monai-weekly 1.5.dev2508__tar.gz → 1.5.dev2509__tar.gz

{monai_weekly-1.5.dev2508/monai_weekly.egg-info → monai_weekly-1.5.dev2509}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: monai-weekly
-Version: 1.5.dev2508
+Version: 1.5.dev2509
 Summary: AI Toolkit for Healthcare Imaging
 Home-page: https://monai.io/
 Author: MONAI Consortium

{monai_weekly-1.5.dev2508 → monai_weekly-1.5.dev2509}/monai/__init__.py

@@ -136,4 +136,4 @@ except BaseException:
 
     if MONAIEnvVars.debug():
         raise
-__commit_id__ = "a7905909e785d1ef24103c32a2d3a5a36e1059a2"
+__commit_id__ = "a09c1f08461cec3d2131fde3939ef38c3c4ad5fc"

{monai_weekly-1.5.dev2508 → monai_weekly-1.5.dev2509}/monai/_version.py

@@ -8,11 +8,11 @@ import json
 
 version_json = '''
 {
- "date": "2025-02-23T02:28:09+0000",
+ "date": "2025-03-02T02:29:03+0000",
  "dirty": false,
  "error": null,
- "full-revisionid": "e55b5cbfbbba1800a968a9c06b2deaaa5c9bec54",
- "version": "1.5.dev2508"
+ "full-revisionid": "5f85a7bfd54b91be03213999a7c177bfe2d583b2",
+ "version": "1.5.dev2509"
 }
 '''  # END VERSION_JSON
 

{monai_weekly-1.5.dev2508 → monai_weekly-1.5.dev2509}/monai/bundle/scripts.py

@@ -15,6 +15,7 @@ import ast
 import json
 import os
 import re
+import urllib
 import warnings
 import zipfile
 from collections.abc import Mapping, Sequence
@@ -58,7 +59,7 @@ from monai.utils import (
 validate, _ = optional_import("jsonschema", name="validate")
 ValidationError, _ = optional_import("jsonschema.exceptions", name="ValidationError")
 Checkpoint, has_ignite = optional_import("ignite.handlers", IgniteInfo.OPT_IMPORT_VERSION, min_version, "Checkpoint")
-requests_get, has_requests = optional_import("requests", name="get")
+requests, has_requests = optional_import("requests")
 onnx, _ = optional_import("onnx")
 huggingface_hub, _ = optional_import("huggingface_hub")
 
@@ -206,6 +207,16 @@ def _download_from_monaihosting(download_path: Path, filename: str, version: str
     extractall(filepath=filepath, output_dir=download_path, has_base=True)
 
 
+def _download_from_bundle_info(download_path: Path, filename: str, version: str, progress: bool) -> None:
+    bundle_info = get_bundle_info(bundle_name=filename, version=version)
+    if not bundle_info:
+        raise ValueError(f"Bundle info not found for {filename} v{version}.")
+    url = bundle_info["browser_download_url"]
+    filepath = download_path / f"{filename}_v{version}.zip"
+    download_url(url=url, filepath=filepath, hash_val=None, progress=progress)
+    extractall(filepath=filepath, output_dir=download_path, has_base=True)
+
+
 def _add_ngc_prefix(name: str, prefix: str = "monai_") -> str:
     if name.startswith(prefix):
         return name
@@ -222,7 +233,7 @@ def _get_all_download_files(request_url: str, headers: dict | None = None) -> li
     if not has_requests:
         raise ValueError("requests package is required, please install it.")
     headers = {} if headers is None else headers
-    response = requests_get(request_url, headers=headers)
+    response = requests.get(request_url, headers=headers)
     response.raise_for_status()
     model_info = json.loads(response.text)
 
@@ -266,7 +277,7 @@ def _download_from_ngc_private(
     request_url = _get_ngc_private_bundle_url(model_name=filename, version=version, repo=repo)
     if has_requests:
         headers = {} if headers is None else headers
-        response = requests_get(request_url, headers=headers)
+        response = requests.get(request_url, headers=headers)
         response.raise_for_status()
     else:
         raise ValueError("NGC API requires requests package. Please install it.")
@@ -289,7 +300,7 @@ def _get_ngc_token(api_key, retry=0):
     url = "https://authn.nvidia.com/token?service=ngc"
     headers = {"Accept": "application/json", "Authorization": "ApiKey " + api_key}
     if has_requests:
-        response = requests_get(url, headers=headers)
+        response = requests.get(url, headers=headers)
         if not response.ok:
             # retry 3 times, if failed, raise an error.
             if retry < 3:
@@ -303,14 +314,17 @@ def _get_ngc_token(api_key, retry=0):
 
 def _get_latest_bundle_version_monaihosting(name):
     full_url = f"{MONAI_HOSTING_BASE_URL}/{name.lower()}"
-    requests_get, has_requests = optional_import("requests", name="get")
     if has_requests:
-        resp = requests_get(full_url)
-        resp.raise_for_status()
-    else:
-        raise ValueError("NGC API requires requests package. Please install it.")
-    model_info = json.loads(resp.text)
-    return model_info["model"]["latestVersionIdStr"]
+        resp = requests.get(full_url)
+        try:
+            resp.raise_for_status()
+            model_info = json.loads(resp.text)
+            return model_info["model"]["latestVersionIdStr"]
+        except requests.exceptions.HTTPError:
+            # for monaihosting bundles, if cannot find the version, get from model zoo model_info.json
+            return get_bundle_versions(name)["latest_version"]
+
+    raise ValueError("NGC API requires requests package. Please install it.")
 
 
 def _examine_monai_version(monai_version: str) -> tuple[bool, str]:
@@ -388,14 +402,14 @@ def _get_latest_bundle_version_ngc(name: str, repo: str | None = None, headers:
     version_header = {"Accept-Encoding": "gzip, deflate"}  # Excluding 'zstd' to fit NGC requirements
     if headers:
         version_header.update(headers)
-    resp = requests_get(version_endpoint, headers=version_header)
+    resp = requests.get(version_endpoint, headers=version_header)
     resp.raise_for_status()
     model_info = json.loads(resp.text)
     latest_versions = _list_latest_versions(model_info)
 
     for version in latest_versions:
         file_endpoint = base_url + f"/{name.lower()}/versions/{version}/files/configs/metadata.json"
-        resp = requests_get(file_endpoint, headers=headers)
+        resp = requests.get(file_endpoint, headers=headers)
         metadata = json.loads(resp.text)
         resp.raise_for_status()
         # if the package version is not available or the model is compatible with the package version
@@ -585,7 +599,16 @@ def download(
             name_ver = "_v".join([name_, version_]) if version_ is not None else name_
             _download_from_github(repo=repo_, download_path=bundle_dir_, filename=name_ver, progress=progress_)
         elif source_ == "monaihosting":
-            _download_from_monaihosting(download_path=bundle_dir_, filename=name_, version=version_, progress=progress_)
+            try:
+                _download_from_monaihosting(
+                    download_path=bundle_dir_, filename=name_, version=version_, progress=progress_
+                )
+            except urllib.error.HTTPError:
+                # for monaihosting bundles, if cannot download from default host, download according to bundle_info
+                _download_from_bundle_info(
+                    download_path=bundle_dir_, filename=name_, version=version_, progress=progress_
+                )
+
         elif source_ == "ngc":
             _download_from_ngc(
                 download_path=bundle_dir_,
@@ -792,9 +815,9 @@ def _get_all_bundles_info(
 
         if auth_token is not None:
             headers = {"Authorization": f"Bearer {auth_token}"}
-            resp = requests_get(request_url, headers=headers)
+            resp = requests.get(request_url, headers=headers)
         else:
-            resp = requests_get(request_url)
+            resp = requests.get(request_url)
         resp.raise_for_status()
     else:
         raise ValueError("requests package is required, please install it.")

{monai_weekly-1.5.dev2508 → monai_weekly-1.5.dev2509}/monai/inferers/inferer.py

@@ -1334,13 +1334,15 @@ class ControlNetDiffusionInferer(DiffusionInferer):
             raise NotImplementedError(f"{mode} condition is not supported")
 
         noisy_image = self.scheduler.add_noise(original_samples=inputs, noise=noise, timesteps=timesteps)
-        down_block_res_samples, mid_block_res_sample = controlnet(
-            x=noisy_image, timesteps=timesteps, controlnet_cond=cn_cond
-        )
+
         if mode == "concat" and condition is not None:
             noisy_image = torch.cat([noisy_image, condition], dim=1)
             condition = None
 
+        down_block_res_samples, mid_block_res_sample = controlnet(
+            x=noisy_image, timesteps=timesteps, controlnet_cond=cn_cond, context=condition
+        )
+
         diffuse = diffusion_model
         if isinstance(diffusion_model, SPADEDiffusionModelUNet):
             diffuse = partial(diffusion_model, seg=seg)
@@ -1396,17 +1398,21 @@ class ControlNetDiffusionInferer(DiffusionInferer):
             progress_bar = iter(scheduler.timesteps)
         intermediates = []
         for t in progress_bar:
-            # 1. ControlNet forward
-            down_block_res_samples, mid_block_res_sample = controlnet(
-                x=image, timesteps=torch.Tensor((t,)).to(input_noise.device), controlnet_cond=cn_cond
-            )
-            # 2. predict noise model_output
             diffuse = diffusion_model
             if isinstance(diffusion_model, SPADEDiffusionModelUNet):
                 diffuse = partial(diffusion_model, seg=seg)
 
             if mode == "concat" and conditioning is not None:
+                # 1. Conditioning
                 model_input = torch.cat([image, conditioning], dim=1)
+                # 2. ControlNet forward
+                down_block_res_samples, mid_block_res_sample = controlnet(
+                    x=model_input,
+                    timesteps=torch.Tensor((t,)).to(input_noise.device),
+                    controlnet_cond=cn_cond,
+                    context=None,
+                )
+                # 3. predict noise model_output
                 model_output = diffuse(
                     model_input,
                     timesteps=torch.Tensor((t,)).to(input_noise.device),
@@ -1415,6 +1421,12 @@ class ControlNetDiffusionInferer(DiffusionInferer):
                     mid_block_additional_residual=mid_block_res_sample,
                 )
             else:
+                down_block_res_samples, mid_block_res_sample = controlnet(
+                    x=image,
+                    timesteps=torch.Tensor((t,)).to(input_noise.device),
+                    controlnet_cond=cn_cond,
+                    context=conditioning,
+                )
                 model_output = diffuse(
                     image,
                     timesteps=torch.Tensor((t,)).to(input_noise.device),
@@ -1485,9 +1497,6 @@ class ControlNetDiffusionInferer(DiffusionInferer):
         for t in progress_bar:
             timesteps = torch.full(inputs.shape[:1], t, device=inputs.device).long()
             noisy_image = self.scheduler.add_noise(original_samples=inputs, noise=noise, timesteps=timesteps)
-            down_block_res_samples, mid_block_res_sample = controlnet(
-                x=noisy_image, timesteps=torch.Tensor((t,)).to(inputs.device), controlnet_cond=cn_cond
-            )
 
             diffuse = diffusion_model
             if isinstance(diffusion_model, SPADEDiffusionModelUNet):
@@ -1495,6 +1504,9 @@ class ControlNetDiffusionInferer(DiffusionInferer):
 
             if mode == "concat" and conditioning is not None:
                 noisy_image = torch.cat([noisy_image, conditioning], dim=1)
+                down_block_res_samples, mid_block_res_sample = controlnet(
+                    x=noisy_image, timesteps=torch.Tensor((t,)).to(inputs.device), controlnet_cond=cn_cond, context=None
+                )
                 model_output = diffuse(
                     noisy_image,
                     timesteps=timesteps,
@@ -1503,6 +1515,12 @@ class ControlNetDiffusionInferer(DiffusionInferer):
                     mid_block_additional_residual=mid_block_res_sample,
                 )
             else:
+                down_block_res_samples, mid_block_res_sample = controlnet(
+                    x=noisy_image,
+                    timesteps=torch.Tensor((t,)).to(inputs.device),
+                    controlnet_cond=cn_cond,
+                    context=conditioning,
+                )
                 model_output = diffuse(
                     x=noisy_image,
                     timesteps=timesteps,

{monai_weekly-1.5.dev2508 → monai_weekly-1.5.dev2509/monai_weekly.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: monai-weekly
-Version: 1.5.dev2508
+Version: 1.5.dev2509
 Summary: AI Toolkit for Healthcare Imaging
 Home-page: https://monai.io/
 Author: MONAI Consortium

{monai_weekly-1.5.dev2508 → monai_weekly-1.5.dev2509}/tests/inferers/test_controlnet_inferers.py

@@ -550,6 +550,8 @@ class ControlNetTestDiffusionSamplingInferer(unittest.TestCase):
     def test_sampler_conditioned(self, model_params, controlnet_params, input_shape):
         model_params["with_conditioning"] = True
         model_params["cross_attention_dim"] = 3
+        controlnet_params["with_conditioning"] = True
+        controlnet_params["cross_attention_dim"] = 3
         model = DiffusionModelUNet(**model_params)
         controlnet = ControlNet(**controlnet_params)
         device = "cuda:0" if torch.cuda.is_available() else "cpu"
@@ -619,8 +621,11 @@ class ControlNetTestDiffusionSamplingInferer(unittest.TestCase):
         model_params = model_params.copy()
         n_concat_channel = 2
         model_params["in_channels"] = model_params["in_channels"] + n_concat_channel
+        controlnet_params["in_channels"] = controlnet_params["in_channels"] + n_concat_channel
         model_params["cross_attention_dim"] = None
+        controlnet_params["cross_attention_dim"] = None
         model_params["with_conditioning"] = False
+        controlnet_params["with_conditioning"] = False
         model = DiffusionModelUNet(**model_params)
         device = "cuda:0" if torch.cuda.is_available() else "cpu"
         model.to(device)
@@ -1023,8 +1028,10 @@ class LatentControlNetTestDiffusionSamplingInferer(unittest.TestCase):
         if ae_model_type == "SPADEAutoencoderKL":
             stage_1 = SPADEAutoencoderKL(**autoencoder_params)
         stage_2_params = stage_2_params.copy()
+        controlnet_params = controlnet_params.copy()
         n_concat_channel = 3
         stage_2_params["in_channels"] = stage_2_params["in_channels"] + n_concat_channel
+        controlnet_params["in_channels"] = controlnet_params["in_channels"] + n_concat_channel
         if dm_model_type == "SPADEDiffusionModelUNet":
             stage_2 = SPADEDiffusionModelUNet(**stage_2_params)
         else:
@@ -1106,8 +1113,10 @@ class LatentControlNetTestDiffusionSamplingInferer(unittest.TestCase):
         if ae_model_type == "SPADEAutoencoderKL":
             stage_1 = SPADEAutoencoderKL(**autoencoder_params)
         stage_2_params = stage_2_params.copy()
+        controlnet_params = controlnet_params.copy()
         n_concat_channel = 3
         stage_2_params["in_channels"] = stage_2_params["in_channels"] + n_concat_channel
+        controlnet_params["in_channels"] = controlnet_params["in_channels"] + n_concat_channel
         if dm_model_type == "SPADEDiffusionModelUNet":
             stage_2 = SPADEDiffusionModelUNet(**stage_2_params)
         else: