Upload 5 files

dataset.py

@@ -0,0 +1,144 @@
+import tensorflow as tf
+from absl.flags import FLAGS
+
+@tf.function
+def transform_targets_for_output(y_true, grid_size, anchor_idxs):
+    # y_true: (N, boxes, (x1, y1, x2, y2, class, best_anchor))
+    N = tf.shape(y_true)[0]
+
+    # y_true_out: (N, grid, grid, anchors, [x1, y1, x2, y2, obj, class])
+    y_true_out = tf.zeros(
+        (N, grid_size, grid_size, tf.shape(anchor_idxs)[0], 6))
+
+    anchor_idxs = tf.cast(anchor_idxs, tf.int32)
+
+    indexes = tf.TensorArray(tf.int32, 1, dynamic_size=True)
+    updates = tf.TensorArray(tf.float32, 1, dynamic_size=True)
+    idx = 0
+    for i in tf.range(N):
+        for j in tf.range(tf.shape(y_true)[1]):
+            if tf.equal(y_true[i][j][2], 0):
+                continue
+            anchor_eq = tf.equal(
+                anchor_idxs, tf.cast(y_true[i][j][5], tf.int32))
+
+            if tf.reduce_any(anchor_eq):
+                box = y_true[i][j][0:4]
+                box_xy = (y_true[i][j][0:2] + y_true[i][j][2:4]) / 2
+
+                anchor_idx = tf.cast(tf.where(anchor_eq), tf.int32)
+                grid_xy = tf.cast(box_xy // (1/grid_size), tf.int32)
+
+                # grid[y][x][anchor] = (tx, ty, bw, bh, obj, class)
+                indexes = indexes.write(
+                    idx, [i, grid_xy[1], grid_xy[0], anchor_idx[0][0]])
+                updates = updates.write(
+                    idx, [box[0], box[1], box[2], box[3], 1, y_true[i][j][4]])
+                idx += 1
+
+    # tf.print(indexes.stack())
+    # tf.print(updates.stack())
+
+    return tf.tensor_scatter_nd_update(
+        y_true_out, indexes.stack(), updates.stack())
+
+
+def transform_targets(y_train, anchors, anchor_masks, size):
+    y_outs = []
+    grid_size = size // 32
+
+    # calculate anchor index for true boxes
+    anchors = tf.cast(anchors, tf.float32)
+    anchor_area = anchors[..., 0] * anchors[..., 1]
+    box_wh = y_train[..., 2:4] - y_train[..., 0:2]
+    box_wh = tf.tile(tf.expand_dims(box_wh, -2),
+                     (1, 1, tf.shape(anchors)[0], 1))
+    box_area = box_wh[..., 0] * box_wh[..., 1]
+    intersection = tf.minimum(box_wh[..., 0], anchors[..., 0]) * \
+        tf.minimum(box_wh[..., 1], anchors[..., 1])
+    iou = intersection / (box_area + anchor_area - intersection)
+    anchor_idx = tf.cast(tf.argmax(iou, axis=-1), tf.float32)
+    anchor_idx = tf.expand_dims(anchor_idx, axis=-1)
+
+    y_train = tf.concat([y_train, anchor_idx], axis=-1)
+
+    for anchor_idxs in anchor_masks:
+        y_outs.append(transform_targets_for_output(
+            y_train, grid_size, anchor_idxs))
+        grid_size *= 2
+
+    return tuple(y_outs)
+
+
+def transform_images(x_train, size):
+    x_train = tf.image.resize(x_train, (size, size))
+    x_train = x_train / 255
+    return x_train
+
+
+# https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/using_your_own_dataset.md#conversion-script-outline-conversion-script-outline
+# Commented out fields are not required in our project
+IMAGE_FEATURE_MAP = {
+    # 'image/width': tf.io.FixedLenFeature([], tf.int64),
+    # 'image/height': tf.io.FixedLenFeature([], tf.int64),
+    # 'image/filename': tf.io.FixedLenFeature([], tf.string),
+    # 'image/source_id': tf.io.FixedLenFeature([], tf.string),
+    # 'image/key/sha256': tf.io.FixedLenFeature([], tf.string),
+    'image/encoded': tf.io.FixedLenFeature([], tf.string),
+    # 'image/format': tf.io.FixedLenFeature([], tf.string),
+    'image/object/bbox/xmin': tf.io.VarLenFeature(tf.float32),
+    'image/object/bbox/ymin': tf.io.VarLenFeature(tf.float32),
+    'image/object/bbox/xmax': tf.io.VarLenFeature(tf.float32),
+    'image/object/bbox/ymax': tf.io.VarLenFeature(tf.float32),
+    'image/object/class/text': tf.io.VarLenFeature(tf.string),
+    # 'image/object/class/label': tf.io.VarLenFeature(tf.int64),
+    # 'image/object/difficult': tf.io.VarLenFeature(tf.int64),
+    # 'image/object/truncated': tf.io.VarLenFeature(tf.int64),
+    # 'image/object/view': tf.io.VarLenFeature(tf.string),
+}
+
+
+def parse_tfrecord(tfrecord, class_table, size):
+    x = tf.io.parse_single_example(tfrecord, IMAGE_FEATURE_MAP)
+    x_train = tf.image.decode_jpeg(x['image/encoded'], channels=3)
+    x_train = tf.image.resize(x_train, (size, size))
+
+    class_text = tf.sparse.to_dense(
+        x['image/object/class/text'], default_value='')
+    labels = tf.cast(class_table.lookup(class_text), tf.float32)
+    y_train = tf.stack([tf.sparse.to_dense(x['image/object/bbox/xmin']),
+                        tf.sparse.to_dense(x['image/object/bbox/ymin']),
+                        tf.sparse.to_dense(x['image/object/bbox/xmax']),
+                        tf.sparse.to_dense(x['image/object/bbox/ymax']),
+                        labels], axis=1)
+
+    paddings = [[0, FLAGS.yolo_max_boxes - tf.shape(y_train)[0]], [0, 0]]
+    y_train = tf.pad(y_train, paddings)
+
+    return x_train, y_train
+
+
+def load_tfrecord_dataset(file_pattern, class_file, size=416):
+    LINE_NUMBER = -1  # TODO: use tf.lookup.TextFileIndex.LINE_NUMBER
+    class_table = tf.lookup.StaticHashTable(tf.lookup.TextFileInitializer(
+        class_file, tf.string, 0, tf.int64, LINE_NUMBER, delimiter="\n"), -1)
+
+    files = tf.data.Dataset.list_files(file_pattern)
+    dataset = files.flat_map(tf.data.TFRecordDataset)
+    return dataset.map(lambda x: parse_tfrecord(x, class_table, size))
+
+
+def load_fake_dataset():
+    x_train = tf.image.decode_jpeg(
+        open('./data/girl.png', 'rb').read(), channels=3)
+    x_train = tf.expand_dims(x_train, axis=0)
+
+    labels = [
+        [0.18494931, 0.03049111, 0.9435849,  0.96302897, 0],
+        [0.01586703, 0.35938117, 0.17582396, 0.6069674, 56],
+        [0.09158827, 0.48252046, 0.26967454, 0.6403017, 67]
+    ] + [[0, 0, 0, 0, 0]] * 5
+    y_train = tf.convert_to_tensor(labels, tf.float32)
+    y_train = tf.expand_dims(y_train, axis=0)
+
+    return tf.data.Dataset.from_tensor_slices((x_train, y_train))

models.py

@@ -0,0 +1,357 @@
+from absl import flags
+from absl.flags import FLAGS
+import numpy as np
+import tensorflow as tf
+from tensorflow.keras import Model
+from tensorflow.keras.layers import (
+    Add,
+    Concatenate,
+    Conv2D,
+    Input,
+    Lambda,
+    LeakyReLU,
+    MaxPool2D,
+    UpSampling2D,
+    ZeroPadding2D,
+    BatchNormalization,
+)
+from tensorflow.keras.regularizers import l2
+from tensorflow.keras.losses import (
+    binary_crossentropy,
+    sparse_categorical_crossentropy
+)
+from .utils import broadcast_iou
+
+flags.DEFINE_integer('yolo_max_boxes', 100,
+                     'maximum number of boxes per image')
+
+
+#flags.DEFINE_float('yolo_iou_threshold', 0.1, 'iou threshold')
+#flags.DEFINE_float('yolo_score_threshold', 0.1, 'score threshold')
+
+
+yolo_anchors = np.array([(10, 13), (16, 30), (33, 23), (30, 61), (62, 45),
+                         (59, 119), (116, 90), (156, 198), (373, 326)],
+                        np.float32) / 416
+yolo_anchor_masks = np.array([[6, 7, 8], [3, 4, 5], [0, 1, 2]])
+
+yolo_tiny_anchors = np.array([(10, 14), (23, 27), (37, 58),
+                              (81, 82), (135, 169),  (344, 319)],
+                             np.float32) / 416
+yolo_tiny_anchor_masks = np.array([[3, 4, 5], [0, 1, 2]])
+
+
+def DarknetConv(x, filters, size, strides=1, batch_norm=True):
+    if strides == 1:
+        padding = 'same'
+    else:
+        x = ZeroPadding2D(((1, 0), (1, 0)))(x)  # top left half-padding
+        padding = 'valid'
+    x = Conv2D(filters=filters, kernel_size=size,
+               strides=strides, padding=padding,
+               use_bias=not batch_norm, kernel_regularizer=l2(0.0005))(x)
+    if batch_norm:
+        x = BatchNormalization()(x)
+        x = LeakyReLU(alpha=0.1)(x)
+    return x
+
+
+def DarknetResidual(x, filters):
+    prev = x
+    x = DarknetConv(x, filters // 2, 1)
+    x = DarknetConv(x, filters, 3)
+    x = Add()([prev, x])
+    return x
+
+
+def DarknetBlock(x, filters, blocks):
+    x = DarknetConv(x, filters, 3, strides=2)
+    for _ in range(blocks):
+        x = DarknetResidual(x, filters)
+    return x
+
+
+def Darknet(name=None):
+    x = inputs = Input([None, None, 3])
+    x = DarknetConv(x, 32, 3)
+    x = DarknetBlock(x, 64, 1)
+    x = DarknetBlock(x, 128, 2)  # skip connection
+    x = x_36 = DarknetBlock(x, 256, 8)  # skip connection
+    x = x_61 = DarknetBlock(x, 512, 8)
+    x = DarknetBlock(x, 1024, 4)
+    return tf.keras.Model(inputs, (x_36, x_61, x), name=name)
+
+
+def DarknetTiny(name=None):
+    x = inputs = Input([None, None, 3])
+    x = DarknetConv(x, 16, 3)
+    x = MaxPool2D(2, 2, 'same')(x)
+    x = DarknetConv(x, 32, 3)
+    x = MaxPool2D(2, 2, 'same')(x)
+    x = DarknetConv(x, 64, 3)
+    x = MaxPool2D(2, 2, 'same')(x)
+    x = DarknetConv(x, 128, 3)
+    x = MaxPool2D(2, 2, 'same')(x)
+    x = x_8 = DarknetConv(x, 256, 3)  # skip connection
+    x = MaxPool2D(2, 2, 'same')(x)
+    x = DarknetConv(x, 512, 3)
+    x = MaxPool2D(2, 1, 'same')(x)
+    x = DarknetConv(x, 1024, 3)
+    return tf.keras.Model(inputs, (x_8, x), name=name)
+
+
+def YoloConv(filters, name=None):
+    def yolo_conv(x_in):
+        if isinstance(x_in, tuple):
+            inputs = Input(x_in[0].shape[1:]), Input(x_in[1].shape[1:])
+            x, x_skip = inputs
+
+            # concat with skip connection
+            x = DarknetConv(x, filters, 1)
+            x = UpSampling2D(2)(x)
+            x = Concatenate()([x, x_skip])
+        else:
+            x = inputs = Input(x_in.shape[1:])
+
+        x = DarknetConv(x, filters, 1)
+        x = DarknetConv(x, filters * 2, 3)
+        x = DarknetConv(x, filters, 1)
+        x = DarknetConv(x, filters * 2, 3)
+        x = DarknetConv(x, filters, 1)
+        return Model(inputs, x, name=name)(x_in)
+    return yolo_conv
+
+
+def YoloConvTiny(filters, name=None):
+    def yolo_conv(x_in):
+        if isinstance(x_in, tuple):
+            inputs = Input(x_in[0].shape[1:]), Input(x_in[1].shape[1:])
+            x, x_skip = inputs
+
+            # concat with skip connection
+            x = DarknetConv(x, filters, 1)
+            x = UpSampling2D(2)(x)
+            x = Concatenate()([x, x_skip])
+        else:
+            x = inputs = Input(x_in.shape[1:])
+            x = DarknetConv(x, filters, 1)
+
+        return Model(inputs, x, name=name)(x_in)
+    return yolo_conv
+
+
+def YoloOutput(filters, anchors, classes, name=None):
+    def yolo_output(x_in):
+        x = inputs = Input(x_in.shape[1:])
+        x = DarknetConv(x, filters * 2, 3)
+        x = DarknetConv(x, anchors * (classes + 5), 1, batch_norm=False)
+        x = Lambda(lambda x: tf.reshape(x, (-1, tf.shape(x)[1], tf.shape(x)[2],
+                                            anchors, classes + 5)))(x)
+        return tf.keras.Model(inputs, x, name=name)(x_in)
+    return yolo_output
+
+
+# As tensorflow lite doesn't support tf.size used in tf.meshgrid,
+# we reimplemented a simple meshgrid function that use basic tf function.
+def _meshgrid(n_a, n_b):
+
+    return [
+        tf.reshape(tf.tile(tf.range(n_a), [n_b]), (n_b, n_a)),
+        tf.reshape(tf.repeat(tf.range(n_b), n_a), (n_b, n_a))
+    ]
+
+
+def yolo_boxes(pred, anchors, classes):
+    # pred: (batch_size, grid, grid, anchors, (x, y, w, h, obj, ...classes))
+    grid_size = tf.shape(pred)[1:3]
+    box_xy, box_wh, objectness, class_probs = tf.split(
+        pred, (2, 2, 1, classes), axis=-1)
+
+    box_xy = tf.sigmoid(box_xy)
+    objectness = tf.sigmoid(objectness)
+    class_probs = tf.sigmoid(class_probs)
+    pred_box = tf.concat((box_xy, box_wh), axis=-1)  # original xywh for loss
+
+    # !!! grid[x][y] == (y, x)
+    grid = _meshgrid(grid_size[1], grid_size[0])
+    grid = tf.expand_dims(tf.stack(grid, axis=-1), axis=2)  # [gx, gy, 1, 2]
+
+    box_xy = (box_xy + tf.cast(grid, tf.float32)) / \
+        tf.cast(grid_size, tf.float32)
+    box_wh = tf.exp(box_wh) * anchors
+
+    box_x1y1 = box_xy - box_wh / 2
+    box_x2y2 = box_xy + box_wh / 2
+    bbox = tf.concat([box_x1y1, box_x2y2], axis=-1)
+
+    return bbox, objectness, class_probs, pred_box
+
+
+def yolo_nms(outputs, anchors, masks, classes):
+    # boxes, conf, type
+    b, c, t = [], [], []
+
+    for o in outputs:
+        b.append(tf.reshape(o[0], (tf.shape(o[0])[0], -1, tf.shape(o[0])[-1])))
+        c.append(tf.reshape(o[1], (tf.shape(o[1])[0], -1, tf.shape(o[1])[-1])))
+        t.append(tf.reshape(o[2], (tf.shape(o[2])[0], -1, tf.shape(o[2])[-1])))
+
+    bbox = tf.concat(b, axis=1)
+    confidence = tf.concat(c, axis=1)
+    class_probs = tf.concat(t, axis=1)
+
+    # If we only have one class, do not multiply by class_prob (always 0.5)
+    if classes == 1:
+        scores = confidence
+    else:
+        scores = confidence * class_probs
+
+    dscores = tf.squeeze(scores, axis=0)
+    scores = tf.reduce_max(dscores, [1])
+    bbox = tf.reshape(bbox, (-1, 4))
+    classes = tf.argmax(dscores, 1)
+
+    print(tf.reduce_max(scores))
+
+    selected_indices, selected_scores = tf.image.non_max_suppression_with_scores(
+        boxes=bbox,
+        scores=scores,
+        max_output_size=FLAGS.yolo_max_boxes,
+        iou_threshold=FLAGS.yolo_iou_threshold,
+        score_threshold=FLAGS.yolo_score_threshold,
+        soft_nms_sigma=0.5
+    )
+
+    num_valid_nms_boxes = tf.shape(selected_indices)[0]
+
+    selected_indices = tf.concat([selected_indices, tf.zeros(
+        FLAGS.yolo_max_boxes-num_valid_nms_boxes, tf.int32)], 0)
+    selected_scores = tf.concat([selected_scores, tf.zeros(
+        FLAGS.yolo_max_boxes-num_valid_nms_boxes, tf.float32)], -1)
+
+    boxes = tf.gather(bbox, selected_indices)
+    boxes = tf.expand_dims(boxes, axis=0)
+    scores = selected_scores
+    scores = tf.expand_dims(scores, axis=0)
+    classes = tf.gather(classes, selected_indices)
+    classes = tf.expand_dims(classes, axis=0)
+    valid_detections = num_valid_nms_boxes
+    valid_detections = tf.expand_dims(valid_detections, axis=0)
+
+    return boxes, scores, classes, valid_detections
+
+
+def YoloV3(size=None, channels=3, anchors=yolo_anchors,
+           masks=yolo_anchor_masks, classes=80, training=False):
+    x = inputs = Input([size, size, channels], name='input')
+
+    x_36, x_61, x = Darknet(name='yolo_darknet')(x)
+
+    x = YoloConv(512, name='yolo_conv_0')(x)
+    output_0 = YoloOutput(512, len(masks[0]), classes, name='yolo_output_0')(x)
+
+    x = YoloConv(256, name='yolo_conv_1')((x, x_61))
+    output_1 = YoloOutput(256, len(masks[1]), classes, name='yolo_output_1')(x)
+
+    x = YoloConv(128, name='yolo_conv_2')((x, x_36))
+    output_2 = YoloOutput(128, len(masks[2]), classes, name='yolo_output_2')(x)
+
+    if training:
+        return Model(inputs, (output_0, output_1, output_2), name='yolov3')
+
+    boxes_0 = Lambda(lambda x: yolo_boxes(x, anchors[masks[0]], classes),
+                     name='yolo_boxes_0')(output_0)
+    boxes_1 = Lambda(lambda x: yolo_boxes(x, anchors[masks[1]], classes),
+                     name='yolo_boxes_1')(output_1)
+    boxes_2 = Lambda(lambda x: yolo_boxes(x, anchors[masks[2]], classes),
+                     name='yolo_boxes_2')(output_2)
+
+    outputs = Lambda(lambda x: yolo_nms(x, anchors, masks, classes),
+                     name='yolo_nms')((boxes_0[:3], boxes_1[:3], boxes_2[:3]))
+
+    return Model(inputs, outputs, name='yolov3')
+
+
+def YoloV3Tiny(size=None, channels=3, anchors=yolo_tiny_anchors,
+               masks=yolo_tiny_anchor_masks, classes=80, training=False):
+    x = inputs = Input([size, size, channels], name='input')
+
+    x_8, x = DarknetTiny(name='yolo_darknet')(x)
+
+    x = YoloConvTiny(256, name='yolo_conv_0')(x)
+    output_0 = YoloOutput(256, len(masks[0]), classes, name='yolo_output_0')(x)
+
+    x = YoloConvTiny(128, name='yolo_conv_1')((x, x_8))
+    output_1 = YoloOutput(128, len(masks[1]), classes, name='yolo_output_1')(x)
+
+    if training:
+        return Model(inputs, (output_0, output_1), name='yolov3')
+
+    boxes_0 = Lambda(lambda x: yolo_boxes(x, anchors[masks[0]], classes),
+                     name='yolo_boxes_0')(output_0)
+    boxes_1 = Lambda(lambda x: yolo_boxes(x, anchors[masks[1]], classes),
+                     name='yolo_boxes_1')(output_1)
+    outputs = Lambda(lambda x: yolo_nms(x, anchors, masks, classes),
+                     name='yolo_nms')((boxes_0[:3], boxes_1[:3]))
+    return Model(inputs, outputs, name='yolov3_tiny')
+
+
+def YoloLoss(anchors, classes=80, ignore_thresh=0.5):
+    def yolo_loss(y_true, y_pred):
+        # 1. transform all pred outputs
+        # y_pred: (batch_size, grid, grid, anchors, (x, y, w, h, obj, ...cls))
+        pred_box, pred_obj, pred_class, pred_xywh = yolo_boxes(
+            y_pred, anchors, classes)
+        pred_xy = pred_xywh[..., 0:2]
+        pred_wh = pred_xywh[..., 2:4]
+
+        # 2. transform all true outputs
+        # y_true: (batch_size, grid, grid, anchors, (x1, y1, x2, y2, obj, cls))
+        true_box, true_obj, true_class_idx = tf.split(
+            y_true, (4, 1, 1), axis=-1)
+        true_xy = (true_box[..., 0:2] + true_box[..., 2:4]) / 2
+        true_wh = true_box[..., 2:4] - true_box[..., 0:2]
+
+        # give higher weights to small boxes
+        box_loss_scale = 2 - true_wh[..., 0] * true_wh[..., 1]
+
+        # 3. inverting the pred box equations
+        grid_size = tf.shape(y_true)[1]
+        grid = tf.meshgrid(tf.range(grid_size), tf.range(grid_size))
+        grid = tf.expand_dims(tf.stack(grid, axis=-1), axis=2)
+        true_xy = true_xy * tf.cast(grid_size, tf.float32) - \
+            tf.cast(grid, tf.float32)
+        true_wh = tf.math.log(true_wh / anchors)
+        true_wh = tf.where(tf.math.is_inf(true_wh),
+                           tf.zeros_like(true_wh), true_wh)
+
+        # 4. calculate all masks
+        obj_mask = tf.squeeze(true_obj, -1)
+        # ignore false positive when iou is over threshold
+        best_iou = tf.map_fn(
+            lambda x: tf.reduce_max(broadcast_iou(x[0], tf.boolean_mask(
+                x[1], tf.cast(x[2], tf.bool))), axis=-1),
+            (pred_box, true_box, obj_mask),
+            tf.float32)
+        ignore_mask = tf.cast(best_iou < ignore_thresh, tf.float32)
+
+        # 5. calculate all losses
+        xy_loss = obj_mask * box_loss_scale * \
+            tf.reduce_sum(tf.square(true_xy - pred_xy), axis=-1)
+        wh_loss = obj_mask * box_loss_scale * \
+            tf.reduce_sum(tf.square(true_wh - pred_wh), axis=-1)
+        obj_loss = binary_crossentropy(true_obj, pred_obj)
+        obj_loss = obj_mask * obj_loss + \
+            (1 - obj_mask) * ignore_mask * obj_loss
+        # TODO: use binary_crossentropy instead
+        class_loss = obj_mask * sparse_categorical_crossentropy(
+            true_class_idx, pred_class)
+
+        # 6. sum over (batch, gridx, gridy, anchors) => (batch, 1)
+        xy_loss = tf.reduce_sum(xy_loss, axis=(1, 2, 3))
+        wh_loss = tf.reduce_sum(wh_loss, axis=(1, 2, 3))
+        obj_loss = tf.reduce_sum(obj_loss, axis=(1, 2, 3))
+        class_loss = tf.reduce_sum(class_loss, axis=(1, 2, 3))
+
+        return xy_loss + wh_loss + obj_loss + class_loss
+    return yolo_loss

requirements.txt

@@ -0,0 +1,6 @@
+tensorflow==2.10.
+opencv-python==4.2.0.32
+lxml
+geotiff==0.2.7
+
+-e .

streamlit_trees.py

@@ -0,0 +1,184 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Tue Jul 13 16:58:28 2021
+
+@author: Alfa
+"""
+
+import time
+import streamlit as st
+import tensorflow as tf
+from tensorflow.keras.preprocessing.image import load_img
+from tensorflow.keras.preprocessing.image import img_to_array
+import numpy as np
+import pandas as pd
+
+
+from absl import app, flags, logging
+from absl.flags import FLAGS
+import cv2
+
+from yolov3_tf2.models import (YoloV3, YoloV3Tiny)
+from yolov3_tf2.dataset import transform_images
+from yolov3_tf2.utils import draw_outputs
+import matplotlib.pyplot as plt
+
+from geotiff import GeoTiff
+
+import os
+import sys
+
+
+image = load_img(r'C:\Users\alfa\Desktop\Python\Baum Projekt Labels\trees.jpg')
+image = img_to_array(image).astype('float')/255
+
+st.image(image)
+
+c1, c2, c3 = st.columns([0.2, 0.6, 0.2])
+
+file = c2.file_uploader(label='Upload GeoTIFF file')
+
+my_bar = c2.progress(0)
+
+if file == None:
+    pass
+else:
+
+    geo_tiff = GeoTiff(file)
+
+    # the original crs code
+    # geo_tiff.crs_code
+    # the current crs code
+    # geo_tiff.as_crs
+    # the shape of the tiff
+    # geo_tiff.tif_shape
+    # the bounding box in the as_crs CRS
+    # geo_tiff.tif_bBox
+    # the bounding box as WGS 84
+    # geo_tiff.tif_bBox_wgs_84
+    # the bounding box in the as_crs converted coordinates
+    # geo_tiff.tif_bBox_converted
+
+    i = geo_tiff.tif_shape[1]
+    j = geo_tiff.tif_shape[0]
+    # in the as_crs coords
+    # geo_tiff.get_coords(i, j)
+    # in WGS 84 coords
+    # print(geo_tiff.get_wgs_84_coords(i, j))
+    # print(geo_tiff.get_wgs_84_coords(0, 0))
+
+    # degrees per Pixel in x-direction
+    deg_pixel_x = (geo_tiff.get_wgs_84_coords(i, j)[
+                   0]-geo_tiff.get_wgs_84_coords(0, 0)[0])/(i, -j)[0]
+    deg_pixel_y = (geo_tiff.get_wgs_84_coords(i, j)[
+                   1]-geo_tiff.get_wgs_84_coords(0, 0)[1])/(i, -j)[1]
+
+    start_x = geo_tiff.get_wgs_84_coords(0, 0)[0]
+    start_y = geo_tiff.get_wgs_84_coords(i, j)[1]
+
+    size = 416
+
+    FLAGS(sys.argv)
+    flags.DEFINE_string('classes', './data/trees_simple.names', 'path to classes file')
+    flags.DEFINE_string('weights', './checkpoints/trees_all.tf',
+                        'path to weights file')
+    flags.DEFINE_boolean('tiny', False, 'yolov3 or yolov3-tiny')
+    flags.DEFINE_integer('size', 416, 'resize images to')
+    flags.DEFINE_string('video', './data/video.mp4',
+                        'path to video file or number for webcam)')
+    flags.DEFINE_string('output', './data/video2.mp4', 'path to output video')
+    flags.DEFINE_string('output_format', 'XVID',
+                        'codec used in VideoWriter when saving video to file')
+    flags.DEFINE_integer('num_classes', 5, 'number of classes in the model')
+
+    flags.DEFINE_float('yolo_iou_threshold', 0.5, 'iou threshold')
+    flags.DEFINE_float('yolo_score_threshold', 0.15, 'score threshold')
+
+    physical_devices = tf.config.experimental.list_physical_devices('GPU')
+    for physical_device in physical_devices:
+        tf.config.experimental.set_memory_growth(physical_device, True)
+
+    if FLAGS.tiny:
+        yolo = YoloV3Tiny(classes=FLAGS.num_classes)
+    else:
+        yolo = YoloV3(classes=FLAGS.num_classes)
+
+    yolo.load_weights(FLAGS.weights)
+    logging.info('weights loaded')
+
+    class_names = [c.strip() for c in open(FLAGS.classes).readlines()]
+    logging.info('classes loaded')
+
+    times = []
+
+    try:
+        vid = cv2.VideoCapture(int(FLAGS.video))
+    except:
+        vid = cv2.VideoCapture(FLAGS.video)
+
+    out = None
+
+    images = []
+    bboxes_x_found = []
+    bboxes_y_found = []
+    classes_found = []
+    scores_found = []
+    for m in (range(int(i/size))):
+
+        my_bar.progress(int(m/int(i/size)*100))
+
+        for n in range(int(j/size)):
+
+            area_box = [(start_x+m*deg_pixel_x*size, start_y+n*deg_pixel_y*size), (start_x+m *
+                                                                                   deg_pixel_x*size+size*deg_pixel_x, start_y+n*deg_pixel_y*size+size*deg_pixel_y)]
+
+            array = geo_tiff.read_box(area_box.copy())
+
+            img = array
+
+            # img_in = np.arra([img[:, :, :3], img[:, :, :3], img[:, :, :3]])
+            img_in = tf.expand_dims(img[:, :, :3], 0)
+            img_in = transform_images(img_in, FLAGS.size)
+
+            t1 = time.time()
+            boxes, scores, classes, nums = yolo.predict(img_in, verbose=False)
+
+            if nums > 0:
+                t2 = time.time()
+                times.append(t2-t1)
+                times = times[-20:]
+                img = draw_outputs(img, (boxes, scores, classes, nums), class_names)
+                img = cv2.putText(img, "Time: {:.2f}ms".format(sum(times)/len(times)*1000), (0, 30),
+                                  cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, (0, 0, 255), 2)
+
+                images.append(img)
+
+                for ind in range(nums[0]):
+                    classes_found.append(class_names[int(classes[0][ind])])
+                    scores_found.append(np.array(scores[0][ind]))
+                    bboxes_x_found.append(
+                        np.array(boxes[0][ind][0]*deg_pixel_x*size+start_x+m*deg_pixel_x*size))
+                    bboxes_y_found.append(
+                        np.array(boxes[0][ind][1]*deg_pixel_y*size+start_y+n*deg_pixel_y*size))
+
+                # plt.imshow(img)
+                # plt.show()
+    print()
+    print(classes_found)
+    print()
+    print(bboxes_x_found)
+    print()
+    print(bboxes_y_found)
+    found = np.concatenate((classes_found, scores_found,
+                            bboxes_x_found, bboxes_y_found), axis=1)
+   # np.savetxt(r'C:\Users\alfa\Desktop\Python\Baum Projekt Labels\found trees.txt',
+   #            found, fmt=['%s', '%.0f', '%.7f', '%.7f'])
+
+    z2 = found
+
+    z2 = pd.DataFrame(z2, columns=['Longitude', 'Lattitude', 'Class', 'Certainty'])
+
+    z3 = z2.to_csv()
+    st.download_button('Download *.csv file', z3)
+
+    st.dataframe(data=z2)

utils.py

@@ -0,0 +1,135 @@
+from absl import logging
+import numpy as np
+import tensorflow as tf
+import cv2
+
+YOLOV3_LAYER_LIST = [
+    'yolo_darknet',
+    'yolo_conv_0',
+    'yolo_output_0',
+    'yolo_conv_1',
+    'yolo_output_1',
+    'yolo_conv_2',
+    'yolo_output_2',
+]
+
+YOLOV3_TINY_LAYER_LIST = [
+    'yolo_darknet',
+    'yolo_conv_0',
+    'yolo_output_0',
+    'yolo_conv_1',
+    'yolo_output_1',
+]
+
+
+def load_darknet_weights(model, weights_file, tiny=False):
+    wf = open(weights_file, 'rb')
+    major, minor, revision, seen, _ = np.fromfile(wf, dtype=np.int32, count=5)
+
+    if tiny:
+        layers = YOLOV3_TINY_LAYER_LIST
+    else:
+        layers = YOLOV3_LAYER_LIST
+
+    for layer_name in layers:
+        sub_model = model.get_layer(layer_name)
+        for i, layer in enumerate(sub_model.layers):
+            if not layer.name.startswith('conv2d'):
+                continue
+            batch_norm = None
+            if i + 1 < len(sub_model.layers) and \
+                    sub_model.layers[i + 1].name.startswith('batch_norm'):
+                batch_norm = sub_model.layers[i + 1]
+
+            logging.info("{}/{} {}".format(
+                sub_model.name, layer.name, 'bn' if batch_norm else 'bias'))
+
+            filters = layer.filters
+            size = layer.kernel_size[0]
+            in_dim = layer.get_input_shape_at(0)[-1]
+
+            if batch_norm is None:
+                conv_bias = np.fromfile(wf, dtype=np.float32, count=filters)
+            else:
+                # darknet [beta, gamma, mean, variance]
+                bn_weights = np.fromfile(
+                    wf, dtype=np.float32, count=4 * filters)
+                # tf [gamma, beta, mean, variance]
+                bn_weights = bn_weights.reshape((4, filters))[[1, 0, 2, 3]]
+
+            # darknet shape (out_dim, in_dim, height, width)
+            conv_shape = (filters, in_dim, size, size)
+            conv_weights = np.fromfile(
+                wf, dtype=np.float32, count=np.product(conv_shape))
+            # tf shape (height, width, in_dim, out_dim)
+            conv_weights = conv_weights.reshape(
+                conv_shape).transpose([2, 3, 1, 0])
+
+            if batch_norm is None:
+                layer.set_weights([conv_weights, conv_bias])
+            else:
+                layer.set_weights([conv_weights])
+                batch_norm.set_weights(bn_weights)
+
+    assert len(wf.read()) == 0, 'failed to read all data'
+    wf.close()
+
+
+def broadcast_iou(box_1, box_2):
+    # box_1: (..., (x1, y1, x2, y2))
+    # box_2: (N, (x1, y1, x2, y2))
+
+    # broadcast boxes
+    box_1 = tf.expand_dims(box_1, -2)
+    box_2 = tf.expand_dims(box_2, 0)
+    # new_shape: (..., N, (x1, y1, x2, y2))
+    new_shape = tf.broadcast_dynamic_shape(tf.shape(box_1), tf.shape(box_2))
+    box_1 = tf.broadcast_to(box_1, new_shape)
+    box_2 = tf.broadcast_to(box_2, new_shape)
+
+    int_w = tf.maximum(tf.minimum(box_1[..., 2], box_2[..., 2]) -
+                       tf.maximum(box_1[..., 0], box_2[..., 0]), 0)
+    int_h = tf.maximum(tf.minimum(box_1[..., 3], box_2[..., 3]) -
+                       tf.maximum(box_1[..., 1], box_2[..., 1]), 0)
+    int_area = int_w * int_h
+    box_1_area = (box_1[..., 2] - box_1[..., 0]) * \
+        (box_1[..., 3] - box_1[..., 1])
+    box_2_area = (box_2[..., 2] - box_2[..., 0]) * \
+        (box_2[..., 3] - box_2[..., 1])
+    return int_area / (box_1_area + box_2_area - int_area)
+
+
+def draw_outputs(img, outputs, class_names):
+    boxes, objectness, classes, nums = outputs
+    boxes, objectness, classes, nums = boxes[0], objectness[0], classes[0], nums[0]
+    wh = np.flip(img.shape[0:2])
+    for i in range(nums):
+        x1y1 = tuple((np.array(boxes[i][0:2]) * wh).astype(np.int32))
+        x2y2 = tuple((np.array(boxes[i][2:4]) * wh).astype(np.int32))
+        img = cv2.rectangle(img, x1y1, x2y2, (255, 0, 0), 2)
+        img = cv2.putText(img, '{} {:.4f}'.format(
+            class_names[int(classes[i])], objectness[i]),
+            x1y1, cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, (0, 0, 255), 2)
+    return img
+
+
+def draw_labels(x, y, class_names):
+    img = x.numpy()
+    boxes, classes = tf.split(y, (4, 1), axis=-1)
+    classes = classes[..., 0]
+    wh = np.flip(img.shape[0:2])
+    for i in range(len(boxes)):
+        x1y1 = tuple((np.array(boxes[i][0:2]) * wh).astype(np.int32))
+        x2y2 = tuple((np.array(boxes[i][2:4]) * wh).astype(np.int32))
+        img = cv2.rectangle(img, x1y1, x2y2, (255, 0, 0), 2)
+        img = cv2.putText(img, class_names[classes[i]],
+                          x1y1, cv2.FONT_HERSHEY_COMPLEX_SMALL,
+                          1, (0, 0, 255), 2)
+    return img
+
+
+def freeze_all(model, frozen=True):
+    model.trainable = not frozen
+    if isinstance(model, tf.keras.Model):
+        for l in model.layers:
+            freeze_all(l, frozen)