Hi, thanks for such fast model, I have tried your code and followed steps. So, initially I am getting this error:

TypeError: Cannot handle this data type: (1, 1, 3), <f4

Traceback (most recent call last): File "F:\ai\deep\fast_neural_style_transfer-dev\main.py", line 71, in <module> main() File "F:\ai\deep\fast_neural_style_transfer-dev\main.py", line 64, in main generated_images = generate(content_targets, model_path, save_path=output_save_path, ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "F:\ai\deep\fast_neural_style_transfer-dev\generate.py", line 23, in generate outputs = _handler2(contents_path, model_path, save_path=save_path, prefix=prefix, suffix=suffix) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "F:\ai\deep\fast_neural_style_transfer-dev\generate.py", line 72, in _handler2 save_images(content_path, output, save_path, prefix=prefix, suffix=suffix) File "F:\ai\deep\fast_neural_style_transfer-dev\utils.py", line 61, in save_images imsave(path, data) File "C:\Users\Najm Abideen\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\imageio\v2.py", line 397, in imwrite return file.write(im, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\Najm Abideen\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\imageio\plugins\pillow.py", line 425, in write pil_frame = Image.fromarray(frame, mode=mode) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\Najm Abideen\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\PIL\Image.py", line 3073, in fromarray raise TypeError(msg) from e TypeError: Cannot handle this data type: (1, 1, 3), <f4

I skipped the error and tried to show the result using: plt.imshow(result[0], interpolation='nearest') plt.show()

but generated result[0] is an empty image, I have seen very little generated noise on following styles:

'wave': [1.0, 7.0, 1e-2], #-

'scream': [1.0, 60.0, 1e-2], #-

'rain_princess': [1.0, 8.0, 1e-2], #-

Actually, I have tried all of your pre trained 10 models. Have also placed the weights file, "imagenet-vgg-verydeep-19.mat" & "imagenet-vgg-19-weights.npz".

I finally was able to save the image using:

if save_path is not None:
    for i, image in enumerate(output):
        # Convert image to the appropriate data type and scale it to 0-255
        image_scaled = (image * 255).astype(np.uint8)
        # Save the image using imageio
        filename = f"{prefix}_{i}_{suffix}.png" if prefix and suffix else f"image_{i}.png"
        imageio.imwrite(f"{save_path}/{filename}", image_scaled)
    #save_images(content_path, output_converted, save_path, prefix=prefix, suffix=suffix)

but images are simply nothing but noise:

Kindly help really appreciate, I don't know why I found this code so late :)

elleryqueenhomels / fast_neural_style_transfer

Unable to produce example results #9

'wave': [1.0, 7.0, 1e-2], #-

'scream': [1.0, 60.0, 1e-2], #-

'rain_princess': [1.0, 8.0, 1e-2], #-