First version

.gitattributes

@@ -32,3 +32,4 @@ 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
+*.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text

app.py

@@ -1,7 +1,188 @@
+import pathlib
+import validators
+import requests
 import gradio as gr
+# For running inference on the TF-Hub module.
+import tensorflow as tf
 
-def greet(name):
-    return "Hello " + name + "!!"
+# For downloading the image.
+import matplotlib.pyplot as plt
+import tempfile
+from six import BytesIO
 
-iface = gr.Interface(fn=greet, inputs="text", outputs="text")
-iface.launch()
+# For drawing onto the image.
+import numpy as np
+from PIL import Image
+from PIL import ImageColor
+from PIL import ImageDraw
+from PIL import ImageFont
+from PIL import ImageOps
+
+print("load model...")
+detector = tf.saved_model.load("model")
+
+
+def draw_bounding_box_on_image(image,
+                               ymin,
+                               xmin,
+                               ymax,
+                               xmax,
+                               color,
+                               font,
+                               thickness=4,
+                               display_str_list=()):
+    """Adds a bounding box to an image."""
+    draw = ImageDraw.Draw(image)
+    im_width, im_height = image.size
+    (left, right, top, bottom) = (xmin * im_width, xmax * im_width,
+                                  ymin * im_height, ymax * im_height)
+    draw.line([(left, top), (left, bottom), (right, bottom), (right, top),
+               (left, top)],
+              width=thickness,
+              fill=color)
+
+    # If the total height of the display strings added to the top of the bounding
+    # box exceeds the top of the image, stack the strings below the bounding box
+    # instead of above.
+    display_str_heights = [font.getsize(ds)[1] for ds in display_str_list]
+    # Each display_str has a top and bottom margin of 0.05x.
+    total_display_str_height = (1 + 2 * 0.05) * sum(display_str_heights)
+
+    if top > total_display_str_height:
+        text_bottom = top
+    else:
+        text_bottom = top + total_display_str_height
+    # Reverse list and print from bottom to top.
+    for display_str in display_str_list[::-1]:
+        text_width, text_height = font.getsize(display_str)
+        margin = np.ceil(0.05 * text_height)
+        draw.rectangle([(left, text_bottom - text_height - 2 * margin),
+                        (left + text_width, text_bottom)],
+                       fill=color)
+        draw.text((left + margin, text_bottom - text_height - margin),
+                  display_str,
+                  fill="black",
+                  font=font)
+        text_bottom -= text_height - 2 * margin
+
+
+"""Overlay labeled boxes on an image with formatted scores and label names."""
+
+
+def draw_boxes(image, boxes, class_names, scores, max_boxes=10, min_score=0.1):
+    colors = list(ImageColor.colormap.values())
+
+    try:
+        font = ImageFont.truetype("/usr/share/fonts/truetype/liberation/LiberationSansNarrow-Regular.ttf",
+                                  25)
+    except IOError:
+        print("Font not found, using default font.")
+        font = ImageFont.load_default()
+
+    for i in range(min(boxes.shape[0], max_boxes)):
+        if scores[i][0] >= min_score:
+            ymin, xmin, ymax, xmax = tuple(boxes[i][0])
+            display_str = "{}: {}%".format(class_names[i],
+                                           int(100 * scores[i][0]))
+            color = colors[hash(class_names[i]) % len(colors)]
+            image_pil = Image.fromarray(np.uint8(image)).convert("RGB")
+            draw_bounding_box_on_image(
+                image_pil,
+                ymin,
+                xmin,
+                ymax,
+                xmax,
+                color,
+                font,
+                display_str_list=[display_str])
+            np.copyto(image, np.array(image_pil))
+    return image
+
+
+def run_detector(url_input, image_input, minscore=0.1):
+
+    if (validators.url(url_input)):
+        img = Image.open(requests.get(url_input, stream=True).raw)
+    elif (image_input):
+        img = image_input
+
+    converted_img = tf.image.convert_image_dtype(img, tf.uint8)[
+        tf.newaxis, ...]
+    result = detector(converted_img)
+
+    result = {key: value.numpy() for key, value in result.items()}
+
+    print("Found %d objects." % len(result["detection_scores"]))
+    labels = ["cyclist" for _ in range(len(result["detection_scores"]))]
+    print(labels)
+
+    image_with_boxes = draw_boxes(
+        np.array(img), result["detection_boxes"],
+        labels, result["detection_scores"], min_score=minscore)
+
+    return image_with_boxes
+
+
+css = '''
+h1#title {
+  text-align: center;
+}
+'''
+demo = gr.Blocks(css=css)
+
+title = """<h1 id="title">Custom Cyclists detector</h1>"""
+description = "todo"
+
+
+def set_example_image(example: list) -> dict:
+    return gr.Image.update(value=example[0])
+
+
+def set_example_url(example: list) -> dict:
+    return gr.Textbox.update(value=example[0])
+
+
+urls = ["https://hips.hearstapps.com/hmg-prod.s3.amazonaws.com/images/cyclist-on-path-by-sea-royalty-free-image-1656931301.jpg?crop=0.727xw:0.699xh;0.134xw,0.169xh&resize=640:*"]
+
+with demo:
+    gr.Markdown(title)
+    gr.Markdown(description)
+    slider_input = gr.Slider(minimum=0.0, maximum=1,
+                             value=0.2, label='Prediction Threshold')
+
+    with gr.Tabs():
+        with gr.TabItem('Image URL'):
+            with gr.Row():
+                url_input = gr.Textbox(
+                    lines=2, label='Enter valid image URL here..')
+                img_output_from_url = gr.Image(shape=(640, 640))
+
+            with gr.Row():
+                example_url = gr.Dataset(components=[url_input], samples=[
+                                         [str(url)] for url in urls])
+
+            url_but = gr.Button('Detect')
+
+        with gr.TabItem('Image Upload'):
+            with gr.Row():
+                img_input = gr.Image(type='pil')
+                img_output_from_upload = gr.Image(shape=(650, 650))
+
+            with gr.Row():
+                example_images = gr.Dataset(components=[img_input],
+                                            samples=[[path.as_posix()]
+                                                     for path in sorted(pathlib.Path('images').rglob('*.jpg'))])
+
+            img_but = gr.Button('Detect')
+
+    url_but.click(run_detector, inputs=[
+                  url_input, img_input, slider_input], outputs=img_output_from_url, queue=True)
+    img_but.click(run_detector, inputs=[
+                  url_input, img_input, slider_input], outputs=img_output_from_upload, queue=True)
+    example_images.click(fn=set_example_image, inputs=[
+                         example_images], outputs=[img_input])
+    example_url.click(fn=set_example_url, inputs=[
+                      example_url], outputs=[url_input])
+
+
+demo.launch(enable_queue=True)

model/pipeline.config

@@ -0,0 +1,195 @@
+model {
+  ssd {
+    num_classes: 1
+    image_resizer {
+      keep_aspect_ratio_resizer {
+        min_dimension: 640
+        max_dimension: 640
+        pad_to_max_dimension: true
+      }
+    }
+    feature_extractor {
+      type: "ssd_efficientnet-b1_bifpn_keras"
+      conv_hyperparams {
+        regularizer {
+          l2_regularizer {
+            weight: 4e-05
+          }
+        }
+        initializer {
+          truncated_normal_initializer {
+            mean: 0.0
+            stddev: 0.03
+          }
+        }
+        activation: SWISH
+        batch_norm {
+          decay: 0.99
+          scale: true
+          epsilon: 0.001
+        }
+        force_use_bias: true
+      }
+      bifpn {
+        min_level: 3
+        max_level: 7
+        num_iterations: 4
+        num_filters: 88
+      }
+    }
+    box_coder {
+      faster_rcnn_box_coder {
+        y_scale: 1.0
+        x_scale: 1.0
+        height_scale: 1.0
+        width_scale: 1.0
+      }
+    }
+    matcher {
+      argmax_matcher {
+        matched_threshold: 0.5
+        unmatched_threshold: 0.5
+        ignore_thresholds: false
+        negatives_lower_than_unmatched: true
+        force_match_for_each_row: true
+        use_matmul_gather: true
+      }
+    }
+    similarity_calculator {
+      iou_similarity {
+      }
+    }
+    box_predictor {
+      weight_shared_convolutional_box_predictor {
+        conv_hyperparams {
+          regularizer {
+            l2_regularizer {
+              weight: 4e-05
+            }
+          }
+          initializer {
+            random_normal_initializer {
+              mean: 0.0
+              stddev: 0.01
+            }
+          }
+          activation: SWISH
+          batch_norm {
+            decay: 0.99
+            scale: true
+            epsilon: 0.001
+          }
+          force_use_bias: true
+        }
+        depth: 88
+        num_layers_before_predictor: 3
+        kernel_size: 3
+        class_prediction_bias_init: -4.6
+        use_depthwise: true
+      }
+    }
+    anchor_generator {
+      multiscale_anchor_generator {
+        min_level: 3
+        max_level: 7
+        anchor_scale: 4.0
+        aspect_ratios: 1.0
+        aspect_ratios: 2.0
+        aspect_ratios: 0.5
+        scales_per_octave: 3
+      }
+    }
+    post_processing {
+      batch_non_max_suppression {
+        score_threshold: 1e-08
+        iou_threshold: 0.5
+        max_detections_per_class: 100
+        max_total_detections: 100
+      }
+      score_converter: SIGMOID
+    }
+    normalize_loss_by_num_matches: true
+    loss {
+      localization_loss {
+        weighted_smooth_l1 {
+        }
+      }
+      classification_loss {
+        weighted_sigmoid_focal {
+          gamma: 1.5
+          alpha: 0.25
+        }
+      }
+      classification_weight: 1.0
+      localization_weight: 1.0
+    }
+    encode_background_as_zeros: true
+    normalize_loc_loss_by_codesize: true
+    inplace_batchnorm_update: true
+    freeze_batchnorm: false
+    add_background_class: false
+  }
+}
+train_config {
+  batch_size: 3
+  data_augmentation_options {
+    random_horizontal_flip {
+      probability: 0.3
+    }
+  }
+  data_augmentation_options {
+    random_scale_crop_and_pad_to_square {
+      output_size: 640
+      scale_min: 0.1
+      scale_max: 2.0
+    }
+  }
+  data_augmentation_options {
+    random_distort_color {
+      color_ordering: 1
+    }
+  }
+  sync_replicas: true
+  optimizer {
+    momentum_optimizer {
+      learning_rate {
+        cosine_decay_learning_rate {
+          learning_rate_base: 0.02
+          total_steps: 300000
+          warmup_learning_rate: 0.001
+          warmup_steps: 2500
+        }
+      }
+      momentum_optimizer_value: 0.9
+    }
+    use_moving_average: false
+  }
+  fine_tune_checkpoint: "pre-trained-models/efficientdet_d1_coco17_tpu-32/checkpoint/ckpt-0"
+  num_steps: 300000
+  startup_delay_steps: 0.0
+  replicas_to_aggregate: 8
+  max_number_of_boxes: 100
+  unpad_groundtruth_tensors: false
+  fine_tune_checkpoint_type: "detection"
+  use_bfloat16: false
+  fine_tune_checkpoint_version: V2
+}
+train_input_reader {
+  label_map_path: "annotations/label_map.pbtxt"
+  tf_record_input_reader {
+    input_path: "annotations/train.record"
+  }
+}
+eval_config {
+  metrics_set: "coco_detection_metrics"
+  use_moving_averages: false
+  batch_size: 1
+}
+eval_input_reader {
+  label_map_path: "annotations/label_map.pbtxt"
+  shuffle: true
+  num_epochs: 1
+  tf_record_input_reader {
+    input_path: "annotations/validation.record"
+  }
+}

model/saved_model/saved_model.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8935bf4db280c457ea008e4f1f86463d8d9f6c6ae4320b3a30150859c3c298f
+size 22291244

model/saved_model/variables/variables.data-00000-of-00001

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1da925cefb226e8bccd26e171f658e4f237cb96e0e576db580e3c13c81d369c9
+size 33885404