code-loader 1.0.44__tar.gz → 1.0.45__tar.gz

{code_loader-1.0.44 → code_loader-1.0.45}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: code-loader
-Version: 1.0.44
+Version: 1.0.45
 Summary: 
 Home-page: https://github.com/tensorleap/code-loader
 License: MIT

code_loader-1.0.45/code_loader/code_inegration_processes_manager.py

@@ -0,0 +1,83 @@
+# mypy: ignore-errors
+import traceback
+from dataclasses import dataclass
+
+from typing import List, Tuple, Optional
+
+from multiprocessing import Process, Queue
+
+from code_loader.leap_loader_parallelized_base import LeapLoaderParallelizedBase
+from code_loader.leaploader import LeapLoader
+from code_loader.contract.enums import DataStateEnum
+from code_loader.metric_calculator_parallelized import MetricCalculatorParallelized
+from code_loader.samples_generator_parallelized import SamplesGeneratorParallelized
+
+
+@dataclass
+class SampleSerializableError:
+    state: DataStateEnum
+    index: int
+    leap_script_trace: str
+    exception_as_str: str
+
+
+class CodeIntegrationProcessesManager:
+    def __init__(self, code_path: str, code_entry_name: str, n_workers: Optional[int] = 2,
+                 max_samples_in_queue: int = 128) -> None:
+        self.metric_calculator_parallelized = MetricCalculatorParallelized(code_path, code_entry_name)
+        self.samples_generator_parallelized = SamplesGeneratorParallelized(code_path, code_entry_name)
+
+    def _create_and_start_process(self) -> Process:
+        process = self.multiprocessing_context.Process(
+            target=CodeIntegrationProcessesManager._process_func,
+            args=(self.code_path, self.code_entry_name, self._inputs_waiting_to_be_process,
+                  self._ready_processed_results))
+        process.daemon = True
+        process.start()
+        return process
+
+    def _run_and_warm_first_process(self):
+        process = self._create_and_start_process()
+        self.processes = [process]
+
+        # needed in order to make sure the preprocess func runs once in nonparallel
+        self._start_process_inputs([(DataStateEnum.training, 0)])
+        self._get_next_ready_processed_result()
+
+    def _operation_decider(self):
+        if self.metric_calculator_parallelized._ready_processed_results.empty() and not \
+            self.metric_calculator_parallelized._inputs_waiting_to_be_process.empty():
+            return 'metric'
+
+        if self.samples_generator_parallelized._ready_processed_results.empty() and not \
+            self.samples_generator_parallelized._inputs_waiting_to_be_process.empty():
+            return 'dataset'
+
+
+
+
+    @staticmethod
+    def _process_func(code_path: str, code_entry_name: str,
+                      samples_to_process: Queue, ready_samples: Queue,
+                      metrics_to_process: Queue, ready_metrics: Queue) -> None:
+        import os
+        os.environ["CUDA_VISIBLE_DEVICES"] = "-1"
+
+        leap_loader = LeapLoader(code_path, code_entry_name)
+        while True:
+
+            # decide on sample or metric to process
+            state, idx = samples_to_process.get(block=True)
+            leap_loader._preprocess_result()
+            try:
+                sample = leap_loader.get_sample(state, idx)
+            except Exception as e:
+                leap_script_trace = traceback.format_exc().split('File "<string>"')[-1]
+                ready_samples.put(SampleSerializableError(state, idx, leap_script_trace, str(e)))
+                continue
+
+            ready_samples.put(sample)
+
+    def generate_samples(self, sample_identities: List[Tuple[DataStateEnum, int]]):
+        return self.start_process_inputs(sample_identities)
+

{code_loader-1.0.44 → code_loader-1.0.45}/code_loader/inner_leap_binder/leapbinder.py

@@ -420,14 +420,12 @@ class LeapBinder:
             ]
             for i, (single_metadata_name, single_metadata_result) in enumerate(raw_result.items()):
                 metadata_test_result = metadata_test_result_payloads[i]
-                assert isinstance(single_metadata_result, (float, int, str, bool))
                 result_shape = get_shape(single_metadata_result)
                 metadata_test_result.shape = result_shape
                 metadata_test_result.raw_result = single_metadata_result
                 metadata_test_result.handler_type = handler_type
             test_result = metadata_test_result_payloads
         else:
-            assert not isinstance(raw_result, dict)
             result_shape = get_shape(raw_result)
             test_result[0].shape = result_shape
             test_result[0].raw_result = raw_result

{code_loader-1.0.44 → code_loader-1.0.45}/code_loader/leaploader.py

@@ -233,13 +233,13 @@ class LeapLoader:
             if hasattr(handler_test_payload.raw_result, 'tolist'):
                 handler_test_payload.raw_result = handler_test_payload.raw_result.tolist()
             metadata_type = type(handler_test_payload.raw_result)
-            if metadata_type == int:
+            if metadata_type == int or isinstance(handler_test_payload.raw_result, (np.unsignedinteger, np.signedinteger)):
                 metadata_type = float
-            if metadata_type == str:
+            if isinstance(handler_test_payload.raw_result, str):
                 dataset_metadata_type = DatasetMetadataType.string
-            elif metadata_type == bool:
+            elif metadata_type == bool or isinstance(handler_test_payload.raw_result, np.bool_):
                 dataset_metadata_type = DatasetMetadataType.boolean
-            elif metadata_type == float:
+            elif metadata_type == float or isinstance(handler_test_payload.raw_result, np.floating):
                 dataset_metadata_type = DatasetMetadataType.float
             else:
                 raise Exception(f"Unsupported return type of metadata {handler_test_payload.name}."

{code_loader-1.0.44 → code_loader-1.0.45}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "code-loader"
-version = "1.0.44"
+version = "1.0.45"
 description = ""
 authors = ["dorhar <doron.harnoy@tensorleap.ai>"]
 license = "MIT"