update dependency, update trained model weights

README.md

@@ -22,7 +22,7 @@ Please note that each user is responsible for checking the data source of the pr
 
 #### Example synthetic image
 An example result from inference is shown below:
-![Example synthetic image](https://developer.download.nvidia.com/assets/Clara/Images/monai_brain_image_gen_ldm3d_example_generation.png)
+![Example synthetic image](https://developer.download.nvidia.com/assets/Clara/Images/monai_brain_image_gen_ldm3d_example_generation_v2.png)
 
 **This is a demonstration network meant to just show the training process for this sort of network with MONAI. To achieve better performance, users need to use larger dataset like [Brats 2021](https://www.synapse.org/#!Synapse:syn25829067/wiki/610865) and have GPU with memory larger than 32G to enable larger networks and attention layers.**
 
@@ -30,11 +30,7 @@ An example result from inference is shown below:
 [MONAI generative models](https://github.com/Project-MONAI/GenerativeModels) can be installed by
 ```
 pip install lpips==0.1.4
-git clone https://github.com/Project-MONAI/GenerativeModels.git
-cd GenerativeModels/
-git checkout f969c24f88d013dc0045fb7b2885a01fb219992b
-python setup.py install
-cd ..
+pip install git+https://github.com/Project-MONAI/GenerativeModels.git@0.2.1
 ```
 
 ## Data
@@ -78,7 +74,7 @@ The latent diffusion model was trained using the following configuration:
 
 #### Training Input
 - 8 channel noisy latent features
-- an int that indicates the time step
+- a long int that indicates the time step
 
 #### Training Output
 8 channel predicted added noise
@@ -96,9 +92,9 @@ If you face memory issues with data loading, you can lower the caching rate `cac
 ## Performance
 
 #### Training Loss
-![A graph showing the autoencoder training curve](https://developer.download.nvidia.com/assets/Clara/Images/monai_brain_image_gen_ldm3d_train_autoencoder_loss.png)
+![A graph showing the autoencoder training curve](https://developer.download.nvidia.com/assets/Clara/Images/monai_brain_image_gen_ldm3d_train_autoencoder_loss_v2.png)
 
-![A graph showing the latent diffusion training curve](https://developer.download.nvidia.com/assets/Clara/Images/monai_brain_image_gen_ldm3d_train_diffusion_loss.png)
+![A graph showing the latent diffusion training curve](https://developer.download.nvidia.com/assets/Clara/Images/monai_brain_image_gen_ldm3d_train_diffusion_loss_v2.png)
 
 ## MONAI Bundle Commands
 

configs/metadata.json

@@ -1,7 +1,8 @@
 {
     "schema": "https://github.com/Project-MONAI/MONAI-extra-test-data/releases/download/0.8.1/meta_schema_generator_ldm_20230507.json",
-    "version": "1.0.0",
+    "version": "1.0.1",
     "changelog": {
+        "1.0.1": "update dependency, update trained model weights",
         "1.0.0": "Initial release"
     },
     "monai_version": "1.2.0rc5",

docs/README.md

@@ -15,7 +15,7 @@ Please note that each user is responsible for checking the data source of the pr
 
 #### Example synthetic image
 An example result from inference is shown below:
-![Example synthetic image](https://developer.download.nvidia.com/assets/Clara/Images/monai_brain_image_gen_ldm3d_example_generation.png)
+![Example synthetic image](https://developer.download.nvidia.com/assets/Clara/Images/monai_brain_image_gen_ldm3d_example_generation_v2.png)
 
 **This is a demonstration network meant to just show the training process for this sort of network with MONAI. To achieve better performance, users need to use larger dataset like [Brats 2021](https://www.synapse.org/#!Synapse:syn25829067/wiki/610865) and have GPU with memory larger than 32G to enable larger networks and attention layers.**
 
@@ -23,11 +23,7 @@ An example result from inference is shown below:
 [MONAI generative models](https://github.com/Project-MONAI/GenerativeModels) can be installed by
 ```
 pip install lpips==0.1.4
-git clone https://github.com/Project-MONAI/GenerativeModels.git
-cd GenerativeModels/
-git checkout f969c24f88d013dc0045fb7b2885a01fb219992b
-python setup.py install
-cd ..
+pip install git+https://github.com/Project-MONAI/GenerativeModels.git@0.2.1
 ```
 
 ## Data
@@ -71,7 +67,7 @@ The latent diffusion model was trained using the following configuration:
 
 #### Training Input
 - 8 channel noisy latent features
-- an int that indicates the time step
+- a long int that indicates the time step
 
 #### Training Output
 8 channel predicted added noise
@@ -89,9 +85,9 @@ If you face memory issues with data loading, you can lower the caching rate `cac
 ## Performance
 
 #### Training Loss
-![A graph showing the autoencoder training curve](https://developer.download.nvidia.com/assets/Clara/Images/monai_brain_image_gen_ldm3d_train_autoencoder_loss.png)
+![A graph showing the autoencoder training curve](https://developer.download.nvidia.com/assets/Clara/Images/monai_brain_image_gen_ldm3d_train_autoencoder_loss_v2.png)
 
-![A graph showing the latent diffusion training curve](https://developer.download.nvidia.com/assets/Clara/Images/monai_brain_image_gen_ldm3d_train_diffusion_loss.png)
+![A graph showing the latent diffusion training curve](https://developer.download.nvidia.com/assets/Clara/Images/monai_brain_image_gen_ldm3d_train_diffusion_loss_v2.png)
 
 ## MONAI Bundle Commands
 

models/model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d780cd5fff4ec886226c5407391a5906c45e388c5d02efbf20da8729b7513e19
-size 765042309
+oid sha256:4af4a27015291c0a6390b45b0d39e4d54924c2250cadd6d5c1bb9717d76a26fd
+size 765020741

models/model_autoencoder.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a788c35df8e6d7b8c5baf2108bfc6e105a1e6685dfbf564d8d07a66194de8727
+oid sha256:85ec0986beb902b93beb5e27ea5c39429e8ae02c3bde8ca581bef0cac83014bc
 size 84050405

models/model_autoencoder.ts

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39fa19c3e4cd35298337ad4dd8684961d55539a7cd3e29155e12731b254aca3f
-size 84147155
+oid sha256:794871bdc4e4fb545d0f6999456376cf6caa1534b6271be4916e5f33cf80e3ce
+size 84141341