fix: Update anomalib version (#130)

* docs: Update anomalib and quadra version, update changelog

* refactor: Suppress heavy prints from auto_convert_mixed_precision function

Author: lorenzomammana

CHANGELOG.md

@@ -2,6 +2,12 @@
 # Changelog
 All notable changes to this project will be documented in this file.
 
+### [2.2.5]
+
+#### Updated
+
+- Update anomalib to v0.7.0.dev143 to fix a bug introduced in the previous version that caused the training to fail if the dataset size was smaller than the batch size.
+
 ### [2.2.4]
 
 #### Updated

poetry.lock

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "quadra"
-version = "2.2.4"
+version = "2.2.5"
 description = "Deep Learning experiment orchestration library"
 authors = [
 	"Federico Belotti <[email protected]>",
@@ -72,7 +72,7 @@ h5py = "~3.8"
 timm = "0.9.12"
 
 segmentation_models_pytorch-orobix = "0.3.3.dev1"
-anomalib-orobix = "0.7.0.dev142"
+anomalib-orobix = "0.7.0.dev143"
 xxhash = "~3.2"
 torchinfo = "~1.8"
 typing_extensions = { version = "4.11.0", python = "<3.10" }

pyproject.toml

@@ -1,4 +1,4 @@
-__version__ = "2.2.4"
+__version__ = "2.2.5"
 
 
 def get_version():

quadra/__init__.py

@@ -1,5 +1,6 @@
 from __future__ import annotations
 
+import contextlib
 import os
 from collections.abc import Sequence
 from typing import Any, Literal, TypeVar, cast
@@ -377,7 +378,11 @@ def _safe_export_half_precision_onnx(
             model_fp32 = onnx.load(export_model_path)
             test_data = {input_names[i]: inp[i].float().cpu().numpy() for i in range(len(inp))}
             log.warning("Attempting to convert model in mixed precision, this may take a while...")
-            model_fp16 = auto_convert_mixed_precision(model_fp32, test_data, rtol=0.01, atol=0.001, keep_io_types=False)
+            with open(os.devnull, "w") as f, contextlib.redirect_stdout(f):
+                # This function prints a lot of information that is not useful for the user
+                model_fp16 = auto_convert_mixed_precision(
+                    model_fp32, test_data, rtol=0.01, atol=0.001, keep_io_types=False
+                )
             onnx.save(model_fp16, export_model_path)
 
             onnx_model = onnx.load(export_model_path)