Mercurial > repos > goeckslab > extract_embeddings

comparison pytorch_embedding.xml @ 1:84f96c952c2c draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/goeckslab/gleam.git commit 5b6cd961948137853177b14b0fff80a5d40e8a07
author goeckslab
date Sun, 09 Nov 2025 19:03:21 +0000
parents 38333676a029
children
comparison
equal deleted inserted replaced
0:38333676a029 1:84f96c952c2c
48 <option value="efficientnet_b6">EfficientNet-B6</option> 48 <option value="efficientnet_b6">EfficientNet-B6</option>
49 <option value="efficientnet_b7">EfficientNet-B7</option> 49 <option value="efficientnet_b7">EfficientNet-B7</option>
50 <option value="efficientnet_v2_s">EfficientNetV2-S</option> 50 <option value="efficientnet_v2_s">EfficientNetV2-S</option>
51 <option value="efficientnet_v2_m">EfficientNetV2-M</option> 51 <option value="efficientnet_v2_m">EfficientNetV2-M</option>
52 <option value="efficientnet_v2_l">EfficientNetV2-L</option> 52 <option value="efficientnet_v2_l">EfficientNetV2-L</option>
53 <option value="gpfm">GPFM (Generalizable Pathology Foundation Model)</option>
53 <option value="googlenet">GoogLeNet</option> 54 <option value="googlenet">GoogLeNet</option>
54 <option value="inception_v3">Inception-V3</option> 55 <option value="inception_v3">Inception-V3</option>
55 <option value="mnasnet0_5">MNASNet-0.5</option> 56 <option value="mnasnet0_5">MNASNet-0.5</option>
56 <option value="mnasnet0_75">MNASNet-0.75</option> 57 <option value="mnasnet0_75">MNASNet-0.75</option>
57 <option value="mnasnet1_0">MNASNet-1.0</option> 58 <option value="mnasnet1_0">MNASNet-1.0</option>
112 <has_text text="sample_name" /> 113 <has_text text="sample_name" />
113 <has_n_columns min="1" /> 114 <has_n_columns min="1" />
114 </assert_contents> 115 </assert_contents>
115 </output> 116 </output>
116 </test> 117 </test>
118 <test>
119 <param name="input_zip" value="1_digit.zip" ftype="zip" />
120 <param name="model_name" value="gpfm" />
121 <param name="apply_normalization" value="true" />
122 <param name="transform_type" value="RGB" />
123 <output name="output_csv">
124 <assert_contents>
125 <has_text text="sample_name" />
126 <has_n_columns min="1" />
127 </assert_contents>
128 </output>
129 </test>
117 </tests> 130 </tests>
118 <help> 131 <help>
119 <![CDATA[ 132 <![CDATA[
120 **What it does** 133 **What it does**
121 This tool extracts image embeddings using a selected deep learning model. 134 This tool extracts image embeddings using a selected deep learning model, including specialized pathology models like GPFM.
122 135
123 **Inputs** 136 **Inputs**
124 - A zip file containing images to process. 137 - A zip file containing images to process.
125 - A model selection for embedding extraction. 138 - A model selection for embedding extraction (includes GPFM for pathology images).
126 - An option to apply normalization to the extracted embeddings. 139 - An option to apply normalization to the extracted embeddings.
127 - A choice of image transformation type before processing. 140 - A choice of image transformation type before processing.
141
142 **Models Available**
143 - Standard computer vision models (ResNet, EfficientNet, ViT, etc.)
144 - GPFM: Generalizable Pathology Foundation Model - specialized for medical/pathology images
145 * Automatically downloads 1.2GB pretrained weights on first use
146 * Uses DinoVisionTransformer architecture (1024-dimensional embeddings)
147 * Optimized for histopathology images at 224x224 resolution
128 148
129 **Outputs** 149 **Outputs**
130 - A CSV file containing embeddings. Each row corresponds to an image, with the file name in the first column and embedding vectors in the subsequent columns. 150 - A CSV file containing embeddings. Each row corresponds to an image, with the file name in the first column and embedding vectors in the subsequent columns.
131 ]]> 151 ]]>
132 </help> 152 </help>