adjust int. plots

Author: mluerig

bioencoder/scripts/interactive_plots.py

@@ -61,7 +61,7 @@ def interactive_plots(
         "valid_batch_size": hyperparams.get("dataloaders", {}).get("valid_batch_size",1),
     }
     num_workers = hyperparams.get("dataloaders", {}).get("num_workers", 4)
-    perplexity = hyperparams.get("perplexity", 30)
+    perplexity = hyperparams.get("perplexity")
 
     plot_config = {
         "color_classes": hyperparams.get("color_classes", None),
@@ -71,11 +71,13 @@ def interactive_plots(
     }
 
 
-    ## Set up directories
+    ## directories and file management
     data_dir = os.path.join(root_dir, "data", run_name)
-    plot_path = os.path.join(root_dir, "plots", run_name, f"embeddings_{run_name}.html")
+    plot_dir = os.path.join(root_dir, "plots", run_name)
+    os.makedirs(plot_dir, exist_ok=True)
+    plot_path = os.path.join(plot_dir, "embeddings_interactive_plot.html")
     if not overwrite and not kwargs.get("ret_embeddings"):
-        assert not os.path.isfile(plot_path), f"File exists: {plot_path}"
+        assert not os.path.isfile(plot_path), f"File already exists: {plot_path}"
 
     ## Load model and set up
     print(f"Checkpoint: using {checkpoint} of {stage} stage")

bioencoder/vis/helpers.py

@@ -242,7 +242,7 @@ def embbedings_dimension_reductions(data_table, perplexity):
     return np.hstack((pca, tsne)), names, pca_obj
 
 
-def bokeh_plot(df, out_path='plot.html', color_map="viridis", color_classes=None, plot_style=1, 
+def bokeh_plot(df, out_path='plot.html', color_map="jet1", color_classes=None, plot_style=1, 
                point_size=10, **kwargs):
     """
     Plot a scatter plot of the PCA and t-SNE dimensions of the data using bokeh.
@@ -265,7 +265,6 @@ class labels of the images).
 
     unique_classes = df['class'].unique()
 
-   
     ## Color management
     if color_classes:
         assert len(unique_classes) == len(color_classes), (

bioencoder_configs/plot_stage1.yml

@@ -4,21 +4,15 @@ model:
   stage: first # Training stage: 'first' for initial training, 'second' for fine-tuning
 
 dataloaders:
-  train_batch_size: 2 # Batch size for training data; ensure validation set size is a multiple of this number
-  valid_batch_size: 2 # Batch size for validation data
-  num_workers: 32 # Number of CPU threads for data loading; should not exceed the number of CPU cores
-
-img_size: 384 # Image size for training and validation
+  train_batch_size:  # Larger is faster but may drop leftover data points - no value or removing this line will not include training data
+  valid_batch_size: 10 # Larger is faster but may drop leftover data points - ideally use a multiple of val set size
+  num_workers: 32 # Should not exceed available CPU cores
 
 plot_style: 1 # (1: pictogram above point, 2: pictogram next to plot panel)
-
-color_classes: # overrides color_map
-  #class1: "#FFD467"
-  #class2: "#4DC9F2"
-
 point_size: 10  ## size of points in scatter plot
-
 color_map: 'Set1' # Default color map; see https://matplotlib.org/stable/users/explain/colors/colormaps.html for options
-
+#color_classes: # overrides color_map
+  #class1: "#FFD467"
+  #class2: "#4DC9F2"