DS598 - Midterm - Project - Bill Jiao

cnnlstm_train.sh

@@ -9,7 +9,7 @@ module load academic-ml/spring-2024
 conda activate spring-2024-pyt
 
 # Change this path to point to your project directory
-export PYTHONPATH="/projectnb/ds598/admin/tgardos/sp2024_midterm:$PYTHONPATH" # Set this!!!
+export PYTHONPATH="/projectnb/ds598/students/jiaobill/sp2024_midterm:$PYTHONPATH" # Set this!!!
 
 python -m spacy download en_core_web_sm   # download spacy model
 python src/cnn_lstm/train.py

src/base/constants.py

@@ -5,7 +5,7 @@
 import spacy
 
 # set this path to where you want to save results
-BASE_DIR = "/projectnb/ds598/projects/tgardos/sp2024_midterm/"
+BASE_DIR = "/projectnb/ds598/students/jiaobill/sp2024_midterm/"
 
 # Do not edit. This points to the dataset folder
 DATA_BASE_DIR = "/projectnb/ds598/materials/datasets/vizwiz/captions/"
@@ -53,5 +53,5 @@
 DEMO_STD = np.array([58.395, 57.120, 57.375]) / 255
 
 # SAVE PATHS
-DEMO_SAVE_PATH = BASE_DIR + "RESULTS/git"
+DEMO_SAVE_PATH = BASE_DIR + "RESULTS/git_new"
 CNNLSTM_SAVE_PATH = BASE_DIR + "RESULTS/cnn_lstm"

src/demo_model/test.py

@@ -33,7 +33,7 @@
 #
 # Of course you should use the same model you trained with.
 try:
-    processor = AutoProcessor.from_pretrained("replace-with-model-choice", cache_dir=CACHE_DIR)
+    processor = AutoProcessor.from_pretrained("microsoft/git-base", cache_dir=CACHE_DIR)
 except Exception as e:
     print("You need to pick a pre-trained model from HuggingFace.")
     print("Exception: ", e)

src/demo_model/train.py

@@ -32,7 +32,7 @@
 # to encode and decode text and images.
 # https://huggingface.co/docs/transformers/model_doc/auto#transformers.AutoProcessor
 try:
-    processor = AutoProcessor.from_pretrained("replace-with-model-choice", cache_dir=CACHE_DIR)
+    processor = AutoProcessor.from_pretrained("microsoft/git-base", cache_dir=CACHE_DIR)
 except Exception as e:
     print("You need to pick a pre-trained model from HuggingFace.")
     print("Exception: ", e)
@@ -72,15 +72,15 @@
 # model you want to fine-tune. This will allow you to use the model to train and evaluate
 # on the VizWiz dataset.
 try:
-    model = AutoModelForCausalLM.from_pretrained("replace-with-model-choice", cache_dir=CACHE_DIR)
+    model = AutoModelForCausalLM.from_pretrained("microsoft/git-base", cache_dir=CACHE_DIR)
 except Exception as e:
     print("You need to pick a pre-trained model from HuggingFace.")
     print("Exception: ", e)
+    exit(1)
 
 ## TODO Select your model optimizer
 try:
-    raise NotImplementedError("Select your model optimizer")
-    optimizer = None   # pick one from torch.optim
+    optimizer = torch.optim.AdamW(model.parameters(), lr=0.00001)
 except Exception as e:
     print("You need to pick an optimizer from torch.optim.")
     print("Exception: ", e)
@@ -223,7 +223,7 @@ def get_val_examples(vizwizEval, vizwizRes, plot_captions_dict, epoch, method="C
 
 
 best_score = 0
-for epoch in range(3):
+for epoch in range(10):
     print(f"Epoch: {epoch+1}")
     # Wrap the dataloader with tqdm for a progress bar
     progress_bar = tqdm(
@@ -235,7 +235,7 @@ def get_val_examples(vizwizEval, vizwizRes, plot_captions_dict, epoch, method="C
     logger.info(f"Loss at epoch {epoch}: {loss}")
 
     # Evaluate the model every 3 epochs
-    if epoch % 3 == 0:
+    if epoch % 1 == 0:
         vizwizEval, vizwizRes, plot_captions_dict = evaluate(
             logger,
             epoch,