X-Git-Url: https://fleuret.org/cgi-bin/gitweb/gitweb.cgi?a=blobdiff_plain;f=sky.py;h=6ef8a3af2184777c223dfd1803647a49bd3dd54d;hb=167c56ace610c3b975c702203bb7c7ddf74930ae;hp=11641853d8e8081f1cc7d0cf63d112f1ba30b518;hpb=aae01e186a959131b446d0365c6b951bacfd71d9;p=culture.git diff --git a/sky.py b/sky.py index 1164185..6ef8a3a 100755 --- a/sky.py +++ b/sky.py @@ -5,7 +5,7 @@ # Written by Francois Fleuret -import math, sys, tqdm, os +import math, sys, tqdm, os, warnings import torch, torchvision @@ -37,8 +37,6 @@ class Sky(problem.Problem): token_background = 0 first_bird_token = 1 nb_bird_tokens = colors.size(0) - 1 - token_forward = first_bird_token + nb_bird_tokens - token_backward = token_forward + 1 token2char = ( "_" + "".join([chr(ord("A") + n) for n in range(len(colors) - 1)]) + "><" @@ -60,9 +58,6 @@ class Sky(problem.Problem): self.nb_iterations = nb_iterations self.avoid_collision = avoid_collision - def direction_tokens(self): - return self.token_forward, self.token_backward - def generate_frame_sequences(self, nb): frame_sequences = [] @@ -157,32 +152,8 @@ class Sky(problem.Problem): ###################################################################### - def generate_token_sequences(self, nb): - frame_sequences = self.generate_frame_sequences(nb) - - result = [] - - for frame_sequence in frame_sequences: - a = [] - if torch.rand(1) < 0.5: - for frame in frame_sequence: - if len(a) > 0: - a.append(torch.tensor([self.token_forward])) - a.append(frame.flatten()) - else: - for frame in reversed(frame_sequence): - if len(a) > 0: - a.append(torch.tensor([self.token_backward])) - a.append(frame.flatten()) - - result.append(torch.cat(a, dim=0)[None, :]) - - return torch.cat(result, dim=0) - - ###################################################################### - def frame2img(self, x, scale=15): - x = x.reshape(-1, self.height, self.width) + x = x.reshape(x.size(0), self.height, -1) m = torch.logical_and( x >= 0, x < self.first_bird_token + self.nb_bird_tokens ).long() @@ -208,92 +179,138 @@ class Sky(problem.Problem): return x - def seq2img(self, seq, scale=15): - all = [ - self.frame2img( - seq[:, : self.height * self.width].reshape(-1, self.height, self.width), - scale, - ) - ] - - separator = torch.full((seq.size(0), 3, self.height * scale - 1, 1), 0) - - t = self.height * self.width - - while t < seq.size(1): - direction_tokens = seq[:, t] - t += 1 - - direction_images = self.colors[ - torch.full( - (direction_tokens.size(0), self.height * scale - 1, scale), 0 - ) - ].permute(0, 3, 1, 2) - - for n in range(direction_tokens.size(0)): - if direction_tokens[n] == self.token_forward: - for k in range(scale): - for l in [0, 1]: - direction_images[ - n, - :, - (self.height * scale) // 2 - scale // 2 + k - l, - 3 + scale // 2 - abs(k - scale // 2), - ] = 0 - elif direction_tokens[n] == self.token_backward: - for k in range(scale): - for l in [0, 1]: - direction_images[ - n, - :, - (self.height * scale) // 2 - scale // 2 + k - l, - 3 + abs(k - scale // 2), - ] = 0 - else: - for k in range(2, scale - 2): - for l in [0, 1]: - direction_images[ - n, - :, - (self.height * scale) // 2 - scale // 2 + k - l, - k, - ] = 0 - direction_images[ - n, - :, - (self.height * scale) // 2 - scale // 2 + k - l, - scale - 1 - k, - ] = 0 - - all += [ - separator, - direction_images, - separator, - self.frame2img( - seq[:, t : t + self.height * self.width].reshape( - -1, self.height, self.width - ), - scale, - ), - ] - - t += self.height * self.width - - return torch.cat(all, dim=3) - def seq2str(self, seq): result = [] for s in seq: result.append("".join([self.token2char[v] for v in s])) return result - def save_image(self, input, result_dir, filename): - img = self.seq2img(input.to("cpu")) + def save_image( + self, + result_dir, + filename, + prompts, + answers, + predicted_prompts=None, + predicted_answers=None, + ): + if predicted_prompts is None: + predicted_prompts = 255 + + if predicted_answers is None: + predicted_answers = 255 + + def add_frame(x, c, margin, bottom=False): + if bottom: + h, w, di, dj = x.size(2) + margin, x.size(3), 0, 0 + else: + h, w, di, dj = ( + x.size(2) + 2 * margin, + x.size(3) + 2 * margin, + margin, + margin, + ) + + y = x.new_full((x.size(0), x.size(1), h, w), 0) + + if type(c) is int: + y[...] = c + else: + c = c.long()[:, None] + c = c * torch.tensor([0, 0, 0], device=c.device) + ( + 1 - c + ) * torch.tensor([255, 255, 255], device=c.device) + y[...] = c[:, :, None, None] + + y[:, :, di : di + x.size(2), dj : dj + x.size(3)] = x + + return y + + margin = 4 + + img_prompts = add_frame(self.frame2img(prompts.to("cpu")), c=0, margin=1) + h = img_prompts.size(2) + img_answers = add_frame(self.frame2img(answers.to("cpu")), c=0, margin=1) + + img_prompts = add_frame(img_prompts, c=255, margin=margin, bottom=True) + img_answers = add_frame(img_answers, c=255, margin=margin, bottom=True) + + img_prompts = add_frame( + img_prompts, c=predicted_prompts, margin=margin, bottom=True + ) + img_answers = add_frame( + img_answers, c=predicted_answers, margin=margin, bottom=True + ) + + marker_size = 16 + + separator = img_prompts.new_full( + ( + img_prompts.size(0), + img_prompts.size(1), + img_prompts.size(2), + marker_size, + ), + 255, + ) + + separator[:, :, 0] = 0 + separator[:, :, h - 1] = 0 + + for k in range(1, 2 * marker_size - 8): + i = k - (marker_size - 4) + j = marker_size - 5 - abs(i) + separator[:, :, h // 2 - 1 + i, 2 + j] = 0 + separator[:, :, h // 2 - 1 + i + 1, 2 + j] = 0 + + img = torch.cat([img_prompts, separator, img_answers], dim=3) + image_name = os.path.join(result_dir, filename) - torchvision.utils.save_image(img.float() / 255.0, image_name, nrow=6, padding=4) + torchvision.utils.save_image( + img.float() / 255.0, image_name, nrow=6, padding=margin * 4, pad_value=1.0 + ) - def save_quizzes(self, input, result_dir, filename_prefix): - self.save_image(input, result_dir, filename_prefix + ".png") + ###################################################################### + + def nb_token_values(self): + return len(self.colors) + + def generate_prompts_and_answers(self, nb): + frame_sequences = self.generate_frame_sequences(nb) + frame_sequences = torch.cat([x[None] for x in frame_sequences], dim=0) + + prompts = frame_sequences[:, : frame_sequences.size(1) // 2].flatten(1) + + answers = frame_sequences[:, frame_sequences.size(1) // 2 :].flatten(1) + + # warnings.warn("dirty test with longer answer", RuntimeWarning) + # answers = torch.cat( + # [ + # frame_sequences[:, frame_sequences.size(1) // 2 :], + # frame_sequences[:, frame_sequences.size(1) // 2 :], + # ], + # dim=3, + # ).flatten(1) + + return prompts, answers + + def save_quizzes( + self, + result_dir, + filename_prefix, + prompts, + answers, + predicted_prompts=None, + predicted_answers=None, + ): + self.save_image( + result_dir, + filename_prefix + ".png", + prompts, + answers, + predicted_prompts, + predicted_answers, + ) ###################################################################### @@ -301,12 +318,21 @@ class Sky(problem.Problem): if __name__ == "__main__": import time - sky = Sky(height=6, width=8, speed=4, nb_iterations=2) + sky = Sky(height=6, width=8, speed=1, nb_iterations=4) - start_time = time.perf_counter() - token_sequences = sky.generate_token_sequences(nb=64) - delay = time.perf_counter() - start_time - print(f"{token_sequences.size(0)/delay:02f} seq/s") + prompts, answers = sky.generate_prompts_and_answers(4) + + predicted_prompts = torch.rand(prompts.size(0)) < 0.5 + predicted_answers = torch.rand(answers.size(0)) < 0.5 + + sky.save_quizzes( + "/tmp", "test", prompts, answers, predicted_prompts, predicted_answers + ) + + # start_time = time.perf_counter() + # token_sequences = sky.generate_token_sequences(nb=64) + # delay = time.perf_counter() - start_time + # print(f"{token_sequences.size(0)/delay:02f} seq/s") # print(sky.seq2str(seq[:4])) @@ -324,9 +350,9 @@ if __name__ == "__main__": # seq = (1 - m) * seq + m * 23 # print(seq.size()) - img = sky.seq2img(token_sequences) + # img = sky.seq2img(token_sequences) # print(img.size()) - torchvision.utils.save_image( - img.float() / 255.0, "/tmp/world.png", nrow=6, padding=6, pad_value=0 - ) + # torchvision.utils.save_image( + # img.float() / 255.0, "/tmp/world.png", nrow=6, padding=6, pad_value=0 + # )