codebasics/potato-disease-classification

Potato Disease Classification - Training, Rest APIs, and Frontend to test.

potato-disease-classification's Issues

ValueError: Exception encountered when calling layer "random_flip" (type RandomFlip).

2023-02-06 23:05:44.031991: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX AVX2
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
Traceback (most recent call last):
File "C:\Users\rudra\OneDrive\Desktop\Projects\potato-disease-classification-main\api\main.py", line 24, in
MODEL = tf.keras.models.load_model("../saved_models/1")
File "C:\Users\rudra\OneDrive\Desktop\Projects\potato-disease-classification-main\api\env\lib\site-packages\keras\utils\traceback_utils.py", line 70, in error_handler
raise e.with_traceback(filtered_tb) from None
File "C:\Users\rudra\OneDrive\Desktop\Projects\potato-disease-classification-main\api\env\lib\site-packages\keras\saving\legacy\saved_model\load.py", line 1015, in _unable_to_call_layer_due_to_serialization_issue
raise ValueError(
ValueError: Exception encountered when calling layer "random_flip" (type RandomFlip).

Cannot call custom layer random_flip of type <class 'keras.saving.legacy.saved_model.load.RandomFlip'>, because the call function was not serialized to the SavedModel.Please try one of the following methods to fix this issue:

(1) Implement get_config and from_config in the layer/model class, and pass the object to the custom_objects argument when loading the model. For more details, see: https://www.tensorflow.org/guide/keras/save_and_serialize

(2) Ensure that the subclassed model or layer overwrites call and not __call__. The input shape and dtype will be automatically recorded when the object is called, and used when saving. To manually specify the input shape/dtype, decorate the call function with @tf.function(input_signature=...).

Call arguments received by layer "random_flip" (type RandomFlip):
• unused_args=('tf.Tensor(shape=(None, 256, 256, 3), dtype=float32)',)
• unused_kwargs={'training': 'None'}

my libs
tensorflow 2.11.0
tensorflow-estimator 2.11.0
tensorflow-intel 2.11.0
tensorflow-io-gcs-filesystem 0.30.0
tensorflow-serving-api 2.11.0
urllib3 1.26.14
uvicorn 0.20.0

Postman error during sending the file

image validation error

when i upload even a meme image , it is classifying as healthy.

Website stuck on an infinite loop

The user interface works fine but when i try to drag and drop the image the backend is not responding

Model Deployed to GCP gives wrong results

When it comes to Model Deployment To GCP. As user inputs, even meme images are giving output with 70% plus accuracy.

Mobile app can't run

isURLSameOrigin.js:57 Uncaught (in promise) TypeError: Cannot read properties of undefined (reading 'protocol')

So I was following part 5 of the codebasics tutorial and when I went to upload my plant file into the drop area it immediately stopped working and gave me this error:

Does anyone know what is going on with the frontend code? I simply copied and pasted it and it is giving me this error.

images_batch error message

Error on this notebook:
potato-disease-classification-model-using-image-data-generator.ipynb

The line:
batch_prediction = model.predict(images_batch)

Getting an error on this line.
images_batch was never defined (misspelling?).

That cell has to be removed.
If you want to keep it alive, need following lines:

first_image = image_batch[0]
first_label = np.argmax(label_batch[0])

plt.imshow(first_image)

img_array = tf.keras.preprocessing.image.img_to_array(first_image)
img_array = tf.expand_dims(img_array, 0)
predictions = model.predict(img_array)
predicted_class = class_names[np.argmax(predictions[0])]

ValueError when drag &drop a pic of different dimension

If we drag and drop a picture of different dimension other than (256 , 256) it shows "value error" of expected shape and found shape.
As I have made changes in main.py of api folder to resolve this bug, so please kindly review the PR #10

Line 193:6: React Hook useEffect has a missing dependency: 'sendFile'. Either include it or remove the dependency array react-hooks/exhaustive-deps

Typing mistake

Sir, in line 3 images[i].numpy() should be img

def predict(model, img):
img_array =
3 tf.keras.preprocessing.image.img_to_array(images[i].numpy())
img_array = tf.expand_dims(img_array, 0)

predictions = model.predict(img_array)

predicted_class = class_names[np.argmax(predictions[0])]
confidence = round(100 * (np.max(predictions[0])), 2)
return predicted_class, confidence