code-loader 1.0.208.dev7__tar.gz → 1.0.208.dev8__tar.gz

{code_loader-1.0.208.dev7 → code_loader-1.0.208.dev8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: code-loader
-Version: 1.0.208.dev7
+Version: 1.0.208.dev8
 Summary: 
 Home-page: https://github.com/tensorleap/code-loader
 License: MIT

{code_loader-1.0.208.dev7 → code_loader-1.0.208.dev8}/code_loader/inner_leap_binder/leapbinder.py

@@ -85,11 +85,6 @@ def _reject_stringized_sample_preprocess_response(function: Callable[..., Any],
         "This breaks Tensorleap type detection, so it must be referenced as a real type.")
 
 
-def _reject_stringized_preprocess_response(function: Callable[..., Any], arg_name: str, annotation: Any) -> None:
-    _reject_stringized_annotation(
-        function, arg_name, annotation, PreprocessResponse,
-        "Tensorleap uses that annotation to tell a dataset-computed custom latent space from a "
-        "model-computed one, so it must be a real type.")
 
 
 

{code_loader-1.0.208.dev7 → code_loader-1.0.208.dev8}/code_loader/inner_leap_binder/leapbinder_decorators.py

@@ -7,6 +7,7 @@ import warnings
 import logging
 from collections import defaultdict
 import functools
+import typing
 from functools import lru_cache
 from pathlib import Path
 from typing import Optional, Union, Callable, List, Dict, Set, Any
@@ -36,7 +37,7 @@ from code_loader.contract.visualizer_classes import LeapImage, LeapImageMask, Le
     LeapHorizontalBar, LeapImageWithBBox, LeapImageWithHeatmap, LeapVideo, LeapAudio, LeapValidationError, \
     map_leap_data_type_to_visualizer_class
 from code_loader.inner_leap_binder.leapbinder import mapping_runtime_mode_env_var_mame, \
-    _reject_stringized_preprocess_response, _reject_stringized_sample_preprocess_response
+    _reject_stringized_sample_preprocess_response
 from code_loader.mixpanel_tracker import clear_integration_events, AnalyticsEvent, emit_integration_event_once
 
 _called_from_inside_tl_decorator = 0
@@ -1751,15 +1752,32 @@ def tensorleap_metadata(
     return decorating_function
 
 
+def _is_preprocess_response_type(annotation: Any) -> bool:
+    if isinstance(annotation, type):
+        return issubclass(annotation, PreprocessResponse)
+    return any(_is_preprocess_response_type(arg) for arg in get_args(annotation))
+
+
 def _classify_custom_latent_space_signature(user_function) -> str:
-    argspec = inspect.getfullargspec(user_function)
-    params = argspec.args
-    if len(params) != 2:
-        return 'model'
+    """Dataset-computed when a parameter is typed PreprocessResponse (a subclass or an
+    Optional[...] of it included), model-computed otherwise."""
+    params = list(inspect.signature(user_function).parameters.values())
+    hints = typing.get_type_hints(user_function)
+    preprocess_params = [p.name for p in params if _is_preprocess_response_type(hints.get(p.name))]
+    if preprocess_params:
+        positional = [p.name for p in params
+                      if p.kind in (inspect.Parameter.POSITIONAL_ONLY, inspect.Parameter.POSITIONAL_OR_KEYWORD)]
+        if positional[1:2] != preprocess_params[:1] or len(preprocess_params) > 1:
+            raise Exception(
+                f"tensorleap_custom_latent_space validation failed: '{user_function.__name__}' is "
+                f"dataset-computed (it takes a PreprocessResponse), so it is called as "
+                f"{user_function.__name__}(sample_id, preprocess) and its PreprocessResponse must be "
+                f"the second positional parameter, and the only one. Got parameters "
+                f"{[p.name for p in params]} with PreprocessResponse on {preprocess_params}.")
+        return 'dataset'
 
-    second = params[1]
-    first = params[0]
-    if second not in argspec.annotations:
+    if len(params) == 2 and params[1].name not in hints:
+        first, second = params[0].name, params[1].name
         raise Exception(
             f"tensorleap_custom_latent_space validation failed: '{user_function.__name__}' has "
             f"exactly two parameters ('{first}', '{second}') and '{second}' has no type "
@@ -1771,11 +1789,6 @@ def _classify_custom_latent_space_signature(user_function) -> str:
             f"If you are upgrading an existing project, this signature used to be accepted "
             f"unannotated as dataset-computed; add ': PreprocessResponse' to '{second}' to keep "
             f"the previous behavior.")
-
-    annotation = argspec.annotations[second]
-    _reject_stringized_preprocess_response(user_function, second, annotation)
-    if annotation is PreprocessResponse:
-        return 'dataset'
     return 'model'
 
 

{code_loader-1.0.208.dev7 → code_loader-1.0.208.dev8}/code_loader/leaploader.py

@@ -55,8 +55,6 @@ class LeapLoader(LeapLoaderBase):
         self._preprocess_result_cached = None
         self._synthetic_lookup: Dict[str, Tuple[PreprocessResponse, Any]] = {}
         self._synthetic_populator: Optional[Callable[[str], None]] = None
-        # Dataset-computed custom LS the engine dropped for this job; get_sample stops computing them.
-        self._skipped_custom_latent_spaces: FrozenSet[str] = frozenset()
 
         try:
             from code_loader.mixpanel_tracker import track_code_loader_loaded
@@ -1208,10 +1206,17 @@ class LeapLoader(LeapLoaderBase):
             if any(handler.instance_aware for handler in latent_handlers.values()):
                 raise Exception(
                     "instance-aware custom latent spaces are not supported with grouped preprocess responses")
+            # TODO: support model-computed custom latent spaces on grouped datasets (skip them here,
+            # as the per-sample path does, once the grouped metrics path is verified to compute them).
+            model_ls_names = [name for name, handler in latent_handlers.items()
+                              if handler.computed_at == CustomLatentSpaceComputedAt.MODEL]
+            if model_ls_names:
+                raise Exception(
+                    f"model-computed custom latent spaces {model_ls_names} are not supported with "
+                    f"grouped preprocess responses yet")
             custom_latent_spaces = {
                 name: self._to_grouped_list(handler.function(group_ids, preprocess_state))
                 for name, handler in latent_handlers.items()
-                if name not in self._skipped_custom_latent_spaces
             }
 
         return DatasetSample(inputs=inputs, gt=gt, metadata=metadata, metadata_is_none=metadata_is_none,
@@ -1435,8 +1440,7 @@ class LeapLoader(LeapLoaderBase):
             instance_id: Optional[int] = None) -> Optional[Dict[str, npt.NDArray[np.float32]]]:
         handlers = {handler_name: handler for handler_name, handler
                     in global_leap_binder.setup_container.custom_latent_spaces.items()
-                    if handler.computed_at != CustomLatentSpaceComputedAt.MODEL
-                    and handler_name not in self._skipped_custom_latent_spaces}
+                    if handler.computed_at != CustomLatentSpaceComputedAt.MODEL}
         if not handlers:
             return None
         if preprocess.is_grouped:
@@ -1463,10 +1467,6 @@ class LeapLoader(LeapLoaderBase):
         self.exec_script()
         return len(global_leap_binder.setup_container.custom_latent_spaces) > 0
 
-    def set_skipped_custom_latent_spaces(self, names: Iterable[str]) -> None:
-        """Stop computing these dataset-computed custom latent spaces in get_sample(s)."""
-        self._skipped_custom_latent_spaces = frozenset(names)
-
     @lru_cache()
     def get_custom_latent_space_names(self) -> Tuple[str, ...]:
         """Names of all registered custom latent spaces, in registration order.

{code_loader-1.0.208.dev7 → code_loader-1.0.208.dev8}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "code-loader"
-version = "1.0.208.dev7"
+version = "1.0.208.dev8"
 description = ""
 authors = ["dorhar <doron.harnoy@tensorleap.ai>"]
 license = "MIT"