testing DPT app

.gitignore

@@ -0,0 +1,129 @@
+# Hugging Face Space doesn't like binary files
+*.jpg
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+data/
+results/
+weights/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don’t work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# celery beat schedule file
+celerybeat-schedule
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/

DPT.py

@@ -0,0 +1,62 @@
+import cv2, torch
+import urllib.request
+import numpy as np
+from PIL import Image
+
+MODEL_DICT = {
+    "DPT_Large": "MiDaS v3 - Large (highest accuracy, slowest inference speed)",
+    "DPT_Hybrid": "MiDaS v3 - Hybrid (medium accuracy, medium inference speed)",
+    "MiDaS_small": "MiDaS v2.1 - Small (lowest accuracy, highest inference speed)"
+    }
+
+def load_model(model_type = 'DPT_Large'):
+    assert model_type in MODEL_DICT.keys(), f'{model_type} is not a valid model_type: {MODEL_DICT.keys()}'
+    midas = torch.hub.load("intel-isl/MiDaS", model_type)
+
+    device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
+    midas.to(device)
+    midas.eval()
+
+    midas_transforms = torch.hub.load("intel-isl/MiDaS", "transforms")
+
+    if model_type == "DPT_Large" or model_type == "DPT_Hybrid":
+        transform = midas_transforms.dpt_transform
+    else:
+        transform = midas_transforms.small_transform
+    return {
+        'midas': midas, 'device': device, 'transform': transform
+    }
+
+def inference(img_array_rgb, model_def):
+    '''run DPT model and returns a PIL image'''
+    # img = cv2.imread(img.name)
+    # img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
+    midas = model_def['midas']
+    transform = model_def['transform']
+    device = model_def['device']
+    input_batch = transform(img_array_rgb).to(device)
+
+    with torch.no_grad():
+        prediction = midas(input_batch)
+
+        prediction = torch.nn.functional.interpolate(
+            prediction.unsqueeze(1),
+            size=img_array_rgb.shape[:2],
+            mode="bicubic",
+            align_corners=False,
+        ).squeeze()
+
+    output = prediction.cpu().numpy()
+    formatted = (output * 255 / np.max(output)).astype('uint8')
+    img = Image.fromarray(formatted)
+    return img
+
+# inputs =  gr.inputs.Image(type='file', label="Original Image")
+# outputs = gr.outputs.Image(type="pil",label="Output Image")
+
+# title = "DPT-Large"
+# description = "Gradio demo for DPT-Large:Vision Transformers for Dense Prediction.To use it, simply upload your image, or click one of the examples to load them. Read more at the links below."
+# article = "<p style='text-align: center'><a href='https://arxiv.org/abs/2103.13413' target='_blank'>Vision Transformers for Dense Prediction</a> | <a href='https://github.com/intel-isl/MiDaS' target='_blank'>Github Repo</a></p>"
+#
+# examples=[['dog.jpg']]
+# gr.Interface(inference, inputs, outputs, title=title, description=description, article=article, analytics_enabled=False,examples=examples,    enable_queue=True).launch(debug=True)

app.py

@@ -0,0 +1,103 @@
+import streamlit as st
+
+import os, sys, io
+import urllib.request as urllib
+import numpy as np
+from PIL import Image
+
+import DPT
+
+### Some Utils Functions ###
+def get_image(st_asset = st.sidebar, as_np_arr = False, extension_list = ['jpg', 'jpeg', 'png']):
+	image_url, image_fh = None, None
+	if st_asset.checkbox('use image URL?'):
+		image_url = st_asset.text_input("Enter Image URL")
+	else:
+		image_fh = st_asset.file_uploader(label = "Update your image", type = extension_list)
+
+	im = None
+	if image_url:
+		response = urllib.urlopen(image_url)
+		im = Image.open(io.BytesIO(bytearray(response.read())))
+	elif image_fh:
+		im = Image.open(image_fh)
+
+	if im and as_np_arr:
+		im = np.array(im)
+	return im
+
+def show_miro_logo(use_column_width = False, width = 100, st_asset= st.sidebar):
+	logo_url = 'https://miro.medium.com/max/1400/0*qLL-32srlq6Y_iTm.png'
+	st_asset.image(logo_url, use_column_width = use_column_width, channels = 'BGR', output_format = 'PNG', width = width)
+
+def im_draw_bbox(pil_im, x0, y0, x1, y1, color = 'black', width = 3, caption = None,
+			bbv_label_only = False):
+	'''
+	draw bounding box on the input image pil_im in-place
+	Args:
+		color: color name as read by Pillow.ImageColor
+		use_bbv: use bbox_visualizer
+	'''
+	import bbox_visualizer as bbv
+	if any([type(i)== float for i in [x0,y0,x1,y1]]):
+		warnings.warn(f'im_draw_bbox: at least one of x0,y0,x1,y1 is of the type float and is converted to int.')
+		x0 = int(x0)
+		y0 = int(y0)
+		x1 = int(x1)
+		y1 = int(y1)
+
+	if bbv_label_only:
+		if caption:
+			im_array = bbv.draw_flag_with_label(np.array(pil_im),
+						label = caption,
+						bbox = [x0,y0,x1,y1],
+						line_color = ImageColor.getrgb(color),
+						text_bg_color = ImageColor.getrgb(color)
+						)
+		else:
+			raise ValueError(f'im_draw_bbox: bbv_label_only is True but caption is None')
+	else:
+		im_array = bbv.draw_rectangle(np.array(pil_im),
+					bbox = [x0, y0, x1, y1],
+					bbox_color = ImageColor.getrgb(color),
+					thickness = width
+					)
+		im_array = bbv.add_label(
+					im_array, label = caption,
+					bbox = [x0,y0,x1,y1],
+					text_bg_color = ImageColor.getrgb(color)
+					)if caption else im_array
+	return Image.fromarray(im_array)
+
+### Streamlit App ###
+
+def mod_DPT(pil_im, model_def):
+	depth_im = DPT.inference(img_array_rgb = np.array(pil_im), model_def = model_def)
+	return depth_im
+
+def Main(model_dict):
+	st.set_page_config(layout = 'wide')
+	l_col, r_col = st.columns(2)
+	show_miro_logo(st_asset = l_col)
+	with l_col.expander('Monocular Depth: CNN vs Transformers'):
+		st.info(f'''
+		Comparsion of two models: [BTS (CNN)](https://github.com/ErenBalatkan/Bts-PyTorch)
+		and [DPT (Transformer)](https://huggingface.co/Intel/dpt-large)
+		''')
+
+	im = get_image(st_asset = r_col.expander('Input Image', expanded = True), extension_list = ['jpg','jpeg'])
+	model_name = r_col.selectbox('Pick Model', options = ['DPT','BTS'])
+
+	if im:
+		model_def = DPT.load_model()
+		d_im = mod_DPT(pil_im = im, model_def=model_def)
+
+		l_col, r_col = st.columns(2)
+		l_col.image(im, caption = 'Input Image')
+		r_col.image(saliency_im, caption = 'Depth Map')
+	else:
+		st.warning(f'please provide an image :point_up:')
+
+if __name__ == '__main__':
+	model_dict = load_model()
+	Main(model_dict = model_dict)

requirements.txt

@@ -0,0 +1,10 @@
+opencv-python-headless>=4.5.5.64
+torch==1.8.0
+#matplotlib==3.1.3
+numpy>=1.15.2
+Pillow>=6.2.0
+# DPT
+timm==0.5.4
+# BTS
+albumentations>=1.1.0
+torchvision==0.9.0