From dea64611730c84a59c711c61f7f80948f82bcd31 Mon Sep 17 00:00:00 2001
From: Edmond Yoo <hj3yoo@uwaterloo.ca>
Date: Fri, 12 Oct 2018 20:12:47 +0000
Subject: [PATCH] Commit before removing YOLO
---
opencv_dnn.py | 433 +++++++++++++++++++++++++++++++++++------------------
1 files changed, 284 insertions(+), 149 deletions(-)
diff --git a/opencv_dnn.py b/opencv_dnn.py
index 8595505..03d4cc5 100644
--- a/opencv_dnn.py
+++ b/opencv_dnn.py
@@ -3,36 +3,68 @@
import pandas as pd
import imagehash as ih
import os
+import ast
import sys
import math
import random
+import collections
+from operator import itemgetter
+import time
from PIL import Image
-from .. import fetch_data
-from .. import transform_data
+import fetch_data
+import transform_data
card_width = 315
card_height = 440
-df = fetch_data.load_all_cards_text('%s/csv/rsv.csv' % transform_data.data_dir)
-df['art_hash'] = np.NaN
-for _, card_info in card_pool.iterrows():
- img_name = '%s/card_img/png/%s/%s_%s.png' % (data_dir, card_info['set'], card_info['collector_number'],
- fetch_data.get_valid_filename(card_info['name']))
- card_img = cv2.imread(img_name)
- if card_img is None:
- fetch_data.fetch_card_image(card_info, out_dir='%s/card_img/png/%s' % (data_dir, card_info['set']))
- card_img = cv2.imread(img_name)
- if card_img is None:
- print('WARNING: card %s is not found!' % img_name)
- img_art = Image.fromarray(card_img[121:580, 63:685])
- card_info['art_hash'] = ih.phash(img_card, hash_size=32, highfreq_factor=4)
-print(df['art_hash'])
+def calc_image_hashes(card_pool, save_to=None, hash_size=32, highfreq_factor=4):
+ new_pool = pd.DataFrame(columns=list(card_pool.columns.values))
+ new_pool['card_hash'] = np.NaN
+ new_pool['art_hash'] = np.NaN
+ for ind, card_info in card_pool.iterrows():
+ if ind % 100 == 0:
+ print(ind)
+ card_names = []
+ if card_info['layout'] in ['transform', 'double_faced_token']:
+ if isinstance(card_info['card_faces'], str): # For some reason, dict isn't being parsed in the previous step
+ card_faces = ast.literal_eval(card_info['card_faces'])
+ else:
+ card_faces = card_info['card_faces']
+ for i in range(len(card_faces)):
+ card_names.append(card_faces[i]['name'])
+ else: # if card_info['layout'] == 'normal':
+ card_names.append(card_info['name'])
+ for card_name in card_names:
+ card_info['name'] = card_name
+ img_name = '%s/card_img/png/%s/%s_%s.png' % (transform_data.data_dir, card_info['set'],
+ card_info['collector_number'],
+ fetch_data.get_valid_filename(card_info['name']))
+ card_img = cv2.imread(img_name)
+ if card_img is None:
+ fetch_data.fetch_card_image(card_info,
+ out_dir='%s/card_img/png/%s' % (transform_data.data_dir, card_info['set']))
+ card_img = cv2.imread(img_name)
+ if card_img is None:
+ print('WARNING: card %s is not found!' % img_name)
+ #img_art = Image.fromarray(card_img[121:580, 63:685]) # For 745*1040 size card image
+ #art_hash = ih.phash(img_art, hash_size=32, highfreq_factor=4)
+ #card_pool.at[ind, 'art_hash'] = art_hash
+ img_card = Image.fromarray(card_img)
+ card_hash = ih.phash(img_card, hash_size=hash_size, highfreq_factor=highfreq_factor)
+ #card_pool.at[ind, 'card_hash'] = card_hash
+ card_info['card_hash'] = card_hash
+ #print(new_pool.index.max())
+ new_pool.loc[0 if new_pool.empty else new_pool.index.max() + 1] = card_info
-# Disclaimer: majority of the basic framework in this file is modified from the following tutorial:
-# https://www.learnopencv.com/deep-learning-based-object-detection-using-yolov3-with-opencv-python-c/
+ new_pool = new_pool[['artist', 'border_color', 'collector_number', 'color_identity', 'colors', 'flavor_text',
+ 'image_uris', 'mana_cost', 'legalities', 'name', 'oracle_text', 'rarity', 'type_line',
+ 'set', 'set_name', 'power', 'toughness', 'art_hash', 'card_hash']]
+ if save_to is not None:
+ new_pool.to_pickle(save_to)
+ return new_pool
# www.pyimagesearch.com/2014/08/25/4-point-opencv-getperspective-transform-example/
@@ -60,6 +92,7 @@
return rect
+# www.pyimagesearch.com/2014/08/25/4-point-opencv-getperspective-transform-example/
def four_point_transform(image, pts):
# obtain a consistent order of the points and unpack them
# individually
@@ -92,14 +125,14 @@
[0, maxHeight - 1]], dtype="float32")
# compute the perspective transform matrix and then apply it
- M = cv2.getPerspectiveTransform(rect, dst)
- warped = cv2.warpPerspective(image, M, (maxWidth, maxHeight))
+ mat = cv2.getPerspectiveTransform(rect, dst)
+ warped = cv2.warpPerspective(image, mat, (maxWidth, maxHeight))
# If the image is horizontally long, rotate it by 90
if maxWidth > maxHeight:
center = (maxHeight / 2, maxHeight / 2)
- M_rot = cv2.getRotationMatrix2D(center, 270, 1.0)
- warped = cv2.warpAffine(warped, M_rot, (maxHeight, maxWidth))
+ mat_rot = cv2.getRotationMatrix2D(center, 270, 1.0)
+ warped = cv2.warpAffine(warped, mat_rot, (maxHeight, maxWidth))
# return the warped image
return warped
@@ -114,11 +147,11 @@
# Remove the bounding boxes with low confidence using non-maxima suppression
+# https://www.learnopencv.com/deep-learning-based-object-detection-using-yolov3-with-opencv-python-c/
def post_process(frame, outs, thresh_conf, thresh_nms):
frame_height = frame.shape[0]
frame_width = frame.shape[1]
-
# Scan through all the bounding boxes output from the network and keep only the
# ones with high confidence scores. Assign the box's class label as the class with the highest score.
class_ids = []
@@ -192,7 +225,7 @@
return corrected
-def find_card(img, thresh_c=5, kernel_size=(3, 3), size_ratio=0.15):
+def find_card(img, thresh_c=5, kernel_size=(3, 3), size_ratio=0.2):
# Typical pre-processing - grayscale, blurring, thresholding
img_gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
img_blur = cv2.medianBlur(img_gray, 5)
@@ -216,7 +249,7 @@
# For each contours detected, check if they are large enough and are rectangle
cnts_rect = []
ind_sort = sorted(range(len(cnts)), key=lambda i: cv2.contourArea(cnts[i]), reverse=True)
- for i in range(len(cnts)):
+ for i in range(min(len(cnts), 5)): # The card should be within top 5 largest contour
size = cv2.contourArea(cnts[ind_sort[i]])
peri = cv2.arcLength(cnts[ind_sort[i]], True)
approx = cv2.approxPolyDP(cnts[ind_sort[i]], 0.04 * peri, True)
@@ -225,38 +258,54 @@
return cnts_rect
+
+def draw_card_graph(exist_cards, card_pool, f_len):
+ w_card = 63
+ h_card = 88
+ gap = 25
+ gap_sm = 10
+ w_bar = 300
+ h_bar = 12
+ txt_scale = 0.8
+ n_cards_p_col = 4
+ w_img = gap + (w_card + gap + w_bar + gap) * 2
+ #h_img = gap + (h_card + gap) * n_cards_p_col
+ h_img = 480
+ img_graph = np.zeros((h_img, w_img, 3), dtype=np.uint8)
+ x_anchor = gap
+ y_anchor = gap
+
+ i = 0
+ for key, val in sorted(exist_cards.items(), key=itemgetter(1), reverse=True)[:n_cards_p_col * 2]:
+ card_name = key[:key.find('(') - 1]
+ card_set = key[key.find('(') + 1:key.find(')')]
+ confidence = sum(val) / f_len
+ card_info = card_pool[(card_pool['name'] == card_name) & (card_pool['set'] == card_set)].iloc[0]
+ img_name = '%s/card_img/tiny/%s/%s_%s.png' % (transform_data.data_dir, card_info['set'],
+ card_info['collector_number'],
+ fetch_data.get_valid_filename(card_info['name']))
+ card_img = cv2.imread(img_name)
+ img_graph[y_anchor:y_anchor + h_card, x_anchor:x_anchor + w_card] = card_img
+ cv2.putText(img_graph, '%s (%s)' % (card_name, card_set),
+ (x_anchor + w_card + gap, y_anchor + gap_sm + int(txt_scale * 25)), cv2.FONT_HERSHEY_SIMPLEX,
+ txt_scale, (255, 255, 255), 1)
+ cv2.rectangle(img_graph, (x_anchor + w_card + gap, y_anchor + h_card - (gap_sm + h_bar)),
+ (x_anchor + w_card + gap + int(w_bar * confidence), y_anchor + h_card - gap_sm), (0, 255, 0),
+ thickness=cv2.FILLED)
+ y_anchor += h_card + gap
+ i += 1
+ if i % n_cards_p_col == 0:
+ x_anchor += w_card + gap + w_bar + gap
+ y_anchor = gap
+ pass
+ return img_graph
+
+
+def detect_frame(net, classes, img, card_pool, thresh_conf=0.5, thresh_nms=0.4, in_dim=(416, 416), out_path=None, display=True,
+ debug=False):
+ start_1 = time.time()
+ elapsed = []
'''
- #card_dim = [630, 880]
- #for cnt in cnts_rect:
- # pts = np.float32([p[0] for p in cnt])
- # img_warp = four_point_transform(img, pts)
-
- # Check which side is longer
- len_1 = math.sqrt((cnt[0][0][0] - cnt[1][0][0]) ** 2 + (cnt[0][0][1] - cnt[1][0][1]) ** 2)
- len_2 = math.sqrt((cnt[0][0][0] - cnt[-1][0][0]) ** 2 + (cnt[0][0][1] - cnt[-1][0][1]) ** 2)
- #print(len_1, len_2)
-
- orig_corner = np.array([p[0] for p in cnt], dtype=np.float32)
- if len_1 > len_2:
- new_corner = np.array([[0, 0], [0, card_dim[1]], [card_dim[0], card_dim[1]], [card_dim[0], 0]], dtype=np.float32)
- else:
- new_corner = np.array([[0, 0], [card_dim[0], 0], [card_dim[0], card_dim[1]], [0, card_dim[1]]],
- dtype=np.float32)
-
- M = cv2.getPerspectiveTransform(orig_corner, new_corner)
- img_warp = cv2.warpPerspective(img, M, (card_dim[0], card_dim[1]))
-
- #cv2.imshow('warp', img_warp)
- #cv2.waitKey(0)
- #img_contour = cv2.drawContours(img_contour, cnts_rect, -1, (0, 255, 0), 3)
- #img_thresh = cv2.cvtColor(img_thresh, cv2.COLOR_GRAY2BGR)
- #img_erode = cv2.cvtColor(img_erode, cv2.COLOR_GRAY2BGR)
- #img_dilate = cv2.cvtColor(img_dilate, cv2.COLOR_GRAY2BGR)
- #return img_thresh, img_erode, img_contour
- '''
-
-def detect_frame(net, classes, img, thresh_conf=0.5, thresh_nms=0.4, in_dim=(416, 416), display=True, out_path=None):
- img_copy = img.copy()
# Create a 4D blob from a frame.
blob = cv2.dnn.blobFromImage(img, 1 / 255, in_dim, [0, 0, 0], 1, crop=False)
@@ -265,123 +314,177 @@
# Runs the forward pass to get output of the output layers
outs = net.forward(get_outputs_names(net))
+ elapsed.append((time.time() - start_1) * 1000)
+
+ start_2 = time.time()
+ img_result = img.copy()
# Remove the bounding boxes with low confidence
obj_list = post_process(img, outs, thresh_conf, thresh_nms)
for obj in obj_list:
class_id, confidence, box = obj
left, top, width, height = box
- draw_pred(img, class_id, classes, confidence, left, top, left + width, top + height)
-
+ draw_pred(img_result, class_id, classes, confidence, left, top, left + width, top + height)
+ elapsed.append((time.time() - start_2) * 1000)
+ '''
+ img_result = img.copy()
+ obj_list = []
# Put efficiency information. The function getPerfProfile returns the
# overall time for inference(t) and the timings for each of the layers(in layersTimes)
- t, _ = net.getPerfProfile()
- label = 'Inference time: %.2f ms' % (t * 1000.0 / cv2.getTickFrequency())
- cv2.putText(img, label, (0, 15), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 255))
+ #if display:
+ # t, _ = net.getPerfProfile()
+ # label = 'Inference time: %.2f ms' % (t * 1000.0 / cv2.getTickFrequency())
+ # cv2.putText(img_result, label, (0, 15), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 255))
+
+ '''
+ Assuming that the model has properly identified all cards, there should be 1 card that can be classified per
+ bounding box. Find the largest rectangular contour from the region of interest, and identify the card by
+ comparing the perceptual hashing of the image with the other cards' image from the database.
+ '''
+ det_cards = []
+ for i in range(len(obj_list)):
+ start_3 = time.time()
+ _, _, box = obj_list[i]
+ left, top, width, height = box
+ # Just in case the bounding box trimmed the edge of the cards, give it a bit of offset around the edge
+ offset_ratio = 0.1
+ x1 = max(0, int(left - offset_ratio * width))
+ x2 = min(img.shape[1], int(left + (1 + offset_ratio) * width))
+ y1 = max(0, int(top - offset_ratio * height))
+ y2 = min(img.shape[0], int(top + (1 + offset_ratio) * height))
+ img_snip = img[y1:y2, x1:x2]
+ cnts = find_card(img_snip)
+ elapsed.append((time.time() - start_3) * 1000)
+ if len(cnts) > 0:
+ start_4 = time.time()
+ cnt = cnts[0] # The largest (rectangular) contour
+ pts = np.float32([p[0] for p in cnt])
+ img_warp = four_point_transform(img_snip, pts)
+ img_warp = cv2.resize(img_warp, (card_width, card_height))
+ elapsed.append((time.time() - start_4) * 1000)
+ '''
+ img_art = img_warp[47:249, 22:294]
+ img_art = Image.fromarray(img_art.astype('uint8'), 'RGB')
+ art_hash = ih.phash(img_art, hash_size=32, highfreq_factor=4)
+ card_pool['hash_diff'] = card_pool['art_hash'] - art_hash
+ min_cards = card_pool[card_pool['hash_diff'] == min(card_pool['hash_diff'])]
+ card_name = min_cards.iloc[0]['name']
+ '''
+ start_5 = time.time()
+ img_card = Image.fromarray(img_warp.astype('uint8'), 'RGB')
+ card_hash = ih.phash(img_card, hash_size=32, highfreq_factor=4).hash.flatten()
+ card_pool['hash_diff'] = card_pool['card_hash'].apply(lambda x: np.count_nonzero(x != card_hash))
+ min_cards = card_pool[card_pool['hash_diff'] == min(card_pool['hash_diff'])]
+ card_name = min_cards.iloc[0]['name']
+ card_set = min_cards.iloc[0]['set']
+ det_cards.append((card_name, card_set))
+ hash_diff = min_cards.iloc[0]['hash_diff']
+ elapsed.append((time.time() - start_5) * 1000)
+
+ # Display the result
+ if debug:
+ # cv2.rectangle(img_warp, (22, 47), (294, 249), (0, 255, 0), 2)
+ cv2.putText(img_warp, card_name + ', ' + str(hash_diff), (0, 50),
+ cv2.FONT_HERSHEY_SIMPLEX, 1, (255, 255, 255), 2)
+ cv2.putText(img_result, card_name, (x1, y1), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (255, 255, 255), 2)
+ if debug:
+ cv2.imshow('card#%d' % i, img_warp)
+ elif debug:
+ cv2.imshow('card#%d' % i, np.zeros((1, 1), dtype=np.uint8))
if out_path is not None:
- cv2.imwrite(out_path, img.astype(np.uint8))
- if display:
- #no_glare = remove_glare(img_copy)
- #img_concat = np.concatenate((img, no_glare), axis=1)
- cv2.imshow('result', img)
- '''
- for i in range(len(obj_list)):
- class_id, confidence, box = obj_list[i]
- left, top, width, height = box
- img_snip = img_copy[max(0, top):min(img.shape[0], top + height),
- max(0, left):min(img.shape[1], left + width)]
- img_thresh, img_dilate, img_canny, img_hough = find_card(img_snip)
- img_concat = np.concatenate((img_snip, img_thresh, img_dilate, img_canny, img_hough), axis=1)
- cv2.imshow('feature#%d' % i, img_concat)
- '''
- cv2.waitKey(0)
- cv2.destroyAllWindows()
-
- return obj_list
+ cv2.imwrite(out_path, img_result.astype(np.uint8))
+ elapsed = [(time.time() - start_1) * 1000] + elapsed
+ #print(', '.join(['%.2f' % t for t in elapsed]))
+ return obj_list, det_cards, img_result
-def detect_video(net, classes, capture, thresh_conf=0.5, thresh_nms=0.4, in_dim=(416, 416), display=True, out_path=None):
+def detect_video(net, classes, capture, card_pool, thresh_conf=0.5, thresh_nms=0.4, in_dim=(416, 416), out_path=None,
+ display=True, debug=False):
if out_path is not None:
- vid_writer = cv2.VideoWriter(out_path, cv2.VideoWriter_fourcc('M', 'J', 'P', 'G'), 30,
- (round(capture.get(cv2.CAP_PROP_FRAME_WIDTH)),
- round(capture.get(cv2.CAP_PROP_FRAME_HEIGHT))))
+ img_graph = draw_card_graph({}, None, -1) # Black image of the graph just to get the dimension
+ width = round(capture.get(cv2.CAP_PROP_FRAME_WIDTH)) + img_graph.shape[1]
+ height = max(round(capture.get(cv2.CAP_PROP_FRAME_HEIGHT)), img_graph.shape[0])
+ vid_writer = cv2.VideoWriter(out_path, cv2.VideoWriter_fourcc(*'MJPG'), 10.0, (width, height))
max_num_obj = 0
- while True:
- ret, frame = capture.read()
- if not ret:
- # End of video
- print("End of video. Press any key to exit")
- cv2.waitKey(0)
- break
- img = frame.copy()
- obj_list = detect_frame(net, classes, frame, thresh_conf=thresh_conf, thresh_nms=thresh_nms, in_dim=in_dim,
- display=False, out_path=None)
- #cnts_rect = find_card(img)
- max_num_obj = max(max_num_obj, len(obj_list))
- if display:
- img_result = frame.copy()
- #img_result = cv2.drawContours(img_result, cnts_rect, -1, (0, 255, 0), 2)
- #for i in range(len(cnts_rect)):
- # pts = np.float32([p[0] for p in cnts_rect[i]])
- # img_warp = four_point_transform(img, pts)
- # cv2.imshow('card#%d' % i, img_warp)
- #for i in range(len(cnts_rect), max_num_obj):
- # cv2.imshow('card#%d' % i, np.zeros((1, 1), dtype=np.uint8))
- #no_glare = remove_glare(img)
- #img_thresh, img_erode, img_contour = find_card(no_glare)
- #img_concat = np.concatenate((no_glare, img_contour), axis=1)
-
- for i in range(len(obj_list)):
- class_id, confidence, box = obj_list[i]
- left, top, width, height = box
- offset_ratio = 0.1
- x1 = max(0, int(left - offset_ratio * width))
- x2 = min(img.shape[1], int(left + (1 + offset_ratio) * width))
- y1 = max(0, int(top - offset_ratio * height))
- y2 = min(img.shape[0], int(top + (1 + offset_ratio) * height))
- img_snip = img[y1:y2, x1:x2]
- cnts = find_card(img_snip)
- if len(cnts) > 0:
- cnt = cnts[-1]
- pts = np.float32([p[0] for p in cnt])
- img_warp = four_point_transform(img_snip, pts)
- img_warp = cv2.resize(img_warp, (card_width, card_height))
- img_card = img_warp[47:249, 22:294]
- img_card = Image.fromarray(img_card.astype('uint8'), 'RGB')
- card_hash = ih.phash(img_card, hash_size=32, highfreq_factor=4)
- print(card_hash - rift_hash)
- #img_thresh, img_dilate, img_contour = find_card(img_snip)
- #img_concat = np.concatenate((img_snip, img_contour), axis=1)
- cv2.rectangle(img_warp, (22, 47), (294, 249), (0, 255, 0), 2)
-
- cv2.imshow('card#%d' % i, img_warp)
+ f_len = 10 # number of frames to consider to check for existing cards
+ exist_cards = {}
+ try:
+ while True:
+ ret, frame = capture.read()
+ start_time = time.time()
+ if not ret:
+ # End of video
+ print("End of video. Press any key to exit")
+ cv2.waitKey(0)
+ break
+ # Use the YOLO model to identify each cards annonymously
+ start_yolo = time.time()
+ obj_list, det_cards, img_result = detect_frame(net, classes, frame, card_pool, thresh_conf=thresh_conf,
+ thresh_nms=thresh_nms, in_dim=in_dim, out_path=None,
+ display=display, debug=debug)
+ elapsed_yolo = (time.time() - start_yolo) * 1000
+ # If the card was already detected in the previous frame, append 1 to the list
+ # If the card previously detected was not found in this trame, append 0 to the list
+ # If the card wasn't previously detected, make a new list and add 1 to it
+ # If the same card is detected multiple times in the same frame, keep track of the duplicates
+ # The confidence will be calculated based on the number of frames the card was detected for
+ det_cards_count = collections.Counter(det_cards).items()
+ det_cards_list = []
+ for card, count in det_cards_count:
+ card_name, card_set = card
+ for i in range(count): 1
+ key = '%s (%s) #%d' % (card_name, card_set, i + 1)
+ det_cards_list.append(key)
+ gone = []
+ for key, val in exist_cards.items():
+ if key in det_cards_list:
+ exist_cards[key] = exist_cards[key][1 - f_len:] + [1]
else:
+ exist_cards[key] = exist_cards[key][1 - f_len:] + [0]
+ if len(val) == f_len and sum(val) == 0:
+ gone.append(key)
+ for key in det_cards_list:
+ if key not in exist_cards.keys():
+ exist_cards[key] = [1]
+ for key in gone:
+ exist_cards.pop(key)
+ start_graph = time.time()
+ img_graph = draw_card_graph(exist_cards, card_pool, f_len)
+ elapsed_graph = (time.time() - start_graph) * 1000
+ if debug:
+ max_num_obj = max(max_num_obj, len(obj_list))
+ for i in range(len(obj_list), max_num_obj):
cv2.imshow('card#%d' % i, np.zeros((1, 1), dtype=np.uint8))
- for i in range(len(obj_list), max_num_obj):
- cv2.imshow('card#%d' % i, np.zeros((1, 1), dtype=np.uint8))
- cv2.imshow('result', img_result)
- #if len(obj_list) > 0:
- # cv2.waitKey(0)
+ start_display = time.time()
+ img_save = np.zeros((height, width, 3), dtype=np.uint8)
+ img_save[0:img_result.shape[0], 0:img_result.shape[1]] = img_result
+ img_save[0:img_graph.shape[0], img_result.shape[1]:img_result.shape[1] + img_graph.shape[1]] = img_graph
+ if display:
+ cv2.imshow('result', img_save)
+ elapsed_display = (time.time() - start_display) * 1000
+ elapsed_ms = (time.time() - start_time) * 1000
+ #print('Elapsed time: %.2f ms, %.2f, %.2f, %.2f' % (elapsed_ms, elapsed_yolo, elapsed_graph, elapsed_display))
+ if out_path is not None:
+ vid_writer.write(img_save.astype(np.uint8))
+ cv2.waitKey(1)
+ except KeyboardInterrupt:
+ capture.release()
if out_path is not None:
- vid_writer.write(frame.astype(np.uint8))
- cv2.waitKey(1)
-
- if out_path is not None:
- vid_writer.release()
- cv2.destroyAllWindows()
+ vid_writer.release()
+ cv2.destroyAllWindows()
def main():
# Specify paths for all necessary files
- test_path = os.path.abspath('../data/test4.mp4')
+ test_path = os.path.abspath('test_file/test4.mp4')
#weight_path = 'backup/tiny_yolo_10_39500.weights'
#cfg_path = 'cfg/tiny_yolo_10.cfg'
#class_path = "data/obj_10.names"
weight_path = 'weights/second_general/tiny_yolo_final.weights'
- cfg_path = 'cfg/tiny_yolo.cfg'
+ cfg_path = 'cfg/tiny_yolo_old.cfg'
class_path = 'data/obj.names'
out_dir = 'out'
if not os.path.isfile(test_path):
@@ -397,6 +500,36 @@
print('The class file %s doesn\'t exist!' % os.path.abspath(test_path))
return
+
+ '''
+ df_list = []
+ for set_name in fetch_data.all_set_list:
+ csv_name = '%s/csv/%s.csv' % (transform_data.data_dir, set_name)
+ df = fetch_data.load_all_cards_text(csv_name)
+ df_list.append(df)
+ #print(df)
+ card_pool = pd.concat(df_list, sort=True)
+ card_pool.reset_index(drop=True, inplace=True)
+ card_pool.drop('Unnamed: 0', axis=1, inplace=True, errors='ignore')
+ for hash_size in [8, 16, 32, 64]:
+ for highfreq_factor in [4, 8, 16, 32]:
+ pck_name = 'card_pool_%d_%d.pck' % (hash_size, highfreq_factor)
+ if not os.path.exists(pck_name):
+ print(pck_name)
+ calc_image_hashes(card_pool, save_to=pck_name, hash_size=hash_size, highfreq_factor=highfreq_factor)
+ '''
+ #csv_name = '%s/csv/%s.csv' % (transform_data.data_dir, 'rtr')
+ #card_pool = fetch_data.load_all_cards_text(csv_name)
+ #card_pool = calc_image_hashes(card_pool, save_to='card_pool.pck')
+ #return
+ card_pool = pd.read_pickle('card_pool_32_4.pck')
+ #card_pool = card_pool[(card_pool['set'] == 'rtr') | (card_pool['set'] == 'isd')]
+ card_pool = card_pool[['name', 'set', 'collector_number', 'card_hash']]
+
+ # ImageHash is basically just one numpy.ndarray with (hash_size)^2 number of bits. pre-emptively flattening it
+ # significantly increases speed for subtracting hashes in the future.
+ card_pool['card_hash'] = card_pool['card_hash'].apply(lambda x: x.hash.flatten())
+
thresh_conf = 0.01
thresh_nms = 0.8
@@ -413,16 +546,18 @@
if out_dir is None or out_dir == '':
out_path = None
else:
- out_path = out_dir + '/' + os.path.split(test_path)[1]
+ f_name = os.path.split(test_path)[1]
+ out_path = out_dir + '/' + f_name[:f_name.find('.')] + '.avi'
# Check if test file is image or video
test_ext = test_path[test_path.find('.') + 1:]
if test_ext in ['jpg', 'jpeg', 'bmp', 'png', 'tiff']:
img = cv2.imread(test_path)
- detect_frame(net, classes, img, out_path=out_path, thresh_conf=thresh_conf, thresh_nms=thresh_nms)
+ detect_frame(net, classes, img, card_pool, out_path=out_path, thresh_conf=thresh_conf, thresh_nms=thresh_nms)
else:
capture = cv2.VideoCapture(0)
- detect_video(net, classes, capture, out_path=out_path, thresh_conf=thresh_conf, thresh_nms=thresh_nms)
+ detect_video(net, classes, capture, card_pool, out_path=out_path, thresh_conf=thresh_conf, thresh_nms=thresh_nms,
+ display=True, debug=False)
capture.release()
pass
--
Gitblit v1.10.0