update generative func to monai core func (#1768)

Fixes # .

### Description
update generative func to monai core func

### Checks
<!--- Put an `x` in all the boxes that apply, and remove the not
applicable items -->
- [ ] Avoid including large-size files in the PR.
- [ ] Clean up long text outputs from code cells in the notebook.
- [ ] For security purposes, please check the contents and remove any
sensitive info such as user names and private key.
- [ ] Ensure (1) hyperlinks and markdown anchors are working (2) use
relative paths for tutorial repo files (3) put figure and graphs in the
`./figure` folder
- [ ] Notebook runs automatically `./runner.sh -t <path to .ipynb file>`

---------

Signed-off-by: Can-Zhao <[email protected]>
Signed-off-by: Can Zhao <[email protected]>
Signed-off-by: YunLiu <[email protected]>
Co-authored-by: YunLiu <[email protected]>

Author: Can-Zhao

.github/workflows/test-modified.yml

@@ -32,7 +32,7 @@ jobs:
         pip uninstall -y monai-weekly
         pip uninstall -y monai-weekly # make sure there's no existing installation
         BUILD_MONAI=0 python -m pip install git+https://github.com/Project-MONAI/MONAI#egg=MONAI
-        python -m pip install -r https://raw.githubusercontent.com/Project-MONAI/MONAI/main/requirements-dev.txt
+        python -m pip install -r https://raw.githubusercontent.com/Project-MONAI/MONAI/dev/requirements-dev.txt
         python -m pip install -U torch torchvision torchaudio
     - uses: actions/checkout@v3
     - name: Notebook quick check

generative/maisi/configs/config_maisi.json

@@ -92,11 +92,11 @@
         "conditioning_embedding_num_channels": [8, 32, 64]
     },
     "mask_generation_autoencoder_def": {
-        "_target_": "generative.networks.nets.AutoencoderKL",
-        "spatial_dims": 3,
+        "_target_": "monai.apps.generation.maisi.networks.autoencoderkl_maisi.AutoencoderKlMaisi",
+        "spatial_dims": "@spatial_dims",
         "in_channels": 8,
         "out_channels": 125,
-        "latent_channels": 4,
+        "latent_channels": "@latent_channels",
         "num_channels": [
             32,
             64,
@@ -114,13 +114,16 @@
         "with_decoder_nonlocal_attn": false,
         "use_flash_attention": false,
         "use_checkpointing": true,
-        "use_convtranspose": true
+        "use_convtranspose": true,
+        "norm_float16": true,
+        "num_splits": 8,
+        "dim_split": 1
     },
     "mask_generation_diffusion_def": {
-        "_target_": "generative.networks.nets.DiffusionModelUNet",
-        "spatial_dims": 3,
-        "in_channels": 4,
-        "out_channels": 4,
+        "_target_": "monai.apps.generation.maisi.networks.diffusion_model_unet_maisi.DiffusionModelUNetMaisi",
+        "spatial_dims": "@spatial_dims",
+        "in_channels": "@latent_channels",
+        "out_channels": "@latent_channels",
         "num_channels":[64, 128, 256, 512],
         "attention_levels":[false, false, true, true],
         "num_head_channels":[0, 0, 32, 32],
@@ -132,15 +135,15 @@
     },
     "mask_generation_scale_factor": 1.0055984258651733,
     "noise_scheduler": {
-        "_target_": "generative.networks.schedulers.DDPMScheduler",
+        "_target_": "monai.networks.schedulers.ddpm.DDPMScheduler",
         "num_train_timesteps": 1000,
         "beta_start": 0.0015,
         "beta_end": 0.0195,
         "schedule": "scaled_linear_beta",
         "clip_sample": false
     },
     "mask_generation_noise_scheduler": {
-        "_target_": "generative.networks.schedulers.DDPMScheduler",
+        "_target_": "monai.networks.schedulers.ddpm.DDPMScheduler",
         "num_train_timesteps": 1000,
         "beta_start": 0.0015,
         "beta_end": 0.0195,

generative/maisi/maisi_inference_tutorial.ipynb

@@ -397,7 +397,7 @@
     "controlnet.load_state_dict(checkpoint_controlnet[\"controlnet_state_dict\"], strict=True)\n",
     "\n",
     "mask_generation_autoencoder = define_instance(args, \"mask_generation_autoencoder_def\").to(device)\n",
-    "checkpoint_mask_generation_autoencoder = torch.load(args.trained_mask_generation_autoencoder_path)\n",
+    "checkpoint_mask_generation_autoencoder = load_autoencoder_ckpt(args.trained_mask_generation_autoencoder_path)\n",
     "mask_generation_autoencoder.load_state_dict(checkpoint_mask_generation_autoencoder)\n",
     "\n",
     "mask_generation_diffusion_unet = define_instance(args, \"mask_generation_diffusion_def\").to(device)\n",