change app.py path structure

app.py

@@ -18,8 +18,8 @@ import pandas as pd
 import numpy as np
 from PIL import Image
 from glob import glob
-import gc # garbage collector, recycles memory usage
-import albumentations as A # library for image augmentation
+import gc 
+import albumentations as A
 import gradio as gr
 #}}}
 # Gradio wrap {{{
@@ -36,11 +36,9 @@ def score(input_img):
     # 02. Model constants {{{
     device = torch.device('cuda')
     class Config:
-        model_base_dir = '/weights/'
-        model_file_ext = '/*.pth'
         im_size =  224
-        batch_size = 1 # match total test images needed for inference to at least 1 batch_size
-        num_workers = 0
+        batch_size = 1
+        num_workers = 8
         # }}}
     # 03. Define Dataset {{{
     class PetDataset(Dataset):
@@ -133,79 +131,47 @@ def score(input_img):
         torch.cuda.empty_cache()
         return fold_preds    
     # }}}
-    # 05. Inference exp53 {{{
-    class Config_exp53(Config):
-        model_dir = 'exp53'
-        model_name = "swin_large_patch4_window7_224"
-
+    # 05. Inference 1 {{{
     test_preds = []                                      
     test_preds_model = []  
-    modelfiles = glob(Config.model_base_dir + Config_exp53.model_dir + Config.model_file_ext) # get all model full file paths
-
-    for model_index, model_path in enumerate(modelfiles): # loop through all indexes (total 10) and model full file paths
-        print(f'inferencing with: {model_path}')
-        test_preds_fold = []
-        model = PetNet(model_name = Config_exp53.model_name, out_features = 1, inp_channels = 3, pretrained=False) # instantiate model
-        model.load_state_dict(torch.load(model_path))  # load coorponding weights into the model
-        model = model.to(device)                       # send to gpu
-        model = model.float()                          # convert to float
-        model.eval()                                   # set to eval mode. (turn off BatchNorm, dropout etc.)
-        test_preds_fold = tta_fn(thefile, model, Config.im_size, [1]) # returns a list of predictions       
-        test_preds_model.append(test_preds_fold)       # append test.size # of predictions for each model
+    test_preds_fold = []
+    model = PetNet(model_name = 'swin_large_patch4_window7_224', out_features = 1, inp_channels = 3, pretrained=False)
+    model.load_state_dict(torch.load('swin_large_patch4_window7_224_fold0_half.pth'))  
+    model = model.to(device)                       
+    model = model.float()                          
+    model.eval()                                   
+    test_preds_fold = tta_fn(thefile, model, Config.im_size, [1]) 
+    test_preds_model.append(test_preds_fold)       
 
     final_predictions53 = np.mean(np.array(test_preds_model), axis=0)
-    print(f'>>>exp53: ', final_predictions53)
     # }}}
-    # 06. Inference exp55 {{{
-    class Config_exp55(Config):
-        model_dir = 'exp55'
-        model_name = "beit_large_patch16_224"
-
+    # 06. Inference 2 {{{
     test_preds = []
     test_preds_model = []
-    modelfiles = glob(Config.model_base_dir + Config_exp55.model_dir + Config.model_file_ext)
-
-    for model_index, model_path in enumerate(modelfiles):
-        print(f'inferencing with: {model_path}')
-        test_preds_fold = []
-        model = PetNet(model_name = Config_exp55.model_name, out_features = 1, inp_channels = 3, pretrained=False)
-        model.load_state_dict(torch.load(model_path))
-        model = model.to(device)
-        model = model.float()
-        model.eval() 
-        test_preds_fold = tta_fn(thefile, model, Config.im_size, [0])
-        test_preds_model.append(test_preds_fold)
+    test_preds_fold = []
+    model = PetNet(model_name = 'beit_large_patch16_224', out_features = 1, inp_channels = 3, pretrained=False)
+    model.load_state_dict(torch.load('beit_large_patch16_224_fold0_half.pth'))
+    model = model.to(device)
+    model = model.float()
+    model.eval() 
+    test_preds_fold = tta_fn(thefile, model, Config.im_size, [0])
+    test_preds_model.append(test_preds_fold)
     final_predictions55 = np.mean(np.array(test_preds_model), axis=0)
-    print(f'>>>exp55: ', final_predictions55)
     # }}}
-    # 07. Inference exp66 {{{
-    class Config_exp66(Config):
-        model_dir = 'exp66'
-        model_name = "swin_large_patch4_window12_384_in22k"
-        im_size =  384
-
+    # 07. Inference 3 {{{
     test_preds = []
     test_preds_model = []
-    modelfiles = glob(Config.model_base_dir + Config_exp66.model_dir + Config.model_file_ext)
-
-    for model_index, model_path in enumerate(modelfiles):
-        print(f'inferencing with: {model_path}')
-        test_preds_fold = []
-        model = PetNet(model_name = Config_exp66.model_name, out_features = 1, inp_channels = 3, pretrained=False)
-        model.load_state_dict(torch.load(model_path))
-        model = model.to(device)
-        model = model.float()
-        model.eval() 
-        test_preds_fold = tta_fn(thefile, model, Config_exp66.im_size, [0])
-        test_preds_model.append(test_preds_fold)
+    test_preds_fold = []
+    model = PetNet(model_name = 'swin_large_patch4_window12_384_in22k', out_features = 1, inp_channels = 3, pretrained=False)
+    model.load_state_dict(torch.load('swin_large_patch4_window12_384_in22k_fold0_half.pth'))
+    model = model.to(device)
+    model = model.float()
+    model.eval() 
+    test_preds_fold = tta_fn(thefile, model, 384, [0])
+    test_preds_model.append(test_preds_fold)
     final_predictions66 = np.mean(np.array(test_preds_model), axis=0)
-    print(f'>>>exp66: ', final_predictions66)
     #}}}
-    # 08. Inference exp77 {{{
-    class Config_exp77(Config):
-        model_dir = 'exp77'
-        model_name = "beit_large_patch16_224"
-
+    # 08. Inference 4 {{{
     class PetNet_exp77(nn.Module):
         def __init__(self, model_name, out_features = 1, inp_channels = 3, pretrained = False):
             super().__init__()
@@ -223,19 +189,15 @@ def score(input_img):
     test_preds = []
     test_preds_model = []
     modelfiles = glob(Config.model_base_dir + Config_exp77.model_dir + Config.model_file_ext)
-
-    for model_index, model_path in enumerate(modelfiles):
-        print(f'inferencing with: {model_path}')
-        test_preds_fold = []
-        model = PetNet_exp77(model_name = Config_exp77.model_name, out_features = 1, inp_channels = 3, pretrained=False)
-        model.load_state_dict(torch.load(model_path))
-        model = model.to(device)
-        model = model.float()
-        model.eval() 
-        test_preds_fold = tta_fn(thefile, model, Config.im_size, [0])
-        test_preds_model.append(test_preds_fold)
+    test_preds_fold = []
+    model = PetNet_exp77(model_name = 'beit_large_patch16_224', out_features = 1, inp_channels = 3, pretrained=False)
+    model.load_state_dict(torch.load('beit_large_patch16_224_fold1_half.pth'))
+    model = model.to(device)
+    model = model.float()
+    model.eval() 
+    test_preds_fold = tta_fn(thefile, model, Config.im_size, [0])
+    test_preds_model.append(test_preds_fold)
     final_predictions77 = np.mean(np.array(test_preds_model), axis=0)
-    print(f'>>>exp77: ', final_predictions77)
     #}}}
     # 09. Final predicted scores {{{
     final_predictions = (3*final_predictions53 +