Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+variables/variables.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,155 @@
----
-license: mit
----
+---
+language:
+  - en
+thumbnail: "/assets/image.jpg"
+tags:
+  - image-classification
+  - computer-vision
+  - agriculture
+  - maize-diseases
+  - agroeye
+  - eligapris
+  - grey
+license: mit
+metrics:
+  - accuracy
+pipeline_tag: image-classification
+---
+
+# agroEye
+
+This model is designed to detect diseases in maize (corn) leaves using computer vision techniques.
+
+## Model description
+
+The agroEye is a convolutional neural network (CNN) trained to classify images of maize leaves into four categories: Healthy, Gray Leaf Spot, Blight, and Common Rust. It aims to assist farmers and agricultural professionals in quickly identifying common maize diseases, potentially leading to earlier interventions and improved crop management.
+
+### Intended uses & limitations
+
+The model is intended for use as a diagnostic tool to assist in the identification of maize leaf diseases. It should be used in conjunction with expert knowledge and not as a sole means of diagnosis. The model's performance may vary depending on image quality, lighting conditions, and the presence of diseases or conditions not included in the training dataset.
+
+**Limitations:**
+- The model is trained on a specific dataset and may not generalize well to significantly different growing conditions or maize varieties.
+- It is not designed to detect diseases other than the four categories it was trained on.
+- Performance on images with multiple diseases present has not been extensively tested.
+- The model should not be used as a replacement for professional agricultural advice.
+
+### How to use
+
+Here's a basic example of how to use the model:
+
+```python
+import tensorflow as tf
+from PIL import Image
+import numpy as np
+import json
+
+import tensorflow as tf
+from huggingface_hub import snapshot_download
+
+# Download the entire model directory
+model_dir = snapshot_download(repo_id="eligapris/agroeye",
+    local_dir="path/to/model")
+
+# Load the model
+model = tf.saved_model.load('path/to/model')
+
+# Now you can use the model for inference
+
+# Load and preprocess the image
+img = Image.open('/path/to/image.jpg')
+img = img.resize((300, 300 * img.size[1] // img.size[0]))  
+img_array = np.array(img)[None]
+
+# Make prediction
+inp = tensorflow.constant(img_array, dtype='float32')
+prediction = model(inp)[0].numpy()
+
+# Load class names
+with open('path/to/model/classes.json', 'r') as f:
+    class_names = json.load(f)
+
+# Get the predicted class
+predicted_class = list(class_names.keys())[prediction.argmax()]
+print(f"Predicted class: {predicted_class}")
+```
+
+
+Here's a detailed output of model prediction:
+
+```python
+import tensorflow as tf
+from PIL import Image
+import numpy as np
+import json
+
+import tensorflow as tf
+from huggingface_hub import snapshot_download
+
+# Download the entire model directory
+model_dir = snapshot_download(repo_id="eligapris/agroeye",
+    local_dir="path/to/model")
+
+# Load the model
+model = tf.saved_model.load('path/to/model')
+
+# Now you can use the model for inference
+
+# Load and preprocess the image
+img = Image.open('/path/to/image.jpg')
+img = img.resize((300, 300 * img.size[1] // img.size[0]))  
+img_array = np.array(img)[None]
+
+# Make prediction
+inp = tensorflow.constant(img_array, dtype='float32')
+prediction = model(inp)[0].numpy()
+
+# Load class names and details
+with open('model/classes_detailed.json', 'r') as f:
+    data = json.load(f)
+
+class_names = data['classes']
+class_details = data['details']
+
+# Get the predicted class
+predicted_class = list(class_names.keys())[prediction.argmax()]
+predicted_class_label = class_names[predicted_class]
+
+print(f"Predicted class: {predicted_class} (Label: {predicted_class_label})")
+
+# Print detailed information about the predicted class
+if predicted_class in class_details:
+    details = class_details[predicted_class]
+    print("\nDetailed Information:")
+    for key, value in details.items():
+        if isinstance(value, list):
+            print(f"{key.capitalize()}:")
+            for item in value:
+                print(f"  - {item}")
+        else:
+            print(f"{key.capitalize()}: {value}")
+
+# Print general notes
+print("\nGeneral Notes:")
+for note in data['general_notes']:
+    print(f"- {note}")
+```
+
+### Test the colab 
+```
+https://colab.research.google.com/drive/13-S-obR6MZDDP5kgj6ytsbFiNKzzfXbp
+```
+
+## Ethical considerations
+
+- The model's predictions should not be used as the sole basis for agricultural decisions that may impact food security or farmers' livelihoods.
+- There may be biases in the training data that could lead to reduced performance for certain maize varieties or growing conditions not well-represented in the dataset.
+- Users should be made aware of the model's limitations and the importance of expert validation.
+
+## Model Card Authors
+
+Grey
+
+## Model Card Contact
+
+eligapris

classes.json

@@ -0,0 +1 @@
+{"Northern_Leaf_Blight": 0, "Gray_Leaf_Spot": 1, "Healthy_Leaf": 2, "Common_Rust": 3}

classes_detailed.json

@@ -0,0 +1,76 @@
+{
+  "classes": {
+    "Healthy": 0,
+    "Gray_Leaf_Spot": 1,
+    "Blight": 2,
+    "Common_Rust": 3
+  },
+  "details": {
+    "Healthy": {
+      "description": "Plants show no signs of disease.",
+      "characteristics": [
+        "Vibrant green color",
+        "Uniform leaf structure",
+        "No spots or lesions",
+        "Normal growth and development"
+      ],
+      "importance": "Represents the ideal state of the crop, with maximum yield potential."
+    },
+    "Gray_Leaf_Spot": {
+      "causative_agent": "Cercospora zeae-maydis, C. sorghi var. maydis",
+      "symptoms": [
+        "Small, regular, elongated brown-gray necrotic spots growing parallel to the veins",
+        "Lesions may reach 3.0 x 0.3 cm",
+        "Lesions may coalesce, producing a complete burning of large areas of the leaves"
+      ],
+      "environmental_conditions": [
+        "Prevalent in subtropical and temperate, humid areas",
+        "Favored by extended periods of leaf wetness and cloudy conditions"
+      ],
+      "impact": "Can result in severe leaf senescence following flowering and poor grain fill",
+      "notes": [
+        "Also known as cercospora leaf spot",
+        "Minimum tillage practices have been associated with increased incidence"
+      ]
+    },
+    "Blight": {
+      "note": "This typically refers to Northern Corn Leaf Blight, but could include other types of blight",
+      "causative_agent": "Setosphaeria turcica (Teleomorph), Exserohilum turcicum (Anamorph)",
+      "symptoms": [
+        "Small, oval, water-soaked spots on leaves",
+        "Spots grow into elongated, spindle-shaped necrotic lesions",
+        "Lesions may appear first on lower leaves and increase in number as the plant develops",
+        "Can lead to complete burning of the foliage"
+      ],
+      "environmental_conditions": [
+        "Occurs worldwide, particularly in areas with high humidity and moderate temperatures",
+        "Prevalent during the growing season"
+      ],
+      "impact": "When infection occurs prior to and at silking and conditions are optimum, it may cause significant economic damage"
+    },
+    "Common_Rust": {
+      "causative_agent": "Puccinia sorghi",
+      "symptoms": [
+        "Small, elongate, powdery pustules over both surfaces of the leaves",
+        "Pustules are dark brown in early stages of infection",
+        "Later, the epidermis is ruptured and the lesions turn black as the plant matures"
+      ],
+      "environmental_conditions": [
+        "Found worldwide in subtropical, temperate, and highland environments with high humidity"
+      ],
+      "impact": "Can reduce yield, especially if infection is severe before or during tasseling",
+      "notes": [
+        "Most conspicuous when plants approach tasseling",
+        "Alternate host (Oxalis spp.) may show light orange colored pustules"
+      ]
+    }
+  },
+  "general_notes": [
+    "Early detection and proper identification of these diseases are crucial for effective management.",
+    "Integrated pest management strategies, including resistant varieties, crop rotation, and timely fungicide applications, can help control these diseases.",
+    "Climate conditions, particularly humidity and temperature, play a significant role in the development and spread of these diseases.",
+    "Many diseases can have similar symptoms, so careful observation and sometimes laboratory analysis may be necessary for accurate diagnosis.",
+    "The severity of disease impact often depends on the timing of infection relative to the plant's growth stage.",
+    "Some pathogens can infect multiple parts of the plant, including leaves, stalks, and ears."
+  ]
+}

example.py

@@ -0,0 +1,23 @@
+
+# TF for image classification model
+
+import tensorflow
+import numpy
+from PIL import Image
+
+model = tensorflow.saved_model.load('./')
+classes = [ "Northern_Leaf_Blight" ,  "Gray_Leaf_Spot" ,  "Healthy_Leaf" ,  "Common_Rust" , ]
+
+img = Image.open("image.jpg").convert('RGB')
+img = img.resize((300, 300 * img.size[1] // img.size[0]), Image.ANTIALIAS)
+inp_numpy = numpy.array(img)[None]
+
+
+inp = tensorflow.constant(inp_numpy, dtype='float32')
+
+class_scores = model(inp)[0].numpy()
+
+
+print("")
+print("class_scores", class_scores)
+print("Class : ", classes[class_scores.argmax()])

saved_model.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:643a3ac8a4c92c47a2f54bc4561d00c168e7bda725c15315d5b407e2e6a5fa1d
+size 6448188

variables/variables.data-00000-of-00001

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3da3190395e6a00fbc78f5c5f964335d0664d4ae9a1bc01e6531686270b2d366
+size 18311730