From a08d963b084f3c34d8daa8223cb7292f2a157199 Mon Sep 17 00:00:00 2001 From: Yiheng Wang Date: Mon, 15 May 2023 16:21:45 +0800 Subject: [PATCH] remove duplicate link and modify default dataset dir Signed-off-by: Yiheng Wang --- .../configs/train_autoencoder.json | 2 +- models/brats_mri_generative_diffusion/docs/README.md | 6 +++--- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/models/brats_mri_generative_diffusion/configs/train_autoencoder.json b/models/brats_mri_generative_diffusion/configs/train_autoencoder.json index f6efce12..28136f51 100644 --- a/models/brats_mri_generative_diffusion/configs/train_autoencoder.json +++ b/models/brats_mri_generative_diffusion/configs/train_autoencoder.json @@ -8,7 +8,7 @@ "device": "$torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')", "ckpt_dir": "$@bundle_root + '/models'", "tf_dir": "$@bundle_root + '/eval'", - "dataset_dir": "/workspace/data/medical/Task01_BrainTumour", + "dataset_dir": "/workspace/data/medical", "pretrained": false, "perceptual_loss_model_weights_path": null, "train_batch_size": 2, diff --git a/models/brats_mri_generative_diffusion/docs/README.md b/models/brats_mri_generative_diffusion/docs/README.md index 6941b054..f081ca3b 100644 --- a/models/brats_mri_generative_diffusion/docs/README.md +++ b/models/brats_mri_generative_diffusion/docs/README.md @@ -7,7 +7,7 @@ This model is trained on BraTS 2016 and 2017 data from [Medical Decathlon](http: This model is a generator for creating images like the Flair MRIs based on BraTS 2016 and 2017 data. It was trained as a 3d latent diffusion model and accepts Gaussian random noise as inputs to produce an image output. The `train_autoencoder.json` file describes the training process of the variational autoencoder with GAN loss. The `train_diffusion.json` file describes the training process of the 3D latent diffusion model. -In this bundle, the autoencoder uses perceptual loss, which is based on ResNet50 with pre-trained weights (The network is frozen and will not be trained in the bundle). In default, the `pretrained` parameter is specified as `False` in `train_autoencoder.json`. To ensure correct training, changing the default settings is necessary. There are two ways to utilize pretrained weights: +In this bundle, the autoencoder uses perceptual loss, which is based on ResNet50 with pre-trained weights (the network is frozen and will not be trained in the bundle). In default, the `pretrained` parameter is specified as `False` in `train_autoencoder.json`. To ensure correct training, changing the default settings is necessary. There are two ways to utilize pretrained weights: 1. if set `pretrained` to `True`, ImageNet pretrained weights from [torchvision](https://pytorch.org/vision/stable/_modules/torchvision/models/resnet.html#ResNet50_Weights) will be used. However, the weights are for non-commercial use only. 2. if set `pretrained` to `True` and specifies the `perceptual_loss_model_weights_path` parameter, users are able to load weights from a local path. This is the way this bundle used to train, and the pre-trained weights are from some internal data. @@ -31,7 +31,7 @@ cd .. ``` ## Data -The training data is BraTS 2016 and 2017 from [Medical Decathlon](http://medicaldecathlon.com/). Users can find more details on the datasets (`Task01_BrainTumour`) at http://medicaldecathlon.com/. +The training data is BraTS 2016 and 2017 from the Medical Segmentation Decathalon. Users can find more details on the dataset (`Task01_BrainTumour`) at http://medicaldecathlon.com/. - Target: Image Generation - Task: Synthesis @@ -107,7 +107,7 @@ For more details usage instructions, visit the [MONAI Bundle Configuration Page] python -m monai.bundle run --config_file configs/train_autoencoder.json ``` -Please note that if the default dataset path is not modified with the actual path in the bundle config files, you can also override it by using `--dataset_dir`: +Please note that if the default dataset path is not modified with the actual path (it should be the path that contains `Task01_BrainTumour`) in the bundle config files, you can also override it by using `--dataset_dir`: ``` python -m monai.bundle run --config_file configs/train_autoencoder.json --dataset_dir