diff --git a/TD2_Deep_Learning.ipynb b/TD2_Deep_Learning.ipynb index 43d83e9c5b6edcb3d1e6e930dec2fd6aea2492a2..8c2a3a02e174637a35e501446637095cc1168e4a 100644 --- a/TD2_Deep_Learning.ipynb +++ b/TD2_Deep_Learning.ipynb @@ -2308,6 +2308,14 @@ "eval_model(quantized_modified_model, dataloaders[\"val\"], criterion_modified)" ] }, + { + "cell_type": "markdown", + "id": "fe954ce4", + "metadata": {}, + "source": [ + "## The quantization process maintains accuracy, and its impact on reducing file size is minimal. Therefore, the use of quantization is not significant in this context.", + ] + } { "cell_type": "markdown", "id": "04a263f0",