End of training

README.md

@@ -0,0 +1,65 @@
+---
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: alexnet-pneumonia
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# alexnet-pneumonia
+
+This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1142
+- Accuracy: 0.9541
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 16
+- eval_batch_size: 50
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.3989        | 0.99  | 52   | 0.3528          | 0.8484   |
+| 0.22          | 2.0   | 105  | 0.1949          | 0.9296   |
+| 0.1723        | 2.99  | 157  | 0.2775          | 0.8962   |
+| 0.1758        | 4.0   | 210  | 0.1318          | 0.9475   |
+| 0.1117        | 4.95  | 260  | 0.1192          | 0.9558   |
+
+
+### Framework versions
+
+- Transformers 4.33.2
+- Pytorch 2.0.1+cu117
+- Datasets 2.14.4
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,13 @@
+{
+  "architectures": [
+    "AlexNetPneumoniaClassification"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_alexnet.AlexNetConfig",
+    "AutoModelForImageClassification": "modeling_alexnet.AlexNetPneumoniaClassification"
+  },
+  "input_channels": 3,
+  "model_type": "alexnet",
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.2"
+}

configuration_alexnet.py

@@ -0,0 +1,14 @@
+# create pretrainconfig
+from transformers import PretrainedConfig
+
+class AlexNetConfig(PretrainedConfig):
+  model_type = "alexnet"
+  def __init__(self, id2label=None, label2id=None, labels=[], **kwargs):    
+    self.input_channels = 3
+    self.output_hidden_states = True
+    self.return_dict = True
+    self.id2label=id2label
+    self.label2id=label2id
+    self.num_labels = len(labels)
+    self.model_type = "alexnet"
+    super().__init__(**kwargs)

modeling_alexnet.py

@@ -0,0 +1,47 @@
+import torch.nn as nn
+import torch
+from transformers.modeling_outputs import SequenceClassifierOutput
+from transformers.modeling_utils import PreTrainedModel
+from alexnet_model.configuration_alexnet import AlexNetConfig
+
+class AlexNetPneumoniaClassification(PreTrainedModel):
+    config_class = AlexNetConfig
+
+    def __init__(self, config):
+        super(AlexNetPneumoniaClassification, self).__init__(config)
+        self.num_labels = config.num_labels
+        self.conv1 = nn.Conv2d(3, 96, kernel_size=11, stride=4, padding=0)
+        self.conv2 = nn.Conv2d(96, 256, kernel_size=5, stride=1,padding=2)                              
+        self.conv3 = nn.Conv2d(256, 384, kernel_size=3, stride=1, padding=1)
+        self.conv4 = nn.Conv2d(384, 384, kernel_size=3, stride=1, padding=1)
+        self.conv5 = nn.Conv2d(384, 256, kernel_size=3, stride=1, padding=1)
+        self.fc1 = nn.Linear(256*6*6, 4096)
+        self.fc2 = nn.Linear(4096, 4096)
+        self.fc3  = nn.Linear(4096, config.num_labels)
+        
+    def forward(self, pixel_values, labels=None):
+        x = torch.relu(self.conv1(pixel_values))
+        x = torch.max_pool2d(x, kernel_size=3, stride=2, padding=0)
+        x = torch.relu(self.conv2(x))
+        x = torch.max_pool2d(x, kernel_size=3, stride=2, padding=0)
+        x = torch.relu(self.conv3(x))
+        x = torch.relu(self.conv4(x))
+        x = torch.relu(self.conv5(x))
+        x = torch.max_pool2d(x, kernel_size=3, stride=2, padding=0)
+        x = x.view(-1, 256*6*6)
+        x = torch.relu(self.fc1(x))
+        x = torch.relu(self.fc2(x))
+        logits = self.fc3(x)        
+        
+        loss = None
+        if labels is not None:
+          loss_fct = nn.CrossEntropyLoss()
+          loss = loss_fct(logits.view(-1, self.num_labels), labels)
+          return SequenceClassifierOutput(
+            loss=loss,
+            logits=logits,
+          )
+        
+        return SequenceClassifierOutput(
+          logits=torch.softmax(logits, dim=1),
+        )

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:080a47fa65872669b93dea27128d61e5bad4ba19df81a6e38ac2f643e55a0de6
+size 233163169

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c5faf82b2dc0e79d48d4a7477bca55fd4c964b6d7d10465f256be6f6dacb523
+size 4027