automl
automl copied to clipboard
google
Google Brain AutoML
I tried: - download pretrain checkpoint D0 and D7 - save model: `python model_inspect.py --runmode=saved_model --model_name=efficientdet-d0 --ckpt_path=efficientdet-d0 --saved_model_dir=/tmp/saved_model_0` - inference with image: `python model_inspect.py --runmode=saved_model_infer --saved_model_dir=/tmp/saved_model_0 --model_name=efficientdet-d0 --input_image=/tmp/train_all/00053190460d56c53cc3e57321387478.jpg --output_image_dir=out `...
If the loss is improving, the weights must be changing? how can the l2 loss not be changing? any push in the right direction towards debugging this would be greatly...
Has the ImageNet1K validation data and Imagenet21K training data been de-duplicated?
Have anyone managed to make a successful training on a Binary Classification of Grayscale images with TF2? I did manage to start training, but after 20 epochs, Validation accuracy was...
Hi, sorry to bother but I'm curious whether you will be releasing EfficientNetV2-lite model variants (as similar to their V1 counterparts)? Best regards, Sebastian
Hi, I am trying to use adaptive learning rates for the training process. Here is my config file: ''' num_classes: 31 label_map: {1: airplane, 2: antelope, 3: bear, 4: bicycle,...
Hi, I am training EfficientDet on a custom dataset. I started with freeze the backbone part. ('var_freeze_expr: '(efficientnet)'' in the hyperparameter file) And after 50 epochs, the mAP has achieved...
when should you upload your model into [https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/tf2_detection_zoo.md](url) so we can easily use pre-trained weights to train our custom model?
Gradual training strategy i.e training network for few epochs with all layers freezed , next resume training with unfreezing some last layers , finally training all layers for finetuning. can...
