesss

Bumps [tensorflow](https://github.com/tensorflow/tensorflow) from 1.15.4 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]

Is the trained projection head available?

7

I am interested in downloading a pre-trained simCLR model with the projection head, to retrieve the latent features z, upon which the contrastive loss was applied. Is this layer +...

lkshrsch

Is training on multiple GPUs possible?

2

In the [environment setup](https://github.com/google-research/simclr#enviroment-setup) it's stated that "Our code can also run on a single GPU. It does not support multi-GPUs, for reasons such as global BatchNorm and contrastive loss...

lukasugar

Hello, I have a question after reading your paper. You mentioned that it's beneficial to define the contrastive loss on zi’s rather than hi’s, but I'm not sure what's the...

garynlfd

I use TF2.4.1 I would like to finetune the savedModel of pretrained .I write this : ``` target_model_path = "gs://simclr-checkpoints-tf2/simclrv1/pretrain/1x/saved_model/" def create_model(): baseModel = tf.saved_model.load(target_model_path) baseModel= tf.saved_model.save('./saved_model.h5') headModel = baseModel.output...

aynesss

TF2.4. Here is what I write to begin finetuning: ``` target_model_path = "gs://simclr-checkpoints-tf2/simclrv2/pretrained/r50_2x_sk1/saved_model" saved_model = tf.keras.models.load_model(target_model_path) saved_model.model.save_weights('./weights.h5') simclr_model.load_weights('./weights.h5', by_name=True, skip_mismatch=True) ``` But I found many lines :+1: ``` WARNING:absl:Importing a...

aynesss

After I run the simclr on custom dataset, I got checkpoints and I tried to load checkpoints to resnet model like below ; import tensorflow as tf from tensorflow.keras.models import...

fatmacelebi