Upload final_run_concurrent.py

final_run_concurrent.py

@@ -0,0 +1,205 @@
+# -*- coding: utf-8 -*-
+"""Final Run-Concurrent
+
+Automatically generated by Colaboratory.
+
+Original file is located at
+    https://colab.research.google.com/drive/19foLOwCXRH0e0P_Xqqc-9VgpnmjYyAX8
+"""
+
+# Install the Necessary Packages
+
+!pip install datasets huggingface_hub sentence-transformers gradio evaluate
+!pip install git+https://github.com/huggingface/accelerate
+!pip install transformers==4.28.0
+
+import datasets
+from datasets import load_dataset
+import pandas
+from PIL import Image
+import cv2
+import os
+from pandas import read_csv
+from google.colab import drive
+
+drive.mount('/content/drive/')
+
+raw_dataset = load_dataset("imagefolder", data_dir="/content/drive/MyDrive/california_fire_damage_classification_merged/train")
+dataset = raw_dataset["train"].train_test_split(test_size=0.2, stratify_by_column="label")
+
+from transformers import ViTImageProcessor, ViTForImageClassification
+import torch
+
+device = 'cuda' # for GPU
+
+model = ViTForImageClassification.from_pretrained('google/vit-base-patch16-224')
+
+model.eval()
+#model.to(device);
+
+# image_processor is the same as Tokenizer
+extractor = ViTImageProcessor.from_pretrained('google/vit-base-patch16-224')
+
+labels = raw_dataset['train'].features['label'].names
+
+labels
+
+from transformers import AutoFeatureExtractor, AutoModelForImageClassification, AutoTokenizer
+
+extractor = AutoFeatureExtractor.from_pretrained("/content/drive/MyDrive/california_fire_damage_classification_merged/saved_model_files")
+model = AutoModelForImageClassification.from_pretrained("/content/drive/MyDrive/california_fire_damage_classification_merged/saved_model_files")
+
+import torch
+
+def transform(example_batch):
+    inputs = extractor([x.convert("RGB") for x in example_batch['image']], return_tensors='pt')
+    inputs['labels'] = example_batch['label']
+    return inputs
+
+prepared_ds = dataset.with_transform(transform)
+
+### RUNNING EVALUATION ON PRETRAINED MODEL
+
+from transformers import TrainingArguments, Trainer
+
+training_args = TrainingArguments("test_trainer"),
+
+
+import numpy as np
+from datasets import load_metric
+
+metric = load_metric("accuracy")
+
+
+def compute_metrics(eval_pred):
+    logits, labels = eval_pred
+    predictions = np.argmax(logits, axis=-1)
+    return metric.compute(predictions=predictions, references=labels)
+
+
+trainer = Trainer(
+    model=model,
+    args=training_args,
+    train_dataset=None,
+    eval_dataset=prepared_ds['test'],
+    compute_metrics=compute_metrics,
+)
+
+j = 2095
+
+print('Groundtruth: ', y_test_np[j], ' ', labels[y_test_np[j]], 'Prediction: ', y_predicts_np[j], ' ', labels[y_predicts_np[j]])
+dataset['test'][j]['image']
+
+pixel_values_array = []
+y_test = []
+counter = 0
+
+for img_pair in prepared_ds['test']:
+  pixel_values_array.append(img_pair['pixel_values'])
+  y_test.append(img_pair["labels"])
+  #pixel_values_tensor = torch.concat((pixel_values_tensor, img_pair['pixel_values']), 0)
+  counter += 1
+  print(counter)
+
+#pixel_values_tensor = torch.stack(pixel_values_array)
+
+#pixel_values_tensor
+
+len(pixel_values_tensor)
+len(y_predicts_merged)
+
+import numpy as np
+y_test_np = np.array(y_test)
+y_predicts_np = np.array(y_predicts_merged)
+
+np.where((y_test_np == y_predicts_np) == False)
+
+y_predicts = []
+
+for i in range(len(pixel_values_tensor)):
+  logits = model(pixel_values_tensor[i:i+1])[-1]
+  y_predict = [logit.argmax(-1).item() for logit in logits]
+  y_predicts.append(y_predict)
+
+y_predicts
+
+y_predicts_merged = [inner for outer in y_predicts for inner in outer]
+
+y_predicts_merged
+
+logits = model(pixel_values_tensor[0:1])[-1]
+
+logits
+
+y_predict = [logit.argmax(-1).item() for logit in logits]
+y_predict
+
+#y_test = [img_pair["labels"] for img_pair in prepared_ds['test']]
+y_test = prepared_ds['test'][0:100]["labels"]
+y_test
+
+from sklearn.metrics import classification_report, confusion_matrix
+
+print(confusion_matrix(y_test, y_predicts_merged))
+print(classification_report(y_test, y_predicts_merged))
+
+probability = torch.nn.functional.softmax(logits, dim=-1)
+probability
+
+probs = probability.detach().numpy()
+probs
+
+confidences = [{label: float(prob[j]) for j, label in enumerate(labels)} for prob in probs]
+confidences
+
+# First we get the features corresponding to the first training image
+encoding = image_processor(images=prepared_ds['test'][0]['image'], return_tensors="pt").to(device)
+
+# Then pass it through the model and get a prediction
+
+######
+outputs = model(**encoding)
+logits = outputs.logits
+######
+
+prediction = logits.argmax(-1).item()
+
+print("Predicted class:", model.config.id2label[prediction])
+
+# For 1 Sample -> look at distribution of probabilities assigned
+
+tokenizer = AutoTokenizer.from_pretrained("google/vit-base-patch16-224")
+
+def tokenize_function(examples):
+    return tokenizer(examples["text"], padding="max_length", truncation=True)
+
+encoding = image_processor(images=[prepared_ds["test"][0]['image']], return_tensors="pt").to(device)
+outputs = model(**encoding)
+logits = outputs.logits
+prediction = logits.argmax(-1).item()
+
+print("Predicted class:", model.config.id2label[prediction])
+
+im_test = [dataset['test'][0]['image'], dataset['test'][1]['image']]
+features_test = extractor(im_test, return_tensors='pt')
+features_test['pixel_values'][0]
+
+
+
+features_test['pixel_values'][-1]
+
+logits = model(features_test["pixel_values"])
+logits[-1]
+
+probability = torch.nn.functional.softmax(logits, dim=-1)
+
+logits = model(features_test["pixel_values"])[-1]
+
+probs = probability[0].detach().numpy()
+confidences = {label: float(probs[i]) for i, label in enumerate(labels)}
+
+probability = torch.nn.functional.softmax(logits, dim=-1)
+probability
+
+prepared_ds['test'][0]['pixel_values']
+